WO2025209060A1 - Computing power scheduling method, apparatus, and device - Google Patents

Abstract

The present disclosure provides a computing power scheduling method, an apparatus, and a device. The method comprises: a first device acquires group computing power service requirements of a user group; the first device generates a computing power scheduling policy on the basis of the group computing power service requirements; and the first device sends the computing power scheduling policy to a node comprised in the user group and/or the computing power scheduling policy.

Description

Computing power scheduling method, device and equipment

This disclosure claims priority to the Chinese patent application filed with the China Patent Office on April 3, 2024, with application number 202410400034.3 and application name “Computing Power Scheduling Method, Device and Equipment”, the entire contents of which are incorporated herein by reference.

Technical Field

The present disclosure relates to the field of communication technology, and in particular to a computing power scheduling method, apparatus, and device.

Background Art

Currently, computing networks (including those for bearer networks and mobile computing networks) orchestrate computing services independently, tailored to the business needs of a single user. There has been no research or implementation of group-level orchestration for computing services used by multiple users with specific business relationships, and the concept of computing user groups has not been proposed. If each user independently initiates a computing service request, the computing orchestration center will need to orchestrate computing services and generate scheduling strategies for each user. This not only consumes excessive computing network resources but also fails to effectively achieve multi-user business collaboration, significantly reducing the efficiency of the system's computing orchestration and scheduling.

Summary of the Invention

The purpose of the present disclosure is to provide a computing power scheduling method, device and equipment to solve the problem that related computing power service scheduling strategies reduce work efficiency.

An embodiment of the present disclosure provides a computing power scheduling strategy, which is executed by a first device. The method includes:

The first device obtains the group computing power service demand of the user group;

The first device generates a computing power scheduling strategy according to the computing power service demand of the group;

The first device sends the computing power scheduling policy to the user group and/or the nodes included in the computing power scheduling policy.

In some embodiments, the group computing power business requirement includes at least one of the following:

User IDs included in the user group;

Identification of the user group;

An identifier of a first target user within the user group, where the first target user is a user with group management authority;

Business type;

Group computing power requirements;

Group network requirements.

In some embodiments, the group computing power requirement includes at least one of the following:

Computing power application scenarios;

Computing service type;

Computing resource location;

Hash rate usage time;

Computing resource type;

The size of computing resources;

Computing power and energy consumption requirements.

In some embodiments, the group network requirement includes at least one of the following:

bandwidth;

Delay;

Packet loss rate.

In some embodiments, obtaining the group computing power service demand of the user group includes:

Receive the group computing power service requirements of the user group sent by the computing power network access node;

or,

Receive the group computing power business requirements of the user group sent by the user.

In some embodiments, obtaining the group computing power service requirements of the user group includes at least one of the following:

Obtain computing power business requirements of multiple users, where the multiple users belong to the same user group;

Process each user's computing power business requirements separately to obtain the user's computing power requirement list and network requirement list;

Aggregate the computing power requirement lists of multiple users and aggregate the network requirement lists of multiple users to obtain the group computing power service requirements of the user group.

In some embodiments, the aggregating of computing power requirement lists of multiple users includes:

According to the first aggregation principle, the computing power demand lists of multiple users are aggregated;

The first aggregation principle includes at least one of the following:

Aggregation principles related to computing resource types;

Aggregation principles related to computing power;

Aggregation principles related to the location of computing resources;

Aggregation principles related to computing power usage time.

In some embodiments, aggregating the network demand lists of multiple users includes:

According to the second aggregation principle, the network demand lists of multiple users are aggregated;

The second aggregation principle includes at least one of the following:

Group maximum bandwidth principle;

Group minimum delay principle;

Group minimum packet loss rate principle.

In some embodiments, generating a computing power scheduling strategy based on the group computing power service demand includes:

Selecting computing nodes and/or computing services for the user group based on the group computing service requirements;

Generate a computing power scheduling policy based on the selected computing power nodes and/or computing power services;

Among them, the computing power scheduling strategy includes routing path information of the computing power business, and the routing path information includes at least one of the following: information of the computing power network access node, information of the computing power routing node, information of the computing power network exit node, information of the computing power node, and information of the computing power service.

In some embodiments, sending the computing power scheduling policy to the user group includes:

The computing power scheduling policy is sent to the computing power network access node, so that the computing power network access node sends the computing power scheduling policy to the user corresponding to the computing power network access node.

In some embodiments, when multiple users access the network through the same computing power network access node, the computing power scheduling strategy includes a routing path information;

or,

When multiple users access the network through different computing power network access nodes, the computing power scheduling strategy includes public path information and independent path information of the user group.

In some embodiments, the method further comprises:

Allocating a maximum guaranteed bandwidth to the user group;

and/or,

Priorities are assigned to the user groups, and resources are reserved or preempted for the user groups according to the priorities.

An embodiment of the present disclosure provides a computing power scheduling method, which is performed by a second device. The method includes:

The second device receives the computing power scheduling policy sent by the first device, where the computing power scheduling policy is generated based on the group computing power service demand of the user group.

In some embodiments, the group computing power business requirement includes at least one of the following:

User IDs included in the user group;

Identification of the user group;

An identifier of a first target user within the user group, where the first target user is a user with group management authority;

Business type;

Group computing power requirements;

Group network requirements.

In some embodiments, the group computing power requirement includes at least one of the following:

Computing power application scenarios;

Computing service type;

Computing resource location;

Hash rate usage time;

Computing resource type;

The size of computing resources;

Computing power and energy consumption requirements.

In some embodiments, the group network requirement includes at least one of the following:

bandwidth;

Delay;

Packet loss rate.

In some embodiments, the second device includes at least one of the following:

Computing power network access node;

Computing power routing nodes;

Hash power network exit node;

Computing power node.

In some embodiments, the computing power scheduling strategy includes routing path information of the computing power service, and the routing path information includes at least one of the following:

Information about nodes connected to the computing network;

Information about computing power routing nodes;

Information about the computing network’s exit nodes;

Information about computing power nodes;

Information about computing power services.

In some embodiments, when multiple users access the network through the same computing power network access node, the computing power scheduling strategy includes a routing path information;

or,

When multiple users access the network through different computing power network access nodes, the computing power scheduling strategy includes public path information and independent path information of the user group.

In some embodiments, the method further comprises:

Obtain group computing power business requirements sent by user groups;

Send the group computing power service demand to the first device.

In some embodiments, obtaining the group computing power service demand sent by the user group includes at least one of the following:

Obtain computing power business requirements of multiple users, where the multiple users belong to the same user group;

Process each user's computing power business requirements separately to obtain the user's computing power requirement list and network requirement list;

Aggregate the computing power requirement lists of multiple users and aggregate the network requirement lists of multiple users to obtain the group computing power service requirements of the user group.

In some embodiments, the aggregating of computing power requirement lists of multiple users includes:

According to the first aggregation principle, the computing power demand lists of multiple users are aggregated;

The first aggregation principle includes at least one of the following:

Aggregation principles related to computing resource types;

Aggregation principles related to computing power;

Aggregation principles related to the location of computing resources;

Aggregation principles related to computing power usage time.

In some embodiments, aggregating the network demand lists of multiple users includes:

According to the second aggregation principle, the network demand lists of multiple users are aggregated;

The second aggregation principle includes at least one of the following:

Group maximum bandwidth principle;

Group minimum delay principle;

Group minimum packet loss rate principle.

In some embodiments, the method further comprises:

Broadcast or multicast the computing power scheduling strategy to users.

An embodiment of the present disclosure provides a communication device, which is a first device and includes: a memory, a transceiver, and a processor.

A memory for storing a computer program; a transceiver for receiving and sending data under the control of the processor; and a processor for reading the computer program in the memory and performing the following operations:

Obtain the group computing power business requirements of the user group;

Generate a computing power scheduling strategy based on the computing power business requirements of the group;

Send the computing power scheduling policy to the user group and/or the nodes included in the computing power scheduling policy.

In some embodiments, the group computing power business requirement includes at least one of the following:

User IDs included in the user group;

Identification of the user group;

An identifier of a first target user within the user group, where the first target user is a user with group management authority;

Business type;

Group computing power requirements;

Group network requirements.

In some embodiments, the group computing power requirement includes at least one of the following:

Computing power application scenarios;

Computing service type;

Computing resource location;

Hashrate usage time;

Computing resource type;

The size of computing resources;

Computing power and energy consumption requirements.

In some embodiments, the group network requirement includes at least one of the following:

bandwidth;

Delay;

Packet loss rate.

In some embodiments, the processor is configured to read the computer program in the memory and perform the following operations:

Receive the group computing power service requirements of the user group sent by the computing power network access node;

or,

Receive the group computing power business requirements of the user group sent by the user.

In some embodiments, the processor is configured to read the computer program in the memory and perform at least one of the following operations:

Obtain computing power business requirements of multiple users, where the multiple users belong to the same user group;

Process each user's computing power business requirements separately to obtain the user's computing power requirement list and network requirement list;

Aggregate the computing power requirement lists of multiple users and aggregate the network requirement lists of multiple users to obtain the group computing power service requirements of the user group.

In some embodiments, the processor is configured to read the computer program in the memory and perform the following operations:

According to the first aggregation principle, the computing power demand lists of multiple users are aggregated;

The first aggregation principle includes at least one of the following:

Aggregation principles related to computing resource types;

Aggregation principles related to computing power;

Aggregation principles related to the location of computing resources;

Aggregation principles related to computing power usage time.

In some embodiments, the processor is configured to read the computer program in the memory and perform the following operations:

According to the second aggregation principle, the network demand lists of multiple users are aggregated;

The second aggregation principle includes at least one of the following:

Group maximum bandwidth principle;

Group minimum delay principle;

Group minimum packet loss rate principle.

In some embodiments, the processor is configured to read the computer program in the memory and perform the following operations:

Selecting computing nodes and/or computing services for the user group based on the group computing service requirements;

Generate a computing power scheduling policy based on the selected computing power nodes and/or computing power services;

Among them, the computing power scheduling strategy includes routing path information of the computing power business, and the routing path information includes at least one of the following: information of the computing power network access node, information of the computing power routing node, information of the computing power network exit node, information of the computing power node, and information of the computing power service.

In some embodiments, the processor is configured to read the computer program in the memory and perform the following operations:

The computing power scheduling policy is sent to the computing power network access node, so that the computing power network access node sends the computing power scheduling policy to the user corresponding to the computing power network access node.

In some embodiments, when multiple users access the network through the same computing power network access node, the computing power scheduling strategy includes a routing path information;

or,

When multiple users access the network through different computing power network access nodes, the computing power scheduling strategy includes public path information and independent path information of the user group.

In some embodiments, the processor is configured to read the computer program in the memory and perform the following operations:

Allocating a maximum guaranteed bandwidth to the user group;

and/or,

Priorities are assigned to the user groups, and resources are reserved or preempted for the user groups according to the priorities.

An embodiment of the present disclosure provides a communication device, which is a second device and includes: a memory, a transceiver, and a processor.

A memory for storing a computer program; a transceiver for receiving and sending data under the control of the processor; and a processor for reading the computer program in the memory and performing the following operations:

A computing power scheduling policy sent by the first device is received, where the computing power scheduling policy is generated based on a group computing power service demand of a user group.

In some embodiments, the group computing power business requirement includes at least one of the following:

User IDs included in the user group;

Identification of the user group;

An identifier of a first target user within the user group, where the first target user is a user with group management authority;

Business type;

Group computing power requirements;

Group network requirements.

In some embodiments, the group computing power requirement includes at least one of the following:

Computing power application scenarios;

Computing service type;

Computing resource location;

Hash rate usage time;

Computing resource type;

The size of computing resources;

Computing power and energy consumption requirements.

In some embodiments, the group network requirement includes at least one of the following:

bandwidth;

Delay;

Packet loss rate.

In some embodiments, the second device includes at least one of the following:

Computing power network access node;

Computing power routing nodes;

Hash power network exit node;

Computing power node.

In some embodiments, the computing power scheduling strategy includes routing path information of the computing power service, and the routing path information includes at least one of the following:

Information about nodes connected to the computing network;

Information about computing power routing nodes;

Information about the computing network’s exit nodes;

Information about computing power nodes;

Information about computing power services.

In some embodiments, when multiple users access the network through the same computing power network access node, the computing power scheduling strategy includes a routing path information;

or,

When multiple users access the network through different computing power network access nodes, the computing power scheduling strategy includes public path information and independent path information of the user group.

In some embodiments, the processor is configured to read the computer program in the memory and perform the following operations:

Obtain group computing power business requirements sent by user groups;

Send the group computing power service demand to the first device.

In some embodiments, the processor is configured to read the computer program in the memory and perform at least one of the following operations:

Obtain computing power business requirements of multiple users, where the multiple users belong to the same user group;

Process each user's computing power business requirements separately to obtain the user's computing power requirement list and network requirement list;

Aggregate the computing power requirement lists of multiple users and aggregate the network requirement lists of multiple users to obtain the group computing power service requirements of the user group.

In some embodiments, the processor is configured to read the computer program in the memory and perform the following operations:

According to the first aggregation principle, the computing power demand lists of multiple users are aggregated;

The first aggregation principle includes at least one of the following:

Aggregation principles related to computing resource types;

Aggregation principles related to computing power;

Aggregation principles related to the location of computing resources;

Aggregation principles related to computing power usage time.

In some embodiments, the processor is configured to read the computer program in the memory and perform the following operations:

According to the second aggregation principle, the network demand lists of multiple users are aggregated;

The second aggregation principle includes at least one of the following:

Group maximum bandwidth principle;

Group minimum delay principle;

Group minimum packet loss rate principle.

In some embodiments, the processor is configured to read the computer program in the memory and perform the following operations:

Broadcast or multicast the computing power scheduling strategy to users.

An embodiment of the present disclosure provides a computing power scheduling apparatus, applied to a first device, including:

A first acquisition unit is used to obtain the group computing power business requirements of the user group;

A first generating unit, configured to generate a computing power scheduling strategy according to the computing power service requirements of the group;

The first sending unit is used to send the computing power scheduling policy to the user group and/or the nodes included in the computing power scheduling policy.

An embodiment of the present disclosure provides a computing power scheduling apparatus, applied to a second device, including:

The first receiving unit is configured to receive a computing power scheduling policy sent by the first device, where the computing power scheduling policy is generated based on a group computing power service requirement of a user group.

An embodiment of the present disclosure provides a processor-readable storage medium having a computer program stored thereon, which implements the steps of the above-mentioned computing power scheduling method when executed by a processor.

An embodiment of the present disclosure provides a computer program product, including computer instructions, which implement the steps of the above-mentioned computing power scheduling method when executed by a processor.

The beneficial effects of the above technical solution disclosed in the present invention are:

In an embodiment of the present disclosure, a first device obtains computing power service requirements at the granularity of user groups, generates a computing power scheduling strategy based on the group computing power service requirements, and feeds back the computing power scheduling strategy to the user group and/or computing power node. By performing computing power scheduling based on groups, computing power service routing can be simplified, system orchestration efficiency and stability can be improved, and the accuracy of business collaboration can be improved. Through a computing power scheduling strategy, computing network resources can be shared within the group, improving resource utilization, more efficiently solving the problem of multi-user collaborative computing power services, and improving the user business experience.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG1 is a schematic diagram showing a flow chart of a computing power scheduling method according to an embodiment of the present disclosure;

FIG2 is a schematic diagram showing a process of obtaining computing power service requirements by a first device according to an embodiment of the present disclosure;

FIG3 is a schematic diagram showing a computing power processing architecture composed of a user and multiple nodes according to an embodiment of the present disclosure;

FIG4 shows one of the schematic diagrams of computing power routing paths according to an embodiment of the present disclosure;

FIG5 shows a second schematic diagram of a computing power routing path according to an embodiment of the present disclosure;

FIG6 shows a second flow chart of the computing power scheduling method according to an embodiment of the present disclosure;

FIG7 shows one structural diagram of a computing power scheduling device according to an embodiment of the present disclosure;

FIG8 shows a second structural diagram of the computing power scheduling device according to an embodiment of the present disclosure;

FIG9 shows one structural diagram of a communication device according to an embodiment of the present disclosure;

FIG10 shows a second schematic structural diagram of the communication device according to an embodiment of the present disclosure.

DETAILED DESCRIPTION

To make the technical problems, technical solutions, and advantages to be solved by the present disclosure more clear, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments. In the following description, specific details such as specific configurations and components are provided only to help fully understand the embodiments of the present disclosure. Therefore, it should be clear to those skilled in the art that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. In addition, for the sake of clarity and brevity, descriptions of known functions and configurations have been omitted.

It should be understood that references throughout this specification to "one embodiment" or "an embodiment" mean that a particular feature, structure, or characteristic associated with the embodiment is included in at least one embodiment of the present disclosure. Therefore, the appearances of "in one embodiment" or "in an embodiment" throughout this specification do not necessarily refer to the same embodiment. Furthermore, these particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

In the various embodiments of the present disclosure, it should be understood that the size of the serial numbers of the following processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present disclosure.

In the embodiments of the present disclosure, the term "and/or" describes the association relationship between associated objects, indicating that three relationships can exist. For example, A and/or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the associated objects are in an "or" relationship.

In the embodiments of the present disclosure, the term "plurality" refers to two or more than two, and other quantifiers are similar thereto.

The following will be combined with the accompanying drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. Obviously, the embodiments described are only part of the embodiments of the present disclosure and not all of the embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present disclosure.

The embodiments of the present disclosure provide a computing power scheduling method, apparatus, and device to solve the problem that related computing power service scheduling strategies reduce work efficiency.

Among them, the method and the device are based on the same application concept. Since the principles of solving problems by the method and the device are similar, the implementation of the device and the method can refer to each other, and the repeated parts will not be repeated.

As shown in FIG1 , an embodiment of the present disclosure provides a computing power scheduling method, which is applied to a first device. The method specifically includes the following steps:

Step 101: The first device obtains the group computing power service demand of the user group;

In this embodiment, the user group may include one or more users who have computing power service requirements. The users are computing power users, and may also be referred to as computing power users. The users may include, for example, one or more user equipment (UE), third-party applications, access network functions, core network functions, and the like.

The first device may be a device with computing power network management capabilities, such as a computing power network management center. The first device may obtain computing power service requirements based on user groups.

Step 102: The first device generates a computing power scheduling strategy according to the computing power service requirements of the group;

Step 103: The first device sends the computing power scheduling policy to the user group and/or the nodes included in the computing power scheduling policy.

In this embodiment, after obtaining the computing power service requirements of the user group, the first device can determine appropriate computing nodes and/or computing services based on the computing power service requirements of the user group to provide computing services for the user group, deploy the computing services on the selected computing nodes, obtain computing power routes for users to reach the computing nodes and/or for users to access the computing services, and then generate a computing power scheduling policy. The first device sends the computing power scheduling policy to the selected computing nodes and/or user groups.

The nodes included in the computing power scheduling strategy include one or more of the following: computing power network access node; computing power routing node; computing power network exit node; computing power node. This node can also be called a second device.

In this embodiment, for scenarios where computing power is orchestrated when multiple users with business associations use computing power services, such as multi-UE collaboration scenarios, joint office scenarios, joint data training scenarios, etc., multiple computing power users may need to use the same computing service (computing power demand), and require multiple users' data as input to complete data calculation and processing using the same computing service, and then output a unified calculation result. In these types of business scenarios, users have business associations and require collaboration between UEs to jointly complete the same business. Alternatively, for security reasons, when multiple users need to use computing power services (computing power demands) through the same network path (network demand) or computing power node, the multiple computing power users with business associations are divided into one or more computing power user groups. The first device orchestrates computing power services for users at a group granularity, efficiently solving the problem of multi-user collaborative computing power services and improving resource utilization.

In an embodiment of the present disclosure, a first device obtains computing power service requirements at the granularity of user groups, generates a computing power scheduling strategy based on the group computing power service requirements, and feeds back the computing power scheduling strategy to the user group and/or computing power node. By performing computing power scheduling based on groups, computing power service routing can be simplified, system orchestration efficiency and stability can be improved, and the accuracy of business collaboration can be improved. Through a computing power scheduling strategy, computing network resources can be shared within the group, improving resource utilization, more efficiently solving the problem of multi-user collaborative computing power services, and improving the user business experience.

As an optional embodiment, the group computing power business requirement includes at least one of the following:

User IDs included in the user group;

The identifier of the user group; it can be the unique identifier of the user group;

An identifier of a first target user in the user group, where the first target user is a user with group management authority, such as a main computing power user; the group management authority of the first target user may be granted to the user by the first device.

Service type; such as group service, UE service, etc.;

Group computing power requirements;

Group network requirements.

In some embodiments, the group computing power requirement includes at least one of the following:

1) Computing power application scenarios, such as artificial intelligence (AI) applications, extended reality (XR) applications, and manufacturing applications;

2) Computing service types, such as video encoding and decoding services, AI model training services, etc.

3) Location of computing resources; such as administrative regions, longitude and latitude, etc.

4) Computing power usage time; such as the start time, end time, time period, etc. of the computing power service;

5) Computing resource types, such as central processing unit (CPU) computing power, graphics processing unit (GPU) computing power, application-specific integrated circuit (ASIC), mobile edge computing (MEC), etc.

6) Computing power resources;

7) Computing power and energy consumption requirements: such as unit computing power energy consumption, etc.

In some embodiments, the group network requirement includes at least one of the following:

bandwidth;

Delay;

Packet loss rate.

As an optional embodiment, obtaining the group computing power service demand of the user group includes:

Receive the group computing power service requirements of the user group sent by the computing power network access node;

or,

Receive the group computing power business requirements of the user group sent by the user.

In this embodiment, the group computing power service demand can be sent directly by the user to the first device, or can be sent to the first device by the user's computing power network access node. The computing power network access node may include but is not limited to one or more of a Radio Access Network (RAN) node, a computing power network entry router, and a wireless access point (AP). The computing power user can send the group computing power service demand to the computing power network access node, which then sends it to the first device.

As an optional embodiment, obtaining the group computing power service demand of the user group includes at least one of the following:

(1) obtaining computing power business requirements of multiple users, where the multiple users belong to the same user group;

(2) Processing the computing power service requirements of each user separately to obtain the computing power requirement list and network requirement list of the user;

(3) Aggregate the computing power requirement lists of multiple users and aggregate the network requirement lists of multiple users to obtain the group computing power service requirements of the user group.

In this embodiment, the first device can execute any one of the above three steps or a combination thereof. When the first device executes one or two of the above steps, the remaining steps are executed by the computing power network access node, so that the computing power network access node sends the group computing power service requirements of the user group to the first device; when the first device executes the above three steps, the user directly sends the group computing power service requirements to the first device.

For example: the computing power network access node executes the above steps (1) and (2), that is, the computing power network access node obtains the computing power business requirements of multiple users; processes the computing power business requirements of each user respectively, and obtains the computing power requirement list and network requirement list of the user; the computing power network access node can send the computing power requirement list and the network requirement list to the first device, and the first device executes the above step (3): aggregates the computing power requirement lists of multiple users, and aggregates the network requirement lists of multiple users to obtain the group computing power business requirements of the user group.

Another example: the computing power network access node executes the above step (1), that is, the computing power network access node obtains the computing power business requirements of multiple users; the first device executes the above steps (2) and (3): the computing power network access node sends the computing power business requirements of multiple users to the first device, and the first device processes the computing power business requirements of each user respectively to obtain the computing power requirement list and network requirement list of the user; the first device aggregates the computing power requirement lists of multiple users and aggregates the network requirement lists of multiple users to obtain the group computing power business requirements of the user group.

In some embodiments, the computing power network access node may also perform the above steps (1), (2), and (3), namely, the computing power network access node obtains the computing power service requirements of multiple users; the computing power network access node processes the computing power service requirements of each user respectively to obtain the computing power requirement list and network requirement list of the user; the computing power network access node aggregates the computing power requirement lists of multiple users and aggregates the network requirement lists of multiple users to obtain the group computing power service requirements of the user group. The computing power network access node sends the group computing power service requirements to the first device.

In some embodiments, the aggregating of computing power requirement lists of multiple users includes:

According to the first aggregation principle, the computing power demand lists of multiple users are aggregated;

The first aggregation principle includes at least one of the following:

1) Aggregation principles related to computing power resource types. For example, in scenarios where users request different types of computing power resources, normalization is performed using a computing power measurement method, which is not limited here. Alternatively, a converged device can be used to support multiple types of computing power, achieving the integration of multiple computing resource types.

2) Aggregation principles related to computing power; for example, according to the principle of maximum computing power for a single user, the requirements of all requesting users can be met simultaneously; or, according to the multi-user weighted principle, weight factors can be divided according to the computing power requirement level of each user, and the computing power requirements of each user are weighted and summed.

3) Aggregation principles related to the location of computing resources; for example, aggregating the computing power requirements of multiple users based on the principle of being closest to the user or close to multiple users.

4) Aggregation principles related to computing power usage time; for example, aggregating the computing power requirements of multiple users based on the longest usage time of user requests.

As an optional embodiment, the aggregating of the network requirement lists of multiple users includes:

According to the second aggregation principle, the network demand lists of multiple users are aggregated;

The second aggregation principle includes at least one of the following:

A) Group Maximum Bandwidth Principle: Aggregate the network demands of multiple users based on the maximum bandwidth in the user request;

B) Group minimum latency principle: Aggregate the network requirements of multiple users based on the minimum latency in user requests;

C) Group minimum packet loss rate principle: Based on the minimum packet loss rate in user requests, the network requirements of multiple users are aggregated.

In some embodiments, the second aggregation principle can also be a weighted principle, which divides the weight factors according to the network demand level of each user and performs weighted summation of the network demands. For example, the weight factors are divided according to the network bandwidth (or network delay, packet loss rate) demand level of each user, and the network bandwidth (or network delay, packet loss rate) is weighted summed.

It should be noted that the steps for the first device to obtain the group computing power service demand can be performed separately by multiple entities, all or part of which can be jointly established. Multiple entities can be set up at the computing power network access node or installed on the first device, thereby enabling the computing power network access node to send the group computing power service demand to the first device, or the user to send the group computing power service demand to the first device. The following example illustrates the implementation process of the first device obtaining the computing power service demand.

As shown in Figure 2, the implementation process of the first device acquiring computing power business needs may include multiple execution subjects, such as a business need acquisition subject, a business need analysis subject, a business need aggregation subject, and a business need perception subject. These subjects can be partially or completely set up together, for example: the business need acquisition subject, the business need analysis subject, the business need aggregation subject, and the business need perception subject are all first devices, then the user directly sends the computing power business needs to the first device; or, the business need acquisition subject is set at the computing power network access node, and the remaining subjects are set at the first device; or, the business need acquisition subject and the business need analysis subject are set at the computing power network access node, and the remaining subjects are set at the first device; or, the business need acquisition subject, the business need analysis subject, and the business need aggregation subject are set at the computing power network access node, and the remaining subjects are set at the first device; or, the business need acquisition subject, the business need analysis subject, and the business need aggregation subject are all set at the main user (main computing power user) in the user group, and the group main user submits the complete group business needs to the first device.

For each subject:

(1) Multiple users in a user group send computing power service requests to the service demand acquisition subject. The computing power service requests carry the user ID, the unique ID of the group to which they belong, the computing power requirements, and the network requirements;

Computing power requirements may include one or more of the following: computing power application scenarios (such as AI applications, XR applications, manufacturing applications, etc.), computing power service types (such as video encoding and decoding services, AI model training services, etc.), computing power resource locations (administrative regions, longitude and latitude, etc.), computing power usage time (start time, time period, etc.), computing power resource types (such as CPU, GPU, ASIC, MEC, etc.) and computing power size, computing power energy consumption requirements, etc.

It should be noted that most users may not clearly know what type of computing power resources they need. The business demand analysis entity can analyze and match the computing power resource needs based on the application scenario and service type.

Network requirements include: network bandwidth, network latency, packet loss rate, etc.

(2) The business demand acquisition subject obtains the computing power business demands of multiple computing power users in the group, pre-processes the multiple computing power business demands, and establishes a list of computing power business demands of group users; the business demand acquisition subject forwards the list of computing power business demands of group users to the business demand analysis subject.

(3) The business demand analysis subject obtains the group user computing power business request list and analyzes the user business request to form a network-readable user computing power demand list and user network demand list.

Among them, if the user cannot clearly indicate the specific computing power resources and/or network resources required, the business demand analysis entity will analyze and map the computing power resource type and computing power size based on the user's computing power application scenario, service type, management experience, etc.

For example, in their computing power business requirements, a user only proposes that the computing power usage scenario is AI model training, but does not know what type of computing power is needed or how much computing power is needed. The business demand analysis module will analyze the scenario based on management experience and map it to computing power requirements such as the need for CPU-type computing power resources and the need for XXX TFLOPS of computing power.

For example, a user may specify only the computing power usage scenario for XR video processing in their computing power business requirements, but they don't know the specific network bandwidth required. This scenario requires video data transmission, which requires a large bandwidth. The business requirements analysis module will analyze the scenario based on management experience and map it to a network bandwidth requirement of XXX Mbps.

(4) The business demand analysis subject sends the computing power demand list and network demand list of the group users to the business demand aggregation subject. The business demand aggregation subject aggregates the needs of multiple users into a group computing power business demand. The group computing power business demand includes the group computing power demand and the group network demand.

Among them, the group computing power requirements include at least one of the following: computing power service type, computing power resource type, computing power resource size, computing power resource location, computing power usage time, group computing power application scenario, etc.

The aggregation principle of the group computing power requirements includes at least one of the following:

Aggregation principles for computing power resource types: For scenarios where users request different types of computing power resources, normalize them using computing power measurement methods. Alternatively, use converged devices that support multiple types of computing power to aggregate computing power requirements.

Aggregation principles related to computing power resource size: According to the principle of maximum computing power for a single user, the requirements of all requesting users can be met at the same time; or according to the multi-user weighted principle, weight factors are divided according to the computing power demand level of each user, and the computing power is weighted and summed.

Aggregation principle related to computing power resource location: Aggregate computing power demand based on the principle of being closest to the user or close to multiple users.

Aggregation principle related to computing power usage time: Aggregate computing power requirements based on the longest usage time of user requests.

The group network requirements include at least one of the following: maximum group bandwidth, minimum group latency, minimum group packet loss rate, etc.

The principles for group network demand aggregation include:

Maximum bandwidth of the group: based on the maximum bandwidth requested by the user.

Minimum group delay: The minimum delay in the user request is used as the basis.

Group minimum packet loss rate: based on the minimum packet loss rate in the user request.

It should be noted that in addition to the maximum and minimum parameter principles, the above parameters can also adopt a weighted principle, which is similar to the weighted approach to computing power resource size in group computing power requirements and will not be elaborated here.

(5) The business demand aggregation subject sends the group computing power business demand to the business demand perception subject to realize the perception of the group computing power business demand.

In this embodiment, the various entities in Figure 2 can be partially or completely combined and can be set up in the computing power network access node and/or the first device.

In some embodiments of the present disclosure, the first device may, upon obtaining the computing power service requirements of each user, group the users based on the computing power service requirements, and then obtain the group computing power service requirements based on the user groups. Alternatively, the user has already established a computing power user group, the first device has assigned a unique identifier to the group, and maintains computing power user group information. Under this premise, the first device obtains the group computing power service requirements of the user group.

As an optional embodiment, generating a computing power scheduling strategy according to the group computing power service demand includes:

Selecting computing nodes and/or computing services for the user group based on the group computing service requirements;

Generate a computing power scheduling policy based on the selected computing power nodes and/or computing power services;

Among them, the computing power scheduling strategy includes routing path information of the computing power business, and the routing path information includes at least one of the following: information of the computing power network access node, information of the computing power routing node, information of the computing power network exit node, information of the computing power node, and information of the computing power service.

In this embodiment, when the first device obtains the group computing power business requirements of the user group, it can select appropriate computing power nodes and/or computing power services to provide computing services for the group based on the group computing power business requirements (such as computing power service type and identification, computing power resource type and size, computing power resource location, computing power usage time, etc.). In some embodiments, a computing power service can be deployed on the selected computing power node to generate a service identifier (service ID). The first device arranges the optimal group computing power service path based on the group network requirements (such as the maximum bandwidth of the group, the minimum latency of the group, etc.), that is, the computing power routing path that users can use to reach the computing power node and/or access the computing power service, generates a computing power scheduling strategy, and feeds back the routing path information to the computing power user group.

In some embodiments, sending the computing power scheduling policy to the user group includes:

The computing power scheduling policy is sent to the computing power network access node, so that the computing power network access node sends the computing power scheduling policy to the user corresponding to the computing power network access node.

In this embodiment, when the first device feeds back the computing power scheduling strategy to the user group, it can send a response message of the computing power scheduling strategy to the computing power network access node (the response message includes the group's unique identifier, a list of group member identifiers (optional), computing power service identifiers accessible to group members, and computing power node addresses, etc.), and the computing power network access node broadcasts the message to members in the user group, and can also multicast the message to some group members as needed.

As an optional embodiment, when multiple users access the network through the same computing power network access node, the computing power scheduling strategy includes a routing path information;

or,

When multiple users access the network through different computing power network access nodes, the computing power scheduling strategy includes public path information and independent path information of the user group.

In this embodiment, if multiple users in a user group access the network through the same computing power network access node, the first device can only generate one computing power routing path, and each user in the user group can reach the target computing power node or access the computing power service based on this path. The routing path includes: computing power network entry node-network path composed of several computing power routers-computing power network exit node-computing power node and/or computing power service.

When multiple users in a user group access the network through multiple computing power network access nodes, the users corresponding to the computing power network access nodes access the network through different paths, where different paths can share some computing power network public nodes. The first device then arranges different routing paths for each computing power network access node. The different routing paths have some shared network nodes, which can be routers or computing power network exit nodes.

For example: User 1 and User 2 in the user group access the network through the computing power network access node 1, and User 3 and User 4 in the user group access the network through the computing power network access node 2. The first device generates a routing path 1 for User 1 and User 2, including: computing power network access node 1-several computing power routers 1-computing power network public nodes (which can be routers or computing power network exit nodes)-computing power network exit nodes-computing power nodes and/or computing power services.

The first device generates a routing path 2 for user 3 and user 4, including: computing power network access node 2-several computing power routers 2-computing power network public node (which can be a router or a computing power network exit node)-computing power network exit node-computing power node and/or computing power service.

In the above two routing paths, the public path is the computing power network public node, computing power network exit node, computing power node and/or computing power service part, and the independent paths of user 1 and user 2 are the computing power network access node 1 and several computing power routers 1; the independent paths of user 3 and user 4 are the computing power network access node 2 and several computing power routers 2.

The computing network egress node includes, but is not limited to, one or more of the following: a Protocol Data Unit (PDU) Session Anchor (PSA), a User Plane Function (UPF), and a computing network egress router. The computing network egress router includes, but is not limited to, one or more of the following: a bearer network router, an N3 UPF, and an I-UPF.

In some embodiments, when the original group computing power business demand changes or the computing power scheduling strategy cannot meet the user's computing power business demand, the first device can adjust the group computing power scheduling strategy, such as adjusting the routing path of the computing power business and/or adjusting the computing power nodes and/or computing power services.

As an optional embodiment, the method further includes:

Allocating a maximum guaranteed bandwidth to the user group;

and/or,

Priorities are assigned to the user groups, and resources are reserved or preempted for the user groups according to the priorities.

In this embodiment, the first device can provide Quality of Service (QoS) assurance at the user group level. For example, it can allocate a maximum guaranteed bandwidth to each user group, assign a group priority, and reserve or preempt resources based on the group priority.

Taking the example where the first device is a computing power network management center and two users submit computing power requirements to the computing power network management center, the group-based computing power scheduling process of the embodiment of the present disclosure includes:

(1) User UE1 and user UE2 access the network from the same computing network access node.

(2) User UE1 submits computing power service requirements to the computing power network management center, including network requirements: bandwidth 100Mbps, latency 10ms; computing power requirements: computing power resource type CPU, computing power size 1000TFLOPS, and computing power service XR video encoding and decoding service.

User UE2 submits computing power service requirements to the computing power network management center, including network requirements: bandwidth 150Mbps, latency 5ms; computing power requirements: computing power resource type CPU, computing power size 1500TFLOPS, and computing power service XR video encoding and decoding service.

(3) The computing power network management center divides user UE1 and user UE2 into a computing power user group and generates a unique group identifier.

The computing network management center perceives the group computing service requirements, including group network requirements: 150Mbps bandwidth, 5ms latency; group computing requirements: CPU resource type, 1500TFLOPS computing power, and XR video encoding and decoding services. It should be noted that group computing service requirements also meet the needs of all users.

The computing power network management center selects the same computing power node for user UE1 and user UE2, deploys the XR video encoding and decoding service, and generates a Service ID.

Generate a computing power service routing path based on the group network requirements: computing power network access node - computing power routing node X - computing power routing node Y - computing power network exit node - computing power node Node.

The computing network management center feeds back the routing path information to users UE1 and UE2, and simultaneously sends the routing strategy (routing table) to the selected routing nodes. In this case, the computing network management center needs to select one computing node and generate one group computing routing path.

It should be noted that this embodiment only uses two users as an example to illustrate the case of the same computing power network access node. For the case where multiple computing power network access nodes access the network, the same group computing power routing is used for the public path part.

In an embodiment of the present disclosure, a first device obtains computing power service requirements at the granularity of user groups, generates a computing power scheduling strategy based on the group computing power service requirements, and feeds back the computing power scheduling strategy to the user group and/or computing power node. By performing computing power scheduling based on groups, computing power service routing can be simplified, system orchestration efficiency and stability can be improved, and the accuracy of business collaboration can be improved. Through a computing power scheduling strategy, computing network resources can be shared within the group, improving resource utilization, more efficiently solving the problem of multi-user collaborative computing power services, and improving the user business experience.

The following examples illustrate the implementation method of the first device obtaining the group computing power service requirements of the user group and the implementation process of the first device generating a computing power scheduling strategy and issuing the computing power scheduling strategy.

As an optional embodiment, the computing power processing architecture formed by users, computing power network access nodes, computing power routers, computing power network exit nodes, computing power nodes and/or computing power services is shown in Figure 3. The purpose of group computing power business demand perception is to enable the computing power network (including the computing power network facing the bearer network and the mobile computing power network) to know the group computing power business demand of the computing power group (including group computing power demand and group network demand) and perform subsequent computing power scheduling based on the group computing power business demand. The ways in which the first device perceives the group computing power business demand may include the following:

Method 1: The computing power network management center obtains, analyzes, aggregates, and perceives the computing power business needs of group users, including:

Step 1: Members (multiple) of the computing power user group send computing power service requirements (multiple) to the computing power network access node. The computing power network access node does not process the computing power service requirements and directly forwards them to the computing power network management center. Alternatively, the user directly sends the computing power service requirements to the computing power network management center. The computing power service request carries one or more of the following parameters:

User identification;

The unique identifier of the group to which the user belongs;

Group primary user ID (the primary user is a user with group management permissions);

Service type, such as group service, UE service, etc.;

Network requirements: such as bandwidth, latency, packet loss rate, etc.

Computing power requirements: such as computing power application scenarios (such as AI applications, XR applications, manufacturing applications, etc.), computing power service types (such as video encoding and decoding services, AI model training services, etc.), computing power resource location (administrative region, longitude and latitude, etc.), computing power usage time (start time, time period, etc.), computing power resource type (such as CPU, GPU, ASIC, MEC, etc.), computing power size, computing power energy consumption requirements, etc., one or more items.

Step 2: After receiving the computing power service requirements of multiple users in the computing power user group, the computing power network management center preprocesses, parses, and aggregates the requirements for group services to form the aggregated group computing power service requirements. The preprocessing, parsing, and aggregation methods are not detailed here. For UE services, the independent user service requirement perception method is still used and is not limited here.

Step 3: After the computing power network management center completes the aggregation of computing power business needs, it forms a group computing power business demand and realizes the perception of group business needs.

Method 2: The computing network access node obtains the computing power business requirements of group users, and the computing network management center analyzes, aggregates, and perceives the computing power business requirements, including:

Step 1. Members (multiple) in the computing power user group send computing power service requirements (multiple) to the computing power network access node. The computing power network access node pre-processes the computing power service requirements of multiple users in the computing power user group received and establishes a user computing power service requirement list; the computing power network access node sends the computing power service requirement list to the computing power network management center.

Step 2: The computing power network management center parses the received computing power business demand list to form a network-readable user computing power demand list and network demand list.

The computing power network management center aggregates the computing power demand lists and network demand lists of multiple users to form aggregated group computing power business needs, thereby realizing the perception of group business needs.

Method 3: The computing network access node obtains and analyzes the computing power business needs of group users, and the computing network management center aggregates and perceives computing power business needs, including:

Step 1: Members (multiple) of the computing power user group send computing power service requirements (multiple) to the computing power network access node. The computing power network access node pre-processes the computing power service requirements of multiple users in the computing power user group and creates a user computing power service requirement list.

Step 2: The computing power network access node parses the user computing power service demand list to form a network-readable user computing power demand list and network demand list, and sends the user computing power demand list and network demand list to the computing power network management center.

Among them, if the user cannot clearly indicate the specific computing power resources and/or network resources required, the computing power network access node will parse and map the computing power resource type and computing power size based on the computing power application scenario, service type, management experience, etc.

Step 3: The computing power network management center aggregates the computing power demand lists and network demand lists of multiple users to form the aggregated group computing power business demand, thereby realizing the perception of group business demand.

Method 4: The computing network access node acquires, analyzes, and aggregates the computing power business needs of group users, and the computing network management center perceives the business needs, including:

Step 1: Members (multiple) of the computing power user group send computing power service requirements (multiple) to the computing power network access node. The computing power network access node pre-processes the computing power service requirements of multiple users in the computing power user group and creates a user computing power service requirement list.

Step 2: The computing power network access node parses the user computing power service demand list to form a network-readable user computing power demand list and network demand list.

Among them, if the user cannot clearly indicate the specific computing power resources and/or network resources required, the computing power network access node will parse and map the computing power resource type and computing power size based on the computing power application scenario, service type, management experience, etc.

Step 3: The computing power network access node aggregates the computing power demand lists and network demand lists of multiple users to form an aggregated group computing power business demand. The computing power network access node sends the aggregated group computing power business demand to the computing power network management center.

Step 4: The computing power network management center receives the group computing power service requirements sent by the computing power network access node to realize the perception of the group service requirements.

Method 5: The main user in the user group (a user with group management privileges) obtains, analyzes, and aggregates computing power business requirements, including:

Member users in a user group each send their computing power requirements to the group's primary user. The primary user preprocesses and parses these requirements, generating an aggregated group computing power requirement. The primary user then sends this requirement to the computing power network management center, enabling the computing power network management center to be aware of the user group's computing power requirements. The preprocessing, parsing, and aggregation methods for computing power requirements are not detailed here.

After the first device obtains the group computing power service demand of the user group, it can generate a computing power scheduling strategy according to the group computing power service demand, and send the computing power scheduling strategy to the user group and the network node.

The following describes the implementation of a user accessing the network through the same computing power network access node and a user accessing the network through multiple computing power network access nodes.

For example, the computing power routing path shown in Figure 4: multiple users in a user group access the network through a computing power network access node. The scheduling process of the computing power network management center based on user groups includes:

Step 41: The computing power network management center perceives the group computing power service demand of the user group and performs computing power scheduling based on the group computing power service demand. The process of perceiving the group computing power service demand is not described in detail here.

Specifically, the computing power network management center selects appropriate computing power nodes and/or computing power services based on the group computing power requirements, and generates a group computing power routing strategy for the computing power user group to reach the target computing power node and/or computing power service based on the group network requirements. The routing path includes: computing power network access node-network path composed of several computing power routers-computing power network exit node-computing power node and/or computing power service.

The group computing power business requirements include one or more of the following:

Unique identifier of the group;

Group network requirements: such as maximum group bandwidth, minimum group latency, and minimum group packet loss rate;

Group computing power requirements: such as computing power service type and identification, computing power resource type and size, computing power resource location, computing power usage time, group computing power application scenarios, computing power energy consumption requirements, etc.

Step 42: The computing power network management center sends the group computing power routing strategy (routing table) to each computing power router in the network, and at the same time feeds back a response message of the computing power scheduling strategy to the user group.

When the computing network management center feeds back a response message regarding the computing power scheduling policy to the user group, the computing network management center sends the computing power scheduling policy response message to the computing network access node, which then sends the computing power scheduling policy to the members of the user group. The response message includes one or more of the following information:

Unique identifier of the group;

Group member ID list (optional);

The computing power service identifier and computing power node address accessible to group members.

When the group member identification list is empty, the computing network access node broadcasts the message to all members in the user group;

When the group member identification list is not empty, the computing power network access node multicasts the message to the group members indicated in the group member identification list.

Step 43: When the user has uplink computing power service data to send, based on the computing power scheduling policy received from the broadcast or multicast message, an access request is initiated to the computing power service identifier and computing power node address in the computing power scheduling policy; after the computing power network access node receives the user's service access request, it maps the service data of multiple users to the group computing power service route and forwards the data.

When a user has a computing service identifier and a computing node address to send downlink computing service data, the computing network access node will distribute the downlink data received from the group computing service path according to the group member identifier.

In this embodiment, when computing power scheduling is performed based on user groups, members within the user group use a group computing power routing path, which can save network resources and avoid the waste of network resources caused by each user establishing and using a computing power service route separately.

For example, the computing power routing path shown in Figure 5: multiple users in a user group access the network through multiple computing power network access nodes. Assume that there are computing power network common nodes on multiple routing paths. The scheduling process of the computing power network management center based on user groups includes:

Step 51: The computing power network management center senses the group computing power business needs of the computing power user group and performs computing power scheduling based on the group computing power business needs.

Among them, appropriate computing power nodes and/or computing power services are selected according to the group computing power requirements, and a group computing power service routing strategy is generated for the computing power user group to reach the computing power nodes and/or computing power services according to the group network requirements. The group computing power service routing strategy includes two paths: a group public path and a group independent path.

As shown in Figure 5:

The group public path refers to the route consisting of the computing network public nodes (which can be computing network routers or computing network exit nodes) connecting to the target computing node/computing service;

The group independent path refers to the route from the computing power network access node to the first computing power network public node.

The group computing power routing strategy needs to maintain the mapping of computing power network access node identification, group independent path, and group public path at the same time.

Step 52: The computing power network management center sends the group computing power routing strategy (routing table) to each router in the network, and at the same time feeds back a response message of the computing power scheduling strategy to the user group.

When the computing network management center feeds back a response message regarding the computing power scheduling policy to the user group, the computing network management center sends the computing power scheduling policy response message to the computing network access node, which then sends the computing power scheduling policy to the members of the user group. The response message contains one or more of the following information:

Unique identifier of the group;

Group member ID list (optional);

The computing power service identifier and computing power node address accessible to group members.

When the group member identification list is empty, the computing network access node broadcasts the message to all members in the user group;

When the group member identification list is not empty, the computing power network access node multicasts the message to the group members indicated in the group member identification list.

Step 53: When the user has uplink computing power service data to send, based on the computing power scheduling policy received from the broadcast or multicast message, initiate an access request to the computing power service identifier and computing power node address in the computing power scheduling policy; after the computing power network access node receives the user's service access request, it maps the service data of multiple users to the group computing power service route and forwards the data.

When a user has a computing service identifier and a computing node address to send downlink computing service data, the computing network access node will distribute the downlink data received from the group computing service path according to the group member identifier.

In an embodiment of the present disclosure, when the original group computing power business demand changes, or the computing power scheduling strategy does not meet the user computing power business demand, the first device can adjust the computing power scheduling strategy. For example, when the group computing power routing cannot meet the business demand due to changes in computing power network access nodes, network status, computing power resource status, joining and leaving of other member users and other group information caused by UE mobility, the first device (such as the computing power network management center) triggers the group computing power scheduling strategy adjustment and generates a new group computing power routing; the first device sends the updated routing table entry information to each router in the network, and responds to the computing power user group at the same time. The updated group computing power routing generation method is not described in detail here.

In an embodiment of the present disclosure, a first device obtains computing power service requirements at the granularity of user groups, generates a computing power scheduling strategy based on the group computing power service requirements, and feeds back the computing power scheduling strategy to the user group and/or computing power node. By performing computing power scheduling based on groups, computing power service routing can be simplified, system orchestration efficiency and stability can be improved, and the accuracy of business collaboration can be improved. Through a computing power scheduling strategy, computing network resources can be shared within the group, improving resource utilization, more efficiently solving the problem of multi-user collaborative computing power services, and improving the user business experience.

As shown in FIG6 , an embodiment of the present disclosure further provides a computing power scheduling method, which is applied to a second device. The method includes:

Step 601: The second device receives a computing power scheduling policy sent by the first device, where the computing power scheduling policy is generated based on the group computing power service requirements of the user group.

In this embodiment, the user group may include one or more users who have computing power service requirements. The users are computing power users, and may also be referred to as computing power users. The users may include one or more of: UE, third-party applications, access network network functions, core network network functions, etc.

The first device may be a device with computing power network management capabilities, such as a computing power network management center. The first device may obtain computing power business requirements at the granularity of user groups. After obtaining the computing power business requirements of the user group, the first device may determine appropriate computing power nodes and/or computing power services to provide computing services for the user group based on the computing power business requirements of the user group, deploy computing power services on the selected computing power nodes, obtain computing power routes for users to reach computing power nodes and/or users to access computing power services, and then generate a computing power scheduling strategy. The first device sends the computing power scheduling strategy to the second device.

The second device may be a node included in the computing power scheduling policy. In some embodiments, the second device includes at least one of the following:

Computing power network access node;

Computing power routing nodes;

Hash power network exit node;

Computing power node.

In this embodiment, after generating the computing power scheduling strategy, the first device can send the computing power scheduling strategy to the computing power node and/or user group corresponding to the computing power scheduling strategy, so that the user can execute uplink data sending or downlink data receiving with the corresponding computing power node based on the computing power scheduling strategy.

As an optional embodiment, the group computing power business requirement includes at least one of the following:

User IDs included in the user group;

The identifier of the user group; it can be the unique identifier of the user group;

An identifier of a first target user in the user group, where the first target user is a user with group management authority, such as a main computing power user; the group management authority of the first target user may be granted to the user by the first device.

Service type; such as group service, UE service, etc.;

Group computing power requirements;

Group network requirements.

In some embodiments, the group computing power requirement includes at least one of the following:

1) Computing power application scenarios, such as AI applications, XR applications, and manufacturing applications;

2) Computing service types, such as video encoding and decoding services, AI model training services, etc.

3) Location of computing resources; such as administrative regions, longitude and latitude, etc.

4) Computing power usage time; such as the start time, end time, time period, etc. of the computing power service;

5) Computing resource type; such as CPU, GPU, ASIC, MEC, etc.

6) Computing power resources;

7) Computing power and energy consumption requirements; such as unit computing power energy consumption, etc.

In some embodiments, the group network requirement includes at least one of the following:

bandwidth;

Delay;

Packet loss rate.

As an optional embodiment, the computing power scheduling strategy includes routing path information of the computing power service, and the routing path information includes at least one of the following:

Information about nodes connected to the computing network;

Information about computing power routing nodes;

Information about the computing network’s exit nodes;

Information about computing power nodes;

Information about computing power services.

In this embodiment, when the first device obtains the group computing power business requirements of the user group, it can select appropriate computing power nodes and/or computing power services to provide computing services for the group based on the group computing power business requirements (such as computing power service type and identification, computing power resource type and size, computing power resource location, computing power usage time, etc.). In some embodiments, a computing power service is deployed on the selected computing power node, and a service ID can be generated. The first device arranges the optimal group computing power service path based on the group network requirements (such as the maximum bandwidth of the group, the minimum latency of the group, etc.), that is, the computing power routing path that users can use to reach the computing power node and/or access the computing power service, generates a computing power scheduling strategy, and feeds back the routing path information to the computing power user group and/or each computing power node.

In some embodiments, when multiple users access the network through the same computing power network access node, the computing power scheduling strategy includes a routing path information;

or,

When multiple users access the network through different computing power network access nodes, the computing power scheduling strategy includes public path information and independent path information of the user group.

In this embodiment, if multiple users in a user group access the network through the same computing power network access node, the first device can only generate one computing power routing path, and each user in the user group can reach the target computing power node or access the computing power service based on this path. The routing path includes: computing power network entry node-network path composed of several computing power routers-computing power network exit node-computing power node and/or computing power service.

When multiple users in a user group access the network through multiple computing power network access nodes, the users corresponding to the computing power network access nodes access the network through different paths, where different paths can share some computing power network public nodes. The first device then arranges different routing paths for each computing power network access node. The different routing paths have some shared network nodes, which can be routers or computing power network exit nodes.

As an optional embodiment, the method further includes:

Obtaining a group computing power service demand sent by a user group; and sending the group computing power service demand to the first device.

In this embodiment, the computing power user can send the computing power service demand to the second device (such as the computing power network access node), and the second device sends the computing power service demand to the first device.

In some embodiments, obtaining the group computing power service demand sent by the user group includes at least one of the following:

(1) obtaining computing power business requirements of multiple users, where the multiple users belong to the same user group;

(2) Processing the computing power service requirements of each user separately to obtain the computing power requirement list and network requirement list of the user;

(3) Aggregate the computing power requirement lists of multiple users and aggregate the network requirement lists of multiple users to obtain the group computing power service requirements of the user group.

In this embodiment, the second device can execute any one of the above three steps or a combination thereof. When the second device executes one or two of the above steps, the remaining steps are executed by the first device, so that the second device sends the group computing power business requirements of the user group to the first device; when the second device executes the above three steps, the second device only needs to send the final aggregated group computing power business requirements to the first device.

For example: the second device is a computing power network access node, and the computing power network access node executes the above steps (1) and (2), that is, the computing power network access node obtains the computing power business requirements of multiple users; processes the computing power business requirements of each user respectively, and obtains the computing power requirement list and network requirement list of the user; the computing power network access node can send the computing power requirement list and the network requirement list to the first device, and the first device executes the above step (3): aggregates the computing power requirement lists of multiple users, and aggregates the network requirement lists of multiple users to obtain the group computing power business requirements of the user group.

For another example: the second device is a computing power network access node, and the computing power network access node executes the above step (1), that is, the computing power network access node obtains the computing power business requirements of multiple users; the first device executes the above steps (2) and (3): the computing power network access node sends the computing power business requirements of multiple users to the first device, and the first device processes the computing power business requirements of each user respectively to obtain the computing power requirement list and network requirement list of the user; the first device aggregates the computing power requirement lists of multiple users, and aggregates the network requirement lists of multiple users to obtain the group computing power business requirements of the user group.

For another example: the second device is a computing power network access node, and the computing power network access node performs the above steps (1), (2) and (3), that is, the computing power network access node obtains the computing power business requirements of multiple users; the computing power network access node processes the computing power business requirements of each user respectively to obtain the computing power requirement list and network requirement list of the user; the computing power network access node aggregates the computing power requirement lists of multiple users and aggregates the network requirement lists of multiple users to obtain the group computing power business requirements of the user group. The computing power network access node sends the group computing power business requirements to the first device.

In some embodiments, the aggregating of computing power requirement lists of multiple users includes:

According to the first aggregation principle, the computing power demand lists of multiple users are aggregated;

The first aggregation principle includes at least one of the following:

1) Aggregation principles related to computing power resource types. For example, in scenarios where users request different types of computing power resources, normalization is performed using a computing power measurement method, which is not limited here. Alternatively, a converged device can be used to support multiple types of computing power, achieving the integration of multiple computing resource types.

2) Aggregation principles related to computing power; for example, according to the principle of maximum computing power for a single user, the requirements of all requesting users can be met simultaneously; or, according to the multi-user weighted principle, weight factors can be divided according to the computing power requirement level of each user, and the computing power requirements of each user are weighted and summed.

3) Aggregation principles related to the location of computing resources; for example, aggregating the computing power requirements of multiple users based on the principle of being closest to the user or close to multiple users.

4) Aggregation principles related to computing power usage time; for example, the computing power requirements of multiple users are aggregated based on the longest usage time requested by the user.

In some embodiments, aggregating the network demand lists of multiple users includes:

According to the second aggregation principle, the network demand lists of multiple users are aggregated;

The second aggregation principle includes at least one of the following:

A) Group Maximum Bandwidth Principle: Aggregate the network demands of multiple users based on the maximum bandwidth in the user request;

B) Group minimum latency principle: Aggregate the network requirements of multiple users based on the minimum latency in user requests;

C) Group minimum packet loss rate principle: Based on the minimum packet loss rate in user requests, the network requirements of multiple users are aggregated.

In some embodiments, the second aggregation principle can also be a weighted principle, which divides the weight factors according to the network demand level of each user and performs weighted summation of the network demands. For example, the weight factors are divided according to the network bandwidth (or network delay, packet loss rate) demand level of each user, and the network bandwidth (or network delay, packet loss rate) is weighted summed.

The method further includes: broadcasting or multicasting the computing power scheduling strategy to users.

In this embodiment, after the second device receives the computing power scheduling policy sent by the first device, it can broadcast the message to the members of the user group, or multicast the message to some group members as needed. For example, the computing power scheduling policy received by the second device includes one or more of the following information:

Unique identifier of the group;

Group member ID list (optional);

The computing power service identifier and computing power node address accessible to group members.

Wherein, when the group member identification list is empty, the second device may broadcast a message to all members in the user group;

When the group member identification list is not empty, the second device may multicast the message to the group members indicated by the group member identification list.

When a user has uplink computing power business data to send, based on the computing power scheduling strategy received from the broadcast or multicast message, it initiates an access request to the computing power service identifier and computing power node address in the computing power scheduling strategy; after the computing power network access node receives the user's business access request, it maps the business data of multiple users to the group computing power business route and forwards the data.

When a user has a computing service identifier and a computing node address to send downlink computing service data, the computing network access node will distribute the downlink data received from the group computing service path according to the group member identifier.

In an embodiment of the present disclosure, a first device obtains computing power service demands at the granularity of user groups, generates a computing power scheduling strategy based on the group computing power service demands, and feeds back the computing power scheduling strategy to a second device. The second device broadcasts or multicasts the computing power scheduling strategy to users in the user group, enabling users to transmit computing power service data based on the computing power scheduling strategy. By performing computing power scheduling based on groups, computing power service routing can be simplified, system orchestration efficiency and stability can be improved, and business collaboration accuracy can be improved. A computing power scheduling strategy can be used to achieve resource sharing of computing network resources in a group, improve resource utilization, and more efficiently solve the problem of multi-user collaborative computing power services, thereby improving user business experience.

The above embodiments introduce the computing power scheduling method disclosed in the present invention. The following embodiments will further illustrate the corresponding device with reference to the accompanying drawings.

Specifically, as shown in FIG7 , an embodiment of the present disclosure provides a computing power scheduling apparatus 700 , which is applied to a first device and includes:

A first obtaining unit 710 is configured to obtain a group computing power service requirement of a user group;

A first generating unit 720 is configured to generate a computing power scheduling strategy according to the computing power service requirements of the group;

The first sending unit 730 is configured to send the computing power scheduling policy to the user group and/or the nodes included in the computing power scheduling policy.

In some embodiments, the group computing power business requirement includes at least one of the following:

User IDs included in the user group;

Identification of the user group;

An identifier of a first target user within the user group, where the first target user is a user with group management authority;

Business type;

Group computing power requirements;

Group network requirements.

In some embodiments, the group computing power requirement includes at least one of the following:

Computing power application scenarios;

Computing service type;

Computing resource location;

Hash rate usage time;

Computing resource type;

The size of computing resources;

Computing power and energy consumption requirements.

In some embodiments, the group network requirement includes at least one of the following:

bandwidth;

Delay;

Packet loss rate.

In some embodiments, the first acquiring unit is specifically configured to:

Receive the group computing power service requirements of the user group sent by the computing power network access node;

or,

Receive the group computing power business requirements of the user group sent by the user.

In some embodiments, the first acquiring unit is specifically configured to perform at least one of the following:

Obtain computing power business requirements of multiple users, where the multiple users belong to the same user group;

Process each user's computing power business requirements separately to obtain the user's computing power requirement list and network requirement list;

Aggregate the computing power requirement lists of multiple users and aggregate the network requirement lists of multiple users to obtain the group computing power service requirements of the user group.

In some embodiments, the first acquiring unit is specifically configured to:

According to the first aggregation principle, the computing power demand lists of multiple users are aggregated;

The first aggregation principle includes at least one of the following:

Aggregation principles related to computing resource types;

Aggregation principles related to computing power;

Aggregation principles related to the location of computing resources;

Aggregation principles related to computing power usage time.

In some embodiments, the first acquiring unit is specifically configured to:

According to the second aggregation principle, the network demand lists of multiple users are aggregated;

The second aggregation principle includes at least one of the following:

Group maximum bandwidth principle;

Group minimum delay principle;

Group minimum packet loss rate principle.

In some embodiments, the first generating unit is specifically configured to:

Selecting computing nodes and/or computing services for the user group based on the group computing service requirements;

Generate a computing power scheduling policy based on the selected computing power nodes and/or computing power services;

Among them, the computing power scheduling strategy includes routing path information of the computing power business, and the routing path information includes at least one of the following: information of the computing power network access node, information of the computing power routing node, information of the computing power network exit node, information of the computing power node, and information of the computing power service.

In some embodiments, the first sending unit is specifically configured to:

The computing power scheduling policy is sent to the computing power network access node, so that the computing power network access node sends the computing power scheduling policy to the user corresponding to the computing power network access node.

In some embodiments, when multiple users access the network through the same computing power network access node, the computing power scheduling strategy includes a routing path information;

or,

When multiple users access the network through different computing power network access nodes, the computing power scheduling strategy includes public path information and independent path information of the user group.

In some embodiments, the apparatus further includes: a processing unit; the processing unit is specifically configured to:

Allocating a maximum guaranteed bandwidth to the user group;

and/or,

Priorities are assigned to the user groups, and resources are reserved or preempted for the user groups according to the priorities.

It should be noted here that the above-mentioned device provided in the embodiment of the present disclosure can implement all the method steps implemented in the above-mentioned method embodiment applied to the first device, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as the method embodiment will not be described in detail here.

Specifically, as shown in FIG8 , an embodiment of the present disclosure provides a computing power scheduling apparatus 800 , which is applied to a second device and includes:

The first receiving unit 810 is configured to receive a computing power scheduling policy sent by a first device, where the computing power scheduling policy is generated based on a group computing power service requirement of a user group.

In some embodiments, the group computing power business requirement includes at least one of the following:

User IDs included in the user group;

Identification of the user group;

An identifier of a first target user within the user group, where the first target user is a user with group management authority;

Business type;

Group computing power requirements;

Group network requirements.

In some embodiments, the group computing power requirement includes at least one of the following:

Computing power application scenarios;

Computing service type;

Computing resource location;

Hash rate usage time;

Computing resource type;

The size of computing resources;

Computing power and energy consumption requirements.

In some embodiments, the group network requirement includes at least one of the following:

bandwidth;

Delay;

Packet loss rate.

In some embodiments, the second device includes at least one of the following:

Computing power network access node;

Computing power routing nodes;

Hash power network exit node;

Computing power node.

In some embodiments, the computing power scheduling strategy includes routing path information of the computing power service, and the routing path information includes at least one of the following:

Information about nodes connected to the computing network;

Information about computing power routing nodes;

Information about the computing network’s exit nodes;

Information about computing power nodes;

Information about computing power services.

In some embodiments, when multiple users access the network through the same computing power network access node, the computing power scheduling strategy includes a routing path information;

or,

When multiple users access the network through different computing power network access nodes, the computing power scheduling strategy includes public path information and independent path information of the user group.

In some embodiments, the device further comprises:

The second acquisition unit is used to acquire the group computing power service demand sent by the user group;

The second sending unit is used to send the group computing power service demand to the first device.

In some embodiments, the second acquiring unit is specifically configured to perform at least one of the following:

Obtain computing power business requirements of multiple users, where the multiple users belong to the same user group;

Process each user's computing power business requirements separately to obtain the user's computing power requirement list and network requirement list;

Aggregate the computing power requirement lists of multiple users and aggregate the network requirement lists of multiple users to obtain the group computing power service requirements of the user group.

In some embodiments, the aggregating of computing power requirement lists of multiple users includes:

According to the first aggregation principle, the computing power demand lists of multiple users are aggregated;

The first aggregation principle includes at least one of the following:

Aggregation principles related to computing resource types;

Aggregation principles related to computing power;

Aggregation principles related to the location of computing resources;

Aggregation principles related to computing power usage time.

In some embodiments, aggregating the network demand lists of multiple users includes:

According to the second aggregation principle, the network demand lists of multiple users are aggregated;

The second aggregation principle includes at least one of the following:

Group maximum bandwidth principle;

Group minimum delay principle;

Group minimum packet loss rate principle.

In some embodiments, the apparatus further comprises:

The third sending unit is used to broadcast or multicast the computing power scheduling strategy to users.

It should be noted here that the above-mentioned device provided in the embodiment of the present disclosure can implement all the method steps implemented in the above-mentioned method embodiment applied to the second device, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as the method embodiment will not be described in detail here.

It should be noted that the division of units in the embodiments of the present disclosure is schematic and is merely a logical functional division. In actual implementation, other division methods may be used. Furthermore, the functional units in the various embodiments of the present disclosure may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a processor-readable storage medium. Based on this understanding, the technical solution of the present disclosure, or the part that contributes to the relevant technology, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of the method described in each embodiment of the present disclosure. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk, and other media that can store program code.

As shown in FIG9 , an embodiment of the present disclosure further provides a communication device, which is a first device and includes: a memory 920, a transceiver 900, and a processor 910; wherein the memory 920 is used to store a computer program; the transceiver 900 is used to receive and send data under the control of the processor 910; and the processor 910 is used to read the computer program in the memory and perform the following operations:

Obtain the group computing power business requirements of the user group;

Generate a computing power scheduling strategy based on the computing power business requirements of the group;

Send the computing power scheduling policy to the user group and/or the nodes included in the computing power scheduling policy.

In some embodiments, the group computing power business requirement includes at least one of the following:

User IDs included in the user group;

Identification of the user group;

An identifier of a first target user within the user group, where the first target user is a user with group management authority;

Business type;

Group computing power requirements;

Group network requirements.

In some embodiments, the group computing power requirement includes at least one of the following:

Computing power application scenarios;

Computing service type;

Computing resource location;

Hash rate usage time;

Computing resource type;

The size of computing resources;

Computing power and energy consumption requirements.

In some embodiments, the group network requirement includes at least one of the following:

bandwidth;

Delay;

Packet loss rate.

In some embodiments, the processor is configured to read the computer program in the memory and perform the following operations:

Receive the group computing power service requirements of the user group sent by the computing power network access node;

or,

Receive the group computing power business requirements of the user group sent by the user.

In some embodiments, the processor is configured to read the computer program in the memory and perform at least one of the following operations:

Obtaining computing power business requirements of multiple users, where the multiple users belong to the same user group;

Process each user's computing power business requirements separately to obtain the user's computing power requirement list and network requirement list;

Aggregate the computing power requirement lists of multiple users and aggregate the network requirement lists of multiple users to obtain the group computing power service requirements of the user group.

In some embodiments, the processor is configured to read the computer program in the memory and perform the following operations:

According to the first aggregation principle, the computing power demand lists of multiple users are aggregated;

The first aggregation principle includes at least one of the following:

Aggregation principles related to computing resource types;

Aggregation principles related to computing power;

Aggregation principles related to the location of computing resources;

Aggregation principles related to computing power usage time.

In some embodiments, the processor is configured to read the computer program in the memory and perform the following operations:

According to the second aggregation principle, the network demand lists of multiple users are aggregated;

The second aggregation principle includes at least one of the following:

Group maximum bandwidth principle;

Group minimum delay principle;

Group minimum packet loss rate principle.

In some embodiments, the processor is configured to read the computer program in the memory and perform the following operations:

Selecting computing nodes and/or computing services for the user group based on the group computing service requirements;

Generate a computing power scheduling policy based on the selected computing power nodes and/or computing power services;

Among them, the computing power scheduling strategy includes routing path information of the computing power business, and the routing path information includes at least one of the following: information of the computing power network access node, information of the computing power routing node, information of the computing power network exit node, information of the computing power node, and information of the computing power service.

In some embodiments, the processor is configured to read the computer program in the memory and perform the following operations:

The computing power scheduling policy is sent to the computing power network access node, so that the computing power network access node sends the computing power scheduling policy to the user corresponding to the computing power network access node.

In some embodiments, when multiple users access the network through the same computing power network access node, the computing power scheduling strategy includes a routing path information;

or,

When multiple users access the network through different computing power network access nodes, the computing power scheduling strategy includes public path information and independent path information of the user group.

In some embodiments, the processor is configured to read the computer program in the memory and perform the following operations:

Allocating a maximum guaranteed bandwidth to the user group;

and/or,

Priorities are assigned to the user groups, and resources are reserved or preempted for the user groups according to the priorities.

In FIG9 , the bus architecture may include any number of interconnected buses and bridges, specifically linking together various circuits of one or more processors represented by processor 910 and memory represented by memory 920. The bus architecture may also link together various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are all well known in the art and, therefore, will not be further described herein. The bus interface provides an interface. The transceiver 900 may be a plurality of components, namely, including a transmitter and a transceiver, providing a unit for communicating with various other devices over a transmission medium. The processor 910 is responsible for managing the bus architecture and general processing, and the memory 920 may store data used by the processor 910 when performing operations.

The processor 910 can be a central processing unit (CPU), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or a complex programmable logic device (CPLD). The processor can also adopt a multi-core architecture.

It should be noted here that the above-mentioned device provided in the embodiment of the present disclosure can implement all the method steps implemented in the above-mentioned method embodiment applied to the first device, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as the method embodiment will not be described in detail here.

As shown in FIG10 , an embodiment of the present disclosure further provides a communication device, which is a second device and includes: a memory 1020, a transceiver 1000, and a processor 1010; wherein the memory 1020 is used to store a computer program; the transceiver 1000 is used to receive and send data under the control of the processor 1010; and the processor 1010 is used to read the computer program in the memory and perform the following operations:

A computing power scheduling policy sent by the first device is received, where the computing power scheduling policy is generated based on a group computing power service demand of a user group.

In some embodiments, the group computing power business requirement includes at least one of the following:

User IDs included in the user group;

Identification of the user group;

An identifier of a first target user within the user group, where the first target user is a user with group management authority;

Business type;

Group computing power requirements;

Group network requirements.

In some embodiments, the group computing power requirement includes at least one of the following:

Computing power application scenarios;

Computing service type;

Computing resource location;

Hash rate usage time;

Computing resource type;

The size of computing resources;

Computing power and energy consumption requirements.

In some embodiments, the group network requirement includes at least one of the following:

bandwidth;

Delay;

Packet loss rate.

In some embodiments, the second device includes at least one of the following:

Computing power network access node;

Computing power routing nodes;

Hash power network exit node;

Computing power node.

In some embodiments, the computing power scheduling strategy includes routing path information of the computing power service, and the routing path information includes at least one of the following:

Information about nodes connected to the computing network;

Information about computing power routing nodes;

Information about the computing network’s exit nodes;

Information about computing power nodes;

Information about computing power services.

In some embodiments, when multiple users access the network through the same computing power network access node, the computing power scheduling strategy includes a routing path information;

or,

When multiple users access the network through different computing power network access nodes, the computing power scheduling strategy includes public path information and independent path information of the user group.

In some embodiments, the processor is configured to read the computer program in the memory and perform the following operations:

Obtain group computing power business requirements sent by user groups;

Send the group computing power service demand to the first device.

In some embodiments, the processor is configured to read the computer program in the memory and perform at least one of the following operations:

Obtain computing power business requirements of multiple users, where the multiple users belong to the same user group;

Process each user's computing power business requirements separately to obtain the user's computing power requirement list and network requirement list;

Aggregate the computing power requirement lists of multiple users and aggregate the network requirement lists of multiple users to obtain the group computing power service requirements of the user group.

In some embodiments, the processor is configured to read the computer program in the memory and perform the following operations:

According to the first aggregation principle, the computing power demand lists of multiple users are aggregated;

The first aggregation principle includes at least one of the following:

Aggregation principles related to computing resource types;

Aggregation principles related to computing power;

Aggregation principles related to the location of computing resources;

Aggregation principles related to computing power usage time.

In some embodiments, the processor is configured to read the computer program in the memory and perform the following operations:

According to the second aggregation principle, the network demand lists of multiple users are aggregated;

The second aggregation principle includes at least one of the following:

Group maximum bandwidth principle;

Group minimum delay principle;

Group minimum packet loss rate principle.

In some embodiments, the processor is configured to read the computer program in the memory and perform the following operations:

Broadcast or multicast the computing power scheduling strategy to users.

In FIG10 , the bus architecture may include any number of interconnected buses and bridges, specifically linking together various circuits of one or more processors represented by processor 1010 and memory represented by memory 1020. The bus architecture may also link together various other circuits such as peripherals, voltage regulators, and power management circuits, all of which are well known in the art and, therefore, will not be further described herein. The bus interface provides an interface. The transceiver 1000 may be a plurality of components, namely, including a transmitter and a transceiver, providing a unit for communicating with various other devices over a transmission medium. The processor 1010 is responsible for managing the bus architecture and general processing, and the memory 1020 may store data used by the processor 1010 when performing operations.

The processor 1010 may be a CPU, an ASIC, an FPGA, or a CPLD, and the processor may also adopt a multi-core architecture.

It should be noted here that the above-mentioned device provided in the embodiment of the present disclosure can implement all the method steps implemented in the above-mentioned method embodiment applied to the second device, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as the method embodiment will not be described in detail here.

In addition, a specific embodiment of the present disclosure also provides a processor-readable storage medium on which a computer program is stored. When the program is executed by the processor, the steps of the computing power scheduling method described above are implemented and the same technical effects can be achieved. To avoid repetition, they will not be described here. Among them, the readable storage medium can be any available medium or data storage device that can be accessed by the processor, including but not limited to magnetic storage (such as floppy disk, hard disk, magnetic tape, magneto-optical disk (MO)), etc.), optical storage (such as compact disc (CD), digital video disc (DVD), Blu-ray disc (BD), high-definition versatile disc (HVD), etc.), and semiconductor memory (such as ROM, erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), non-volatile memory (NAND (Non-volatile Memory Device) FLASH), solid-state drive (SSD)), etc.

In addition, the specific embodiment of the present disclosure also provides a computer program product, including computer instructions. When the computer instructions are executed by the processor, the steps of the computing power scheduling method as described above are implemented, and the same technical effects can be achieved. To avoid repetition, they will not be described here.

It should be noted that the technical solutions provided by the embodiments of the present disclosure can be applicable to a variety of systems, especially 5G systems. For example, applicable systems may include the Global System of Mobile Communication (GSM) system, the Code Division Multiple Access (CDMA) system, the Wideband Code Division Multiple Access (WCDMA) general packet radio service (GPRS) system, the Long Term Evolution (LTE) system, the LTE frequency division duplex (FDD) system, the LTE time division duplex (TDD) system, the Long Term Evolution Advanced (LTE-A) system, the Universal Mobile Telecommunication System (UMTS), the Worldwide Interoperability for Microwave Access (WiMAX) system, and the 5G New Radio (NR) system. These systems include terminal devices and network equipment. They can also include core network components, such as the Evolved Packet System (EPS) and the 5G System (5GS).

The terminal device involved in the embodiments of the present disclosure may be a device that provides voice and/or data connectivity to a user, a handheld device with wireless connection function, or other processing equipment connected to a wireless modem. In different systems, the name of the terminal device may also be different. For example, in a 5G system, the terminal device may be called a user equipment (UE). The wireless terminal device can communicate with one or more core networks (CN) via a radio access network (RAN). The wireless terminal device may be a mobile terminal device, such as a mobile phone (or "cellular" phone) and a computer with a mobile terminal device. For example, it may be a portable, pocket-sized, handheld, computer-built-in or vehicle-mounted mobile device that exchanges language and/or data with the radio access network. For example, Personal Communication Service (PCS) phones, cordless phones, Session Initiated Protocol (SIP) phones, Wireless Local Loop (WLL) stations, Personal Digital Assistants (PDAs), etc. A wireless terminal device may also be referred to as a system, subscriber unit, subscriber station, mobile station, mobile, remote station, access point, remote terminal, access terminal, user terminal, user agent, or user device, but is not limited to these terms in the embodiments of the present disclosure.

The network device involved in the embodiments of the present disclosure may be a base station, which may include multiple cells providing services to the terminal. Depending on the specific application scenario, the base station may also be called an access point, or may be a device in the access network that communicates with the wireless terminal device through one or more sectors on the air interface, or other names. The network device can be used to interchange received air frames with Internet Protocol (IP) packets, acting as a router between the wireless terminal device and the rest of the access network, wherein the rest of the access network may include an Internet Protocol (IP) communication network. The network device may also coordinate the attribute management of the air interface. For example, the network device involved in the embodiments of the present disclosure may be a network device (Base Transceiver Station, BTS) in the Global System for Mobile communications (GSM) or Code Division Multiple Access (CDMA), or a network device (NodeB) in Wide-band Code Division Multiple Access (WCDMA), or an evolved network device (evolutionary Node B, eNB or e-NodeB) in the Long Term Evolution (LTE) system, a 5G base station (gNB) in the 5G network architecture (next generation system), or a Home evolved Node B (HeNB), a relay node, a femto base station, a pico base station, etc., but is not limited in the embodiments of the present disclosure. In some network structures, network devices may include centralized unit (CU) nodes and distributed unit (DU) nodes, and the centralized unit and the distributed unit may also be geographically separated.

Network devices and terminal devices can each use one or more antennas for Multiple Input Multiple Output (MIMO) transmission. MIMO transmission can be either Single User MIMO (SU-MIMO) or Multi User MIMO (MU-MIMO). Depending on the configuration and number of antennas, MIMO transmission can be two-dimensional MIMO (2D-MIMO), three-dimensional MIMO (3D-MIMO), full-dimensional MIMO (FD-MIMO), or massive MIMO. It can also use diversity transmission, precoding, or beamforming.

Those skilled in the art will appreciate that the embodiments of the present disclosure may be provided as methods, systems, or computer program products. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present disclosure may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage and optical storage, etc.) containing computer-usable program code.

The present disclosure is described with reference to the flowcharts and/or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present disclosure. It should be understood that each process and/or box in the flowchart and/or block diagram, as well as the combination of the processes and/or boxes in the flowchart and/or block diagram, can be implemented by computer-executable instructions. These computer-executable instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device for implementing the functions specified in one process or multiple processes in the flowchart and/or one box or multiple boxes in the block diagram.

These processor-executable instructions may also be stored in a processor-readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the processor-readable memory produce a product including an instruction device that implements the functions specified in one or more processes in the flowchart and/or one or more boxes in the block diagram.

These processor-executable instructions may also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and/or one or more boxes in the block diagram.

In addition, it should be noted that, in the apparatus and method of the present invention, it is obvious that each component or each step can be decomposed and/or recombined. These decompositions and/or recombinations should be regarded as equivalent schemes of the present invention. Moreover, the steps of performing the above-mentioned series of processing can naturally be performed in chronological order according to the order of description, but it is not necessary to perform them in chronological order, and some steps can be performed in parallel or independently of each other. For those of ordinary skill in the art, it will be understood that all or any steps or components of the method and apparatus of the present invention can be implemented in any computing device (including processors, storage media, etc.) or a network of computing devices in hardware, firmware, software or a combination thereof, which can be achieved by those of ordinary skill in the art using their basic programming skills after reading the description of the present invention.

It should be noted that it should be understood that the division of the above modules is merely a division of logical functions. In actual implementation, they can be fully or partially integrated into one physical entity, or they can be physically separated. Moreover, these modules can all be implemented in the form of software called by a processing element; or they can all be implemented in the form of hardware; or some modules can be implemented in the form of software called by a processing element, and some modules can be implemented in the form of hardware. For example, a module can be a separately established processing element, or it can be integrated into a chip of the above-mentioned device. In addition, it can also be stored in the memory of the above-mentioned device in the form of program code, and called by a processing element of the above-mentioned device to perform the functions of the above-mentioned module. The implementation of other modules is similar. In addition, these modules can all or partly be integrated together, or they can be implemented independently. The processing element described here can be an integrated circuit with signal processing capabilities. During implementation, each step of the above method or each module above can be completed by an integrated logic circuit of hardware in the processor element or instructions in the form of software.

For example, each module, unit, sub-unit or sub-module can be one or more integrated circuits configured to implement the above method, such as one or more application specific integrated circuits (ASICs), or one or more microprocessors (digital signal processors, DSPs), or one or more field programmable gate arrays (FPGAs). For another example, when a module above is implemented in the form of a processing element scheduling program code, the processing element can be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call program code. For another example, these modules can be integrated together and implemented in the form of a system-on-a-chip (SOC).

The terms "first," "second," and the like in the specification and claims of the present disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, so that the embodiments of the present disclosure described herein may be implemented in a sequence other than that illustrated or described herein. In addition, the terms "including" and "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or device that includes a series of steps or units need not be limited to those steps or units explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to these processes, methods, products, or devices. In addition, the use of "and/or" in the specification and claims to indicate at least one of the connected objects, for example, A and/or B and/or C, means that seven situations are included: A alone, B alone, C alone, both A and B present, both B and C present, both A and C present, and all A, B, and C present. Similarly, the use of "at least one of A and B" in the specification and claims should be understood to mean "A alone, B alone, or both A and B present."

Obviously, those skilled in the art may make various changes and modifications to the present disclosure without departing from the spirit and scope of the present disclosure. Thus, if these modifications and variations of the present disclosure fall within the scope of the claims of the present disclosure and their equivalents, the present disclosure is intended to include these modifications and variations.

Claims (52)

A computing power scheduling method, comprising: The first device obtains the group computing power service demand of the user group; The first device generates a computing power scheduling strategy according to the computing power service demand of the group; The first device sends the computing power scheduling policy to the user group and/or the nodes included in the computing power scheduling policy. The method according to claim 1, wherein the group computing power business requirement includes at least one of the following: User IDs included in the user group; Identification of the user group; An identifier of a first target user within the user group, where the first target user is a user with group management authority; Business type; Group computing power requirements; Group network requirements. The method according to claim 2, wherein the group computing power requirement includes at least one of the following: Computing power application scenarios; Computing service type; Computing resource location; Hash rate usage time; Computing resource type; The size of computing resources; Computing power and energy consumption requirements. The method according to claim 2, wherein the group network requirement includes at least one of the following: bandwidth; Delay; Packet loss rate. The method according to claim 1, wherein obtaining the group computing power business requirements of the user group includes: Receive the group computing power service requirements of the user group sent by the computing power network access node; or, Receive the group computing power business requirements of the user group sent by the user. The method according to claim 1, wherein obtaining the group computing power business requirements of the user group includes at least one of the following: Obtain computing power business requirements of multiple users, where the multiple users belong to the same user group; Process each user's computing power business requirements separately to obtain the user's computing power requirement list and network requirement list; Aggregate the computing power requirement lists of multiple users and aggregate the network requirement lists of multiple users to obtain the group computing power service requirements of the user group. The method according to claim 6, wherein the aggregating the computing power requirement lists of multiple users comprises: According to the first aggregation principle, the computing power demand lists of multiple users are aggregated; The first aggregation principle includes at least one of the following: Aggregation principles related to computing resource types; Aggregation principles related to computing power; Aggregation principles related to the location of computing resources; Aggregation principles related to computing power usage time. The method according to claim 6, wherein the aggregating the network requirement lists of multiple users comprises: According to the second aggregation principle, the network demand lists of multiple users are aggregated; The second aggregation principle includes at least one of the following: Group maximum bandwidth principle; Group minimum delay principle; Group minimum packet loss rate principle. The method according to claim 1, wherein generating a computing power scheduling strategy based on the group computing power business requirements comprises: Selecting computing nodes and/or computing services for the user group based on the group computing service requirements; Generate a computing power scheduling policy based on the selected computing power nodes and/or computing power services; Among them, the computing power scheduling strategy includes routing path information of the computing power business, and the routing path information includes at least one of the following: information of the computing power network access node, information of the computing power routing node, information of the computing power network exit node, information of the computing power node, and information of the computing power service. The method according to claim 1, wherein sending the computing power scheduling policy to the user group comprises: The computing power scheduling policy is sent to the computing power network access node, so that the computing power network access node sends the computing power scheduling policy to the user corresponding to the computing power network access node. The method according to claim 1 or 9, wherein, when multiple users access the network through the same computing power network access node, the computing power scheduling strategy includes a routing path information; or, When multiple users access the network through different computing power network access nodes, the computing power scheduling strategy includes public path information and independent path information of the user group. The method according to claim 1, further comprising: Allocating a maximum guaranteed bandwidth to the user group; and/or, Priorities are assigned to the user groups, and resources are reserved or preempted for the user groups according to the priorities. A computing power scheduling method, comprising: The second device receives the computing power scheduling policy sent by the first device, where the computing power scheduling policy is generated based on the group computing power service demand of the user group. The method according to claim 13, wherein the group computing power business requirement includes at least one of the following: User IDs included in the user group; Identification of the user group; An identifier of a first target user within the user group, where the first target user is a user with group management authority; Business type; Group computing power requirements; Group network requirements. The method according to claim 14, wherein the group computing power requirement includes at least one of the following: Computing power application scenarios; Computing service type; Computing resource location; Hash rate usage time; Computing resource type; The size of computing resources; Computing power and energy consumption requirements. The method according to claim 14, wherein the group network requirement comprises at least one of the following: bandwidth; Delay; Packet loss rate. The method according to claim 13, wherein the second device comprises at least one of the following: Computing power network access node; Computing power routing nodes; Hash power network exit node; Computing power node. The method according to claim 13, wherein the computing power scheduling policy includes routing path information of the computing power service, and the routing path information includes at least one of the following: Information about nodes connected to the computing network; Information about computing power routing nodes; Information about the computing network’s exit nodes; Information about computing power nodes; Information about computing power services. The method according to claim 13 or 18, wherein, when multiple users access the network through the same computing power network access node, the computing power scheduling strategy includes a routing path information; or, When multiple users access the network through different computing power network access nodes, the computing power scheduling strategy includes public path information and independent path information of the user group. The method according to claim 13, further comprising: Obtain group computing power business requirements sent by user groups; Send the group computing power service demand to the first device. The method according to claim 20, wherein obtaining the group computing power service demand sent by the user group includes at least one of the following: Obtain computing power business requirements of multiple users, where the multiple users belong to the same user group; Process each user's computing power business requirements separately to obtain the user's computing power requirement list and network requirement list; Aggregate the computing power requirement lists of multiple users and aggregate the network requirement lists of multiple users to obtain the group computing power service requirements of the user group. The method according to claim 21, wherein the aggregating the computing power requirement lists of multiple users comprises: According to the first aggregation principle, the computing power demand lists of multiple users are aggregated; The first aggregation principle includes at least one of the following: Aggregation principles related to computing resource types; Aggregation principles related to computing power; Aggregation principles related to the location of computing resources; Aggregation principles related to computing power usage time. The method according to claim 21, wherein aggregating the network requirement lists of multiple users comprises: According to the second aggregation principle, the network demand lists of multiple users are aggregated; The second aggregation principle includes at least one of the following: Group maximum bandwidth principle; Group minimum delay principle; Group minimum packet loss rate principle. The method according to claim 13, further comprising: Broadcast or multicast the computing power scheduling strategy to users. A communication device, the communication device being a first device, comprising: a memory, a transceiver, and a processor: A memory for storing a computer program; a transceiver for receiving and sending data under the control of the processor; and a processor for reading the computer program in the memory and performing the following operations: Obtain the group computing power business requirements of the user group; Generate a computing power scheduling strategy based on the computing power business requirements of the group; Send the computing power scheduling policy to the user group and/or the nodes included in the computing power scheduling policy. The device according to claim 25, wherein the group computing power business requirement includes at least one of the following: User IDs included in the user group; Identification of the user group; An identifier of a first target user within the user group, where the first target user is a user with group management authority; Business type; Group computing power requirements; Group network requirements. The device according to claim 26, wherein the group computing power requirement includes at least one of the following: Computing power application scenarios; Computing service type; Computing resource location; Hash rate usage time; Computing resource type; The size of computing resources; Computing power and energy consumption requirements. The apparatus of claim 26, wherein the group network requirement comprises at least one of the following: bandwidth; Delay; Packet loss rate. The apparatus of claim 25, wherein the processor is configured to read the computer program in the memory and perform the following operations: Receive the group computing power service requirements of the user group sent by the computing power network access node; or, Receive the group computing power business requirements of the user group sent by the user. The apparatus of claim 25, wherein the processor is configured to read the computer program in the memory and perform at least one of the following operations: Obtain computing power business requirements of multiple users, where the multiple users belong to the same user group; Process each user's computing power business requirements separately to obtain the user's computing power requirement list and network requirement list; Aggregate the computing power requirement lists of multiple users and aggregate the network requirement lists of multiple users to obtain the group computing power service requirements of the user group. The apparatus of claim 30, wherein the processor is configured to read the computer program in the memory and perform the following operations: According to the first aggregation principle, the computing power demand lists of multiple users are aggregated; The first aggregation principle includes at least one of the following: Aggregation principles related to computing resource types; Aggregation principles related to computing power; Aggregation principles related to the location of computing resources; Aggregation principles related to computing power usage time. The apparatus of claim 30, wherein the processor is configured to read the computer program in the memory and perform the following operations: According to the second aggregation principle, the network demand lists of multiple users are aggregated; The second aggregation principle includes at least one of the following: Group maximum bandwidth principle; Group minimum delay principle; Group minimum packet loss rate principle. The apparatus of claim 25, wherein the processor is configured to read the computer program in the memory and perform the following operations: Selecting computing nodes and/or computing services for the user group based on the group computing service requirements; Generate a computing power scheduling policy based on the selected computing power nodes and/or computing power services; Among them, the computing power scheduling strategy includes routing path information of the computing power business, and the routing path information includes at least one of the following: information of the computing power network access node, information of the computing power routing node, information of the computing power network exit node, information of the computing power node, and information of the computing power service. The apparatus of claim 25, wherein the processor is configured to read the computer program in the memory and perform the following operations: The computing power scheduling policy is sent to the computing power network access node, so that the computing power network access node sends the computing power scheduling policy to the user corresponding to the computing power network access node. The device according to claim 25 or 33, wherein, when multiple users access the network through the same computing power network access node, the computing power scheduling strategy includes a routing path information; or, When multiple users access the network through different computing power network access nodes, the computing power scheduling strategy includes public path information and independent path information of the user group. The apparatus of claim 25, wherein the processor is configured to read the computer program in the memory and perform the following operations: Allocating a maximum guaranteed bandwidth to the user group; and/or, Priorities are assigned to the user groups, and resources are reserved or preempted for the user groups according to the priorities. A communication device, which is a second device, includes: a memory, a transceiver, and a processor: A memory for storing a computer program; a transceiver for receiving and sending data under the control of the processor; and a processor for reading the computer program in the memory and performing the following operations: A computing power scheduling policy sent by the first device is received, where the computing power scheduling policy is generated based on a group computing power service demand of a user group. The device according to claim 37, wherein the group computing power business requirement includes at least one of the following: User IDs included in the user group; Identification of the user group; An identifier of a first target user within the user group, where the first target user is a user with group management authority; Business type; Group computing power requirements; Group network requirements. The device of claim 38, wherein the group computing power requirement comprises at least one of the following: Computing power application scenarios; Computing service type; Computing resource location; Hash rate usage time; Computing resource type; Computing power resource size Computing power and energy consumption requirements. The apparatus of claim 38, wherein the group network requirement comprises at least one of the following: bandwidth; Delay; Packet loss rate. The apparatus of claim 37, wherein the second device comprises at least one of the following: Computing power network access node; Computing power routing nodes; Hash power network exit node; Computing power node. The device according to claim 37, wherein the computing power scheduling policy includes routing path information of the computing power service, and the routing path information includes at least one of the following: Information about nodes connected to the computing network; Information about computing power routing nodes; Information about the computing network’s exit nodes; Information about computing power nodes; Information about computing power services. The device according to claim 37 or 42, wherein, when multiple users access the network through the same computing power network access node, the computing power scheduling strategy includes a routing path information; or, When multiple users access the network through different computing power network access nodes, the computing power scheduling strategy includes public path information and independent path information of the user group. The apparatus of claim 37, wherein the processor is configured to read the computer program in the memory and perform the following operations: Obtain group computing power business requirements sent by user groups; Send the group computing power service demand to the first device. The apparatus of claim 44, wherein the processor is configured to read the computer program in the memory and perform at least one of the following operations: Obtain computing power business requirements of multiple users, where the multiple users belong to the same user group; Process each user's computing power business requirements separately to obtain the user's computing power requirement list and network requirement list; Aggregate the computing power requirement lists of multiple users and aggregate the network requirement lists of multiple users to obtain the group computing power service requirements of the user group. The apparatus of claim 45, wherein the processor is configured to read the computer program in the memory and perform the following operations: According to the first aggregation principle, the computing power demand lists of multiple users are aggregated; The first aggregation principle includes at least one of the following: Aggregation principles related to computing resource types; Aggregation principles related to computing power; Aggregation principles related to the location of computing resources; Aggregation principles related to computing power usage time. The apparatus of claim 45, wherein the processor is configured to read the computer program in the memory and perform the following operations: According to the second aggregation principle, the network demand lists of multiple users are aggregated; The second aggregation principle includes at least one of the following: Group maximum bandwidth principle; Group minimum delay principle; Group minimum packet loss rate principle. The apparatus of claim 37, wherein the processor is configured to read the computer program in the memory and perform the following operations: Broadcast or multicast the computing power scheduling strategy to users. A computing power scheduling device, applied to a first device, comprising: A first acquisition unit is used to obtain the group computing power business requirements of the user group; A first generating unit, configured to generate a computing power scheduling strategy according to the computing power service requirements of the group; The first sending unit is used to send the computing power scheduling policy to the user group and/or the nodes included in the computing power scheduling policy. A computing power scheduling device, applied to a second device, comprising: The first receiving unit is configured to receive a computing power scheduling policy sent by the first device, where the computing power scheduling policy is generated based on a group computing power service requirement of a user group. A processor-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the computing power scheduling method as described in any one of claims 1 to 12, or implements the steps of the computing power scheduling method as described in any one of claims 13 to 24. A computer program product comprising computer instructions, which, when executed by a processor, implement the steps of the computing power scheduling method as described in any one of claims 1 to 12, or implement the steps of the computing power scheduling method as described in any one of claims 13 to 24.