CN118659848B - Predicting wireless channel data, electronic device, computer readable medium - Google Patents
Predicting wireless channel data, electronic device, computer readable medium Download PDFInfo
- Publication number
- CN118659848B CN118659848B CN202410014103.7A CN202410014103A CN118659848B CN 118659848 B CN118659848 B CN 118659848B CN 202410014103 A CN202410014103 A CN 202410014103A CN 118659848 B CN118659848 B CN 118659848B
- Authority
- CN
- China
- Prior art keywords
- wireless channel
- sample
- channel data
- data
- confidence
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B17/00—Monitoring; Testing
- H04B17/30—Monitoring; Testing of propagation channels
- H04B17/391—Modelling the propagation channel
- H04B17/3913—Predictive models, e.g. based on neural network models
Landscapes
- Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The disclosure provides a method for predicting wireless channel data, which comprises the steps of obtaining a plurality of sample groups, determining group confidence of each sample group, wherein each sample group comprises a plurality of sample wireless channel data generated by a wireless channel modeling process, characterizing the credibility of the sample wireless channel data in the sample group, and determining target wireless channel data according to the plurality of sample wireless channel data and the corresponding group confidence. The disclosure also provides an electronic device, a computer readable medium.
Description
Technical Field
The present disclosure relates to the field of wireless channel modeling technology, and in particular, to a method, an electronic device, and a computer readable medium for predicting wireless channel data.
Background
The wireless channel modeling can provide important basis for planning, designing, testing, shaping, adjusting, optimizing and the like of a wireless network (wireless communication network).
However, the existing various wireless channel modeling techniques have unavoidable drawbacks, cannot adapt to the evolution of a wireless network, cannot perform full life cycle modeling, or have low accuracy, or have high cost, or influence normal communication services.
Disclosure of Invention
The present disclosure provides a method, electronic device, computer readable medium for predicting wireless channel data.
In a first aspect, embodiments of the present disclosure provide a method of predicting wireless channel data, comprising:
Obtaining a plurality of sample sets, each of the sample sets comprising a plurality of sample wireless channel data generated by a wireless channel modeling process;
determining a group confidence of each sample group, wherein the group confidence characterizes the credibility of the sample wireless channel data in the sample group;
and determining target wireless channel data according to the plurality of sample wireless channel data and the group confidence corresponding to the sample wireless channel data.
In a second aspect, the disclosed embodiments provide an electronic device comprising a memory, a processor, the memory storing a computer program executable by the processor, the computer program when executed by the processor implementing any one of the methods of predicting wireless channel data of the disclosed embodiments.
In a third aspect, the disclosed embodiments provide a computer readable medium having stored thereon a computer program which, when executed by a processor, implements any of the methods of predicting wireless channel data of the disclosed embodiments.
In the embodiment of the disclosure, the target wireless channel data is obtained by integrating (fusing) the group confidence of the sample wireless channel data (a plurality of data sources) from a plurality of wireless channel modeling processes, that is, the wireless channel modeling is realized, so that the advantages of various data sources can be fully utilized to avoid defects of the wireless channel data, the evolution of a wireless network can be adapted, the full life cycle modeling is realized, and meanwhile, the accuracy is high, the cost is low, and normal communication service is not influenced.
Drawings
In the drawings of the embodiments of the present disclosure:
fig. 1 is a flowchart of a method for predicting wireless channel data according to an embodiment of the present disclosure;
Fig. 2 is a flowchart of another method of predicting wireless channel data provided by an embodiment of the present disclosure;
FIG. 3 is a block diagram of an electronic device according to an embodiment of the present disclosure;
FIG. 4 is a block diagram of one computer-readable medium provided by an embodiment of the present disclosure;
fig. 5 is a process diagram of another method for predicting wireless channel data according to an embodiment of the present disclosure;
fig. 6 is a process diagram of another method for predicting wireless channel data according to an embodiment of the present disclosure.
Detailed Description
For better understanding of the technical solutions of the present disclosure, the following describes in detail a method, an electronic device, and a computer readable medium for predicting wireless channel data provided by embodiments of the present disclosure with reference to the accompanying drawings.
The present disclosure will be described more fully hereinafter with reference to the accompanying drawings, but the embodiments shown may be embodied in different forms and should not be construed as limited to the embodiments set forth below. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
The accompanying drawings, which are included to provide a further understanding of embodiments of the disclosure and are incorporated in and constitute a part of this specification, illustrate the disclosure and together with the detailed embodiment, do not limit the disclosure. The above and other features and advantages will become more readily apparent to those skilled in the art from the description of the detailed embodiments with reference to the accompanying drawings.
The present disclosure may be described with reference to plan and/or cross-sectional views with the aid of idealized schematic diagrams of the present disclosure. Accordingly, the example illustrations may be modified in accordance with manufacturing techniques and/or tolerances.
Embodiments of the disclosure and features of embodiments may be combined with each other without conflict.
The terminology used in the present disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The term "and/or" as used in this disclosure includes any and all combinations of one or more of the associated listed items. As used in this disclosure, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. The terms "comprising," "including," and "includes" as used in this disclosure "made by.,. The presence of said features, integers, steps, operations, elements, and/or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and/or groups thereof.
Unless otherwise defined, all terms (including technical and scientific terms) used in this disclosure have the same meaning as commonly understood by one of ordinary skill in the art. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and the present disclosure, and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
The present disclosure is not limited to the embodiments shown in the drawings, but includes modifications of the configuration formed based on the manufacturing process. Thus, the regions illustrated in the figures have schematic properties and the shapes of the regions illustrated in the figures illustrate the particular shapes of the regions of the elements, but are not intended to be limiting.
The wireless channel modeling is to build an abstract model of a wireless channel (a channel of wireless communication) by a certain means, and to conduct research and simulation of the wireless channel according to the built model so as to predict the technology of wireless channel data, wherein the predicted wireless channel data can be used for planning, designing, testing, shaping, adjusting, optimizing and the like of a wireless network so as to improve the performance and efficiency of the wireless network.
In some cases, data-driven wireless channel modeling may be employed, i.e., rather than using a generalized unified model, dedicated modeling for a particular usage scenario (e.g., target area) may be performed based on data for that scenario.
For example, data-driven wireless channel modeling may include the following categories:
(1) Ray tracing wireless channel modeling
The method is used for constructing a spatial scene model (three-dimensional model) of a target area to be predicted in advance, wherein the spatial scene model comprises information of structures, such as positions, shapes, surface properties (such as reflectivity to electromagnetic waves) and the like, generated by propagation of wireless signals (beams or rays of wireless channels) of buildings, terrains and the like in the target area, so that transmission conditions of the wireless signals can be simulated in the spatial scene model, such as calculation of what structures the wireless signals encounter, how reflection/scattering can be carried out on the structures and the like, and further calculation of the conditions of the wireless signals reaching specific positions, namely prediction of wireless channel data, such as signal-to-noise ratio, multipath amplitude, phase and the like of the wireless channels.
The ray tracing wireless channel modeling does not need to use an actual detection device, can be realized only according to a digital map, a photo and the like of a target area, does not need to actually exist a wireless network, and can be performed without the wireless network.
However, the accuracy of the spatial scene model is limited, such as the surface properties of different buildings, even the surface properties of different positions of a building may be different, and the propagation of wireless signals is affected by variable conditions such as moving objects such as vehicles and climates in the target area, so that it is difficult to build a spatial scene model accurately including all factors affecting the propagation of wireless signals, and the natural accuracy of wireless channel data obtained according to an inaccurate spatial scene model is not high.
(2) Channel sounding wireless channel modeling
According to the method, a plurality of special detection devices (such as Sounder detectors) are deployed in a target area to be modeled, the Sounder detectors are connected with each other through a wireless network, each Sounder detector acquires actual measurement data of wireless signals of the corresponding Sounder detector, such as channel response, channel loss, transmission time delay, RSSI (received signal strength indicator), RTT (round trip time) and the like, and the actual measurement data are uploaded and stored in a central server, and the central server performs denoising, channel parameter estimation, propagation path analysis and the like on the actual measurement data, and builds a model according to the processing results so as to predict future wireless channel conditions (wireless channel data).
The modeling of the channel detection wireless channel depends on measured data, so the accuracy is higher.
However, the channel detection wireless channel modeling needs to use a large number of special detection devices, and the detection devices are deployed and detected for each target area separately, so that the method has high cost, long time consumption and high cost, and cannot be used in a stage that the wireless network is not deployed yet.
(3) Network on-line wireless channel modeling
In the method, communication equipment (such as a mobile phone, a base station and the like) which is actually deployed and operates in a wireless network is used as a detection device, actual measurement data generated in the communication process is recorded, and the actual measurement data are used for modeling and predicting wireless channel data.
The modeling of the network online wireless channel also depends on measured data, so the modeling has higher accuracy, does not need to use and deploy special detection devices, and is easy to realize.
Network online wireless channel modeling relies on communication devices that operate properly and requires consumption of bandwidth and resources in normal communications, thereby affecting normal traffic and also not being useful in stages where the wireless network has not been deployed.
Therefore, various wire-wireless channel modeling technologies in the related technology all use data from a single source, so that each wire-wireless channel modeling has inherent defects which cannot be avoided, cannot adapt to the evolution of a wireless network, cannot perform full life cycle modeling, has low accuracy or high cost, or affects normal communication service.
In a first aspect, embodiments of the present disclosure provide a method of predicting wireless channel data.
Embodiments of the present disclosure are used to predict (wireless channel model) wireless channel conditions in a wireless network (e.g., a wireless network of a target area) to obtain target wireless channel data, such as signal-to-noise ratio, multipath amplitude, phase, etc., of a wireless channel.
Referring to fig. 1, a method of predicting wireless channel data according to an embodiment of the present disclosure includes:
S101, acquiring a plurality of sample groups.
Wherein each sample set includes a plurality of sample wireless channel data generated by a wireless channel modeling process.
S102, determining the group confidence of each sample group.
Wherein the group confidence characterizes a degree of confidence of the sample wireless channel data in the sample group.
S103, determining target wireless channel data according to the plurality of sample wireless channel data and the corresponding group confidence coefficient.
The disclosed embodiments first obtain a plurality of sample groups as operation basis, each sample group including a plurality of sample wireless channel data of a wireless network to be predicted, all sample wireless channel data in the same sample group being generated in one wireless channel modeling process, that is, a result of one wireless channel modeling process.
The term "sample wireless channel data generated by a wireless channel modeling process" refers to a plurality of data detected by a detecting device (e.g., sounder detector) of the wireless channel modeling technology, or a plurality of data detected by a plurality of detecting devices, or a plurality of data obtained in a single prediction process according to the type of wireless channel modeling technology, etc., so that they have the same degree of reliability.
Wherein each sample wireless channel data may be a channel multipath component, each channel multipath component comprising a plurality of specific parameters, and a jth channel multipath component of a kth (k=1,..once., K) sample group of a total of K sample groups may be denoted as x k,j, and there isWherein each parameter sequentially represents the power, time delay, horizontal azimuth of transmission, vertical azimuth of transmission, horizontal azimuth of reception and vertical azimuth of reception of the wireless channel.
It should be appreciated that the specific parameters of the channel multipath component are not limited to the above examples, as other parameters may also be included, such as whether the wireless channel is a line-of-sight wireless channel.
Thus, each sample set corresponds to a "set" of channel multipath components, e.g., the kth sample set can be written asThe representative sample group is a set of J k channel multipath components, so that the number of channel multipath components in all sample groups is
As before, the plurality of sample wireless channel data in each sample group is generated through the same wireless channel modeling process, so the confidence level should be the same, and therefore, the group confidence level of each sample group can be continuously calculated, that is, the confidence level of each sample wireless channel data (necessarily belonging to one sample group) is obtained.
Furthermore, the plurality of sample wireless channel data can be fused according to the corresponding group confidence (equivalent to weight) so as to obtain target wireless channel data as a prediction result, and wireless channel modeling is realized.
In the embodiment of the disclosure, the target wireless channel data is obtained by integrating (fusing) the group confidence of the sample wireless channel data (a plurality of data sources) from a plurality of wireless channel modeling processes, that is, the wireless channel modeling is realized, so that the advantages of various data sources can be fully utilized to avoid defects of the wireless channel data, the evolution of a wireless network can be adapted, the full life cycle modeling is realized, and meanwhile, the accuracy is high, the cost is low, and normal communication service is not influenced.
In some embodiments, the categories of wireless channel modeling processes include at least one of ray traced wireless channel modeling, channel explored wireless channel modeling, network online wireless channel modeling.
As one way of an embodiment of the present disclosure, a specific kind of wireless channel modeling process for each sample set may be the above ray tracing wireless channel modeling, channel sounding wireless channel modeling, network online wireless channel modeling, and so on.
It should be appreciated that the specific kind of wireless channel modeling process in the embodiments of the present disclosure is also not limited to the above examples, and any wireless channel modeling technique is available as long as sample wireless channel data is available.
In some embodiments, the wireless channel modeling process for at least a portion of the sample set is heterogeneous;
and/or the number of the groups of groups,
The wireless channel modeling processes of at least part of the sample groups are the same in kind, and the wireless channel modeling processes of any two sample groups are respectively carried out in two time periods, the time difference between the two time periods exceeds a preset time threshold, and the duration of each time period does not exceed the time threshold.
As one way of an embodiment of the present disclosure, sample wireless channel data (e.g., data collected by different detection devices) obtained by different kinds of wireless channel modeling techniques belong to different sample groups.
As another way of the embodiment of the present disclosure, sample wireless channel data (such as data collected by one collecting device on 1 month, 1 day and 2 months, 2 days) obtained by the same wireless channel modeling technology at two times with longer intervals (exceeding a time threshold, such as 1 month intervals) may also be used as different sample groups, because the situation of the wireless network will change significantly when the time interval is longer, so that the credibility of the data obtained by the same wireless channel modeling technology will also change, that is, the confidence of the group of the sample wireless channel data is different, so the sample wireless channel data should be regarded as different sample groups. Accordingly, the acquisition times of the plurality of sample radio channel data in one sample group cannot differ too much (e.g., not exceed a time threshold).
In some embodiments, referring to fig. 2, determining the group confidence for each sample group (S102) includes:
s1021, determining the group confidence of each sample group according to at least one of the category sub-confidence, the device sub-confidence and the data sub-confidence of the sample group.
The device sub-confidence represents the credibility of the detection device used in the wireless channel modeling process of the sample group, and the data sub-confidence represents the credibility of sample wireless channel data in the sample group.
As one way of an embodiment of the present disclosure, the group confidence of each sample group may be calculated from three components (or some of them) of the category sub-confidence, the device sub-confidence, and the data sub-confidence.
The confidence level of the seed indicates the confidence level of the wireless channel modeling technology itself adopted by the sample group, which may be a value preset according to experience, for example, the confidence levels of the seed corresponding to the various wireless channel modeling technologies may be preset in advance.
In the same kind of wireless channel modeling technology, the performances of different acquisition devices (such as acquisition devices of different grades, different manufacturers and different models) are also different, and the credibility of the generated sample wireless channel data is also different, so that corresponding confidence components, namely device sub-confidence, can be preset for various acquisition devices according to experience.
The multiple sample wireless channel data obtained in each wireless channel modeling process can also indicate the credibility of the wireless channel data, so that the corresponding data sub-confidence can be directly calculated according to the sample wireless channel data in the sample group.
It should be appreciated that the specific manner in which the group confidence is determined based on the class sub-confidence, the device sub-confidence, and the data sub-confidence may be varied, for example, the group confidence w k for the kth sample group may be calculated by the following equation:
wk=qk,1·qk,2·qk,3;
Wherein q k,1 represents the sub-confidence of the type of the kth sample group, and q k,1 corresponding to the three modes of ray tracing wireless channel modeling, channel detection wireless channel modeling and network online wireless channel modeling can be set to be 0.6, 1 and 0.8 respectively.
Q k,2 represents the device sub-confidence of the kth sample group, e.g., q k,2 for a high-precision probe device can be set to 1, while q k,2 for a conventional probe device is set to 0.8.
Qk,3 represents the data sub-confidence of the kth sample group, which is calculated from the sample radio channel data in the sample group, e.g., M correlation parameters s 1,...sM are obtained from the sample radio channel data, and a function q k,3=f(s1,...sM) is set for calculating q k,3.
It should be appreciated that the specific manner of calculating the group confidence in the embodiments of the present disclosure is not limited to the above examples, e.g., q k,1、qk,2、qk,3 may be added as the group confidence, or the group confidence may be calculated based on only one or two sub-confidence levels in q k,1、qk,2、qk,3, or the sub-confidence levels may be selected based on other factors as well, etc.
It should be understood that when the wireless channel modeling of all the data sets is the same in kind, or the types of the probe devices are the same, the values of the kind sub-confidence and the device sub-confidence used in calculating the group confidence may be the same, or the components of the kind sub-confidence and the device sub-confidence may not be used in calculating.
In some embodiments, the data sub-confidence is calculated in a negative correlation based on the dispersion and/or variance of the sample wireless channel data in the sample group.
As a mode of the embodiment of the disclosure, parameters such as dispersion, variance and the like of sample wireless channel data can be calculated first, and the data sub-confidence coefficient is calculated according to an algorithm (namely a negative correlation mode) that the larger the dispersion and variance are, the smaller the data sub-confidence coefficient is, in general, the sample wireless channel data generated in a wireless channel modeling process should be similar, the larger the difference is, the lower the credibility of the sample wireless channel data per se is, and the dispersion, variance and the like can indicate the similarity of the data, so the data sub-confidence coefficient can be calculated in a negative correlation mode according to the dispersion, variance and the like.
It should be appreciated that the specific algorithm of the data sub-confidence in the embodiments of the present disclosure is not limited to the above examples, and may also calculate the data sub-confidence according to parameters such as signal-to-noise ratio in the sample wireless channel data.
In some embodiments, referring to fig. 2, determining target wireless channel data from the plurality of sample wireless channel data and its corresponding group confidence level (S103) includes:
s1031, clustering the plurality of sample wireless channel data into a plurality of clusters.
S1032, determining at least part of the clusters as trusted clusters according to the sample wireless channel data in the clusters.
S1033, respectively determining corresponding target wireless channel data according to the sample wireless channel data in each trusted cluster and the corresponding group confidence coefficient.
The method for determining target wireless channel data according to sample wireless channel data includes the steps of firstly clustering all sample wireless channel data, namely dividing all sample wireless channel data into a plurality of classes (clusters), wherein each cluster comprises a plurality of sample wireless channel data which are similar, determining whether the reliability of the cluster is high enough or not according to the situation of the sample wireless channel data in each cluster, determining that the cluster which is reliable is a reliable cluster, and further, calculating the target wireless channel data corresponding to the reliable cluster according to the sample wireless channel data (namely the plurality of sample wireless channel data which are similar and have high reliability) and the group confidence of each reliable cluster.
In some embodiments, referring to fig. 2, clustering the plurality of sample wireless channel data into a plurality of clusters (S1031) includes:
S10311, unsupervised clustering of the plurality of sample wireless channel data into a plurality of clusters.
As a way of an embodiment of the present disclosure, clustering of sample wireless channel data may specifically be "unsupervised clustering", such as k-means (k-means) clustering, k-median (k-means) clustering, and the like.
The basic flow of the unsupervised clustering comprises the following steps:
(1) The number N of clusters to be generated is predetermined, and N are randomly selected as cluster centers from all sample wireless channel data.
(2) Each sample radio channel data is grouped into clusters that are closest to its cluster center.
(3) Calculating the central position of all sample wireless channel data in each cluster as a new cluster center, returning to the step (2), and re-determining the cluster to which each sample wireless channel data belongs according to the new cluster center.
(4) This loops until the cluster to which all sample radio channel data belongs no longer changes.
Thus, N clusters (i.e., sets of channel multipath components) a n, n=1, N, where, a n contains I n sample wireless channel data (channel multipath component) { x k′,j′ }, which may be from the same or different sample groups.
It should be appreciated that the specific manner of unsupervised clustering is not limited to k-means, k-media, etc., nor is the clustering available in embodiments of the present disclosure limited to unsupervised clustering.
The wireless channel data of each sample (each channel multipath component) may be clustered as a multidimensional vector (the dimension is equal to the number of parameters therein), or may be clustered after each sample wireless channel data is converted into a feature vector, for example, the feature vector of the channel multipath component x k,j may be defined as:
wherein, beta is a normalized weight coefficient;
further, in the above clustering process, the distance between the two sample wireless channel data x k1,j1 and x k2,j2 (or the distance between the sample wireless channel data and the clustering center) can be defined as:
D(xk1,j1,xk2,j2)=||F(xk1,j1)-F(xk2,j2)||;
wherein, the inner product induction norm (may also be other functions or calculators with similar properties) is represented by the |·|.
In some embodiments, referring to fig. 2, determining at least a portion of the clusters as trusted clusters based on the sample wireless channel data in the clusters (S1032) comprises:
s10321, determining at least part of the clusters as trusted clusters according to the group confidence corresponding to the sample wireless channel data in the clusters and/or according to the number of sample groups to which the sample wireless channel data in the clusters belong.
As a way of the embodiment of the present disclosure, the higher the group confidence of the sample wireless channel data in the cluster, the higher the confidence level of the sample wireless channel data in the cluster, so the group confidence of the sample wireless channel data in the cluster can be used as one of the bases for determining the trusted cluster.
As another mode of the embodiment of the present disclosure, if the sample wireless channel data in the cluster is from a plurality of different sample groups, the data diversity is good, and the inherent defect of a single sample group can be more effectively avoided, so that the number of sample groups from which the sample wireless channel data in the cluster is from can be used as one of the bases for determining the trusted cluster.
It should be appreciated that the specific algorithm above to determine the trusted cluster may be varied.
For example, for each clusterIt may be assumed that there are M sample radio channel data therein, and that each sample radio channel data comes from one sample group { k 'm }, a decision function T ({ k' n }) may be used to determine whether the cluster is a trusted cluster, i.e., T ({ k 'm) } =1 represents a trusted cluster and T ({ k' m) } =0 represents a non-trusted cluster.
Further, T ({ k' n }) can be expressed specifically as:
The Threshold is a preset Threshold, that is, the sum of the group confidence of all sample wireless channel data in a cluster can be considered, if the sum exceeds the Threshold, the cluster is a trusted cluster, and if the sum does not exceed the Threshold, the cluster is not a trusted cluster.
Or T ({ k' n }) can also be expressed as:
that is, it can be considered that if one cluster includes sample wireless channel data from all sample groups, it is a trusted cluster, and if one cluster lacks sample wireless channel data for one or more sample groups, it is not a trusted cluster.
Or T ({ k' n }) can also combine the two criteria, as can be expressed as:
T3({k′m})=T1({k′m})T2({k′m})。
It should be understood that the specific manner of determining the trusted cluster is not limited to the above example, for example, the trusted cluster may be considered when the number of source sample groups of sample wireless channel data in one cluster exceeds a predetermined value (not all of them), or a sub-value may be calculated according to the group confidence of the sample wireless channel data in the cluster and the number of source sample groups, respectively, and then whether the cluster is a trusted cluster may be determined according to whether the sum of the sub-values reaches the predetermined value, or other parameters of the cluster (such as the number of sample wireless channel data in the cluster) may be used as one of the parameters for determining the trusted cluster.
In some embodiments, determining (S1033) corresponding target wireless channel data from the sample wireless channel data and its corresponding group confidence in each trusted cluster, respectively, includes:
S10331, multiplying each sample wireless channel data in each trusted cluster by the corresponding group confidence coefficient, and then summing, dividing the summed result by the sum of the group confidence coefficients corresponding to all sample wireless channel data in the trusted cluster, so as to obtain the target wireless channel data corresponding to the trusted cluster.
As one way of an embodiment of the disclosure, for each trusted cluster, the group confidence therein may be used as a "weight" of the corresponding sample wireless channel data, and the target wireless channel data may be calculated according to each sample wireless channel data in a weight averaging manner.
For example, suppose that L trusted clusters B l, n=1, L are selected out of N clusters a n, n=1,..n, where the first trusted cluster is LIncluding V sample radio channel data, target radio channel data including a plurality of parameters can be calculated by the following formula
Further, for L trusted clusters, a total of L y l are available, i.e., L target wireless channel data as a prediction result are obtained.
It should be understood that the method of predicting wireless channel data of embodiments of the present disclosure may also include other steps.
For example, probe devices (such as Sounder probes) required by various wireless channel modeling techniques may be arranged in the target area in advance, data (sample wireless channel data) acquired by the probe devices may be collected, and a sample group may be formed by using data from the same probe device.
For example, the sample wireless channel data collected by the detection device or the sample wireless channel data in the sample group can be preprocessed (i.e. data cleaning) first, and obvious error data such as excessive power value and time delay, and scheduling which does not conform to the value range can be deleted.
Example 1:
an exemplary description of a specific method of predicting wireless channel data according to embodiments of the present disclosure is provided below, with reference to fig. 5, which may include the steps of:
(1) Radio channel data (sample radio channel data) acquisition
A ray tracing channel generator (a detection device for ray tracing wireless channel modeling technology), sounder detectors (a detection device for channel detection wireless channel modeling technology) and communication equipment (a detection device for network online wireless channel modeling technology) are arranged in a target area.
Wherein each detector device can collect a plurality of radio channel data, i.e., a plurality of channel multipath components, and output them as a data set (sample set).
There are a total of 3 detection devices, wherein the data set output by the kth (k=1,..k; k=3) detection device is recorded asIt contains J k channel multipath components, each channel multipath component being counted asWherein, each parameter represents the power, time delay, horizontal emission angle, vertical emission angle, horizontal receiving angle and vertical receiving angle of the wireless channel in turn.
(2) Wireless channel data preprocessing
For the above obtained co-ordinatesThe multipath components of the strip channel are filtered to exclude data with obvious errors, such as excessive power values and time delays, scheduling without conforming to the value range, and the like.
(3) Determining confidence coefficients (group confidence) for a data set
The filtered wireless channel data from the kth data set is endowed with a corresponding confidence coefficient w k, and the confidence coefficient is calculated as follows:
wk=qk,1·qk,2·qk,3;
Wherein q k,1 represents the confidence (type sub-confidence) corresponding to the type of the wireless channel modeling technology of the kth data set, q k,1 corresponding to the ray tracing channel generator, the Sounder detector and the communication equipment are specifically set to be 0.6, 1 and 0.8 respectively, q k,2 represents the confidence (device sub-confidence) of the detection device of the specific model for the kth data set, 1;q k,3 represents the confidence (data sub-confidence) of the wireless channel data in the kth data set, and q k,3 is set to be equal to the reciprocal of the wireless channel data variance in the data set.
(4) Wireless channel data clustering
Will be togetherThe multi-path component of the strip channel is used as a sample point to carry out unsupervised clustering, wherein the feature vector of the sample point x k,j is defined as:
Where β is the inverse of the maximum time delay of all sample o' clock, and thus the distance between two sample points x k1,j1 and x k2,j2 in the cluster can be defined as:
D(xk1,j1,xk2,j2)=||F(xk1,j1)-F(xk2,j2)||;
wherein, and I are inner product induction norms.
The unsupervised clustering specifically adopts a K-Means algorithm, and the number of clusters obtained is set to be N, wherein N is the maximum value of multipath components of all channels.
The clustered sample points { x k′,j } in each cluster are output as one initial classification set (cluster), yielding N initial classification sets a n, n=1, N, where a n contains I n channel multipath components, possibly from one or more data sets.
(5) Initial classification set reliability discrimination
For each initial classification setAssuming that it includes M channel multipath components, a source data set { k ' m } in which each channel multipath component is counted, a decision function T ({ k ' n }) is used to determine whether the initial classification set is reliable, and the initial classification set of T ({ k ' m }) =1 is set as a trusted classification set (trusted cluster).
Wherein T ({ k' n }) is expressed as:
From this, L trusted classification sets B l, n=1, L.
(6) Obtaining an estimated wireless channel multipath component (target wireless channel data)
Let l trusted class set B l contain V channel multipath components, i.eThen to thereinThe following operations are performed (specifically, for each parameter:
and obtains a new estimated channel multipath component
Thus, L channel multipath components y l are obtained as the final prediction result.
Example 2:
an exemplary description of a specific method of predicting wireless channel data in accordance with embodiments of the present disclosure is provided below, with reference to fig. 6, which may include the steps of:
(1) Radio channel data (sample radio channel data) acquisition
Wireless channel data is acquired in a target area with a communication device (probe device for network online wireless channel modeling techniques).
The communication device collects a plurality of wireless channel data, that is, a plurality of channel multipath components, on each of days 5,1, 6, 1, and 7,1, respectively, wherein the plurality of channel multipath components collected on the same day are output as one data set (sample set), and the channel multipath components collected on different days belong to different data sets.
The collection was performed on 3 days, respectively, where on the kth day (k=1,. -%, K; k=3) the collected data set is noted asIt contains J k channel multipath components, each channel multipath component being counted asWherein, each parameter represents the power, time delay, horizontal emission angle, vertical emission angle, horizontal receiving angle and vertical receiving angle of the wireless channel in turn.
(2) Wireless channel data preprocessing
For the above obtained co-ordinatesThe multipath components of the strip channel are filtered to exclude data with obvious errors, such as excessive power values and time delays, scheduling without conforming to the value range, and the like.
(3) Determining confidence coefficients (group confidence) for a data set
The filtered wireless channel data from the kth data set is endowed with a corresponding confidence coefficient w k, and the confidence coefficient is calculated as follows:
wk=qk,1·qk,2·qk,3;
Where q k,1 represents the confidence (type sub-confidence) corresponding to the type of the wireless channel modeling technique of the kth data set, q k,2 represents the confidence of the specific type of probe device used for the kth data set, and since the same communication device is used for acquisition in this example 2, q k,1、qk,2 is set to 1;q k,3 to represent the confidence (data sub-confidence) of the wireless channel data itself in the kth data set, and q k,3 is set to be an exponential function of the signal-to-noise ratio of the wireless channel data in the data set, namely:
qk,3=γexp(SNRk);
wherein, gamma is a normalization parameter.
(4) Wireless channel data clustering
Will be togetherThe multi-path component of the strip channel is used as a sample point to carry out unsupervised clustering, wherein the feature vector of the sample point x k,j is defined as:
Where β is the inverse of the maximum time delay of all sample o' clock, and thus the distance between two sample points x k1,j1 and x k2,j2 in the cluster can be defined as:
D(xk1,j1,xk2,j2)=||F(xk1,j1)-F(xk2,j2)||;
wherein, the terms "and" are the norms induced by the inner product ". Functions with the same properties.
The unsupervised clustering specifically adopts a k-medeian algorithm, and the number of the clusters is set to be N, wherein N is the maximum value of multipath components of all channels.
The clustered sample points { x k′,j } in each cluster are output as one initial classification set (cluster), yielding N initial classification sets a n, n=1, N, where a n contains I n channel multipath components, possibly from one or more data sets.
(5) Initial classification set reliability discrimination
For each initial classification setAssuming that it includes M channel multipath components, a source data set { k ' m } in which each channel multipath component is counted, a decision function T ({ k ' n }) is used to determine whether the initial classification set is reliable, and the initial classification set of T ({ k ' m }) =1 is set as a trusted classification set (trusted cluster).
Wherein T ({ k' n }) is expressed as:
Wherein Threshold is a preset Threshold value.
From this, L trusted classification sets B l, n=1, L.
(6) Obtaining an estimated wireless channel multipath component (target wireless channel data)
Let l trusted class set B l contain V channel multipath components, i.eThen to thereinThe following operations are performed (specifically, for each parameter:
and obtains a new estimated channel multipath component
Thus, L channel multipath components y l are obtained as the final prediction result.
In a second aspect, referring to fig. 3, an embodiment of the present disclosure provides an electronic device, including a memory, and a processor, where the memory stores a computer program executable by the processor, and where the computer program when executed by the processor implements any one of the methods of predicting wireless channel data of the embodiments of the present disclosure.
In a third aspect, referring to fig. 4, the disclosed embodiments provide a computer readable medium having a computer program stored thereon, which when executed by a processor implements any of the methods of predicting wireless channel data of the disclosed embodiments.
The processor is a device with data processing capability, including but not limited to a Central Processing Unit (CPU), the memory is a device with data storage capability, including but not limited to a random access memory (RAM, more specifically SDRAM, DDR, etc.), a read-only memory (ROM), a charged erasable programmable read-only memory (EEPROM) and a FLASH memory (FLASH), and the I/O interface (read-write interface) is connected between the processor and the memory, so that the information interaction between the memory and the processor can be realized, including but not limited to a data Bus (Bus), etc.
Those of ordinary skill in the art will appreciate that all or some of the steps, systems, functional modules/units in the apparatus disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof.
In a hardware implementation, the division between functional modules/units mentioned in the above description does not necessarily correspond to the division of physical components, for example, one physical component may have a plurality of functions, or one function or step may be cooperatively performed by several physical components.
Some or all of the physical components may be implemented as software executed by a processor, such as a Central Processing Unit (CPU), digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). The term computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, as known to those skilled in the art. Computer storage media includes, but is not limited to, random access memory (RAM, more specifically SDRAM, DDR, etc.), read-only memory (ROM), electrically charged erasable programmable read-only memory (EEPROM), FLASH memory (FLASH) or other magnetic disk storage, compact disk read-only memory (CD-ROM), digital Versatile Disk (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage, and any other medium which can be used to store the desired information and which can be accessed by a computer. Furthermore, as is well known to those of ordinary skill in the art, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media.
The present disclosure has disclosed example embodiments, and although specific terms are employed, they are used and should be interpreted in a generic and descriptive sense only and not for purpose of limitation. In some instances, it will be apparent to one skilled in the art that features, characteristics, and/or elements described in connection with a particular embodiment may be used alone or in combination with other embodiments unless explicitly stated otherwise. It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the scope of the disclosure as set forth in the appended claims.
Claims (9)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410014103.7A CN118659848B (en) | 2024-01-02 | 2024-01-02 | Predicting wireless channel data, electronic device, computer readable medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410014103.7A CN118659848B (en) | 2024-01-02 | 2024-01-02 | Predicting wireless channel data, electronic device, computer readable medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN118659848A CN118659848A (en) | 2024-09-17 |
CN118659848B true CN118659848B (en) | 2025-03-28 |
Family
ID=92706820
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410014103.7A Active CN118659848B (en) | 2024-01-02 | 2024-01-02 | Predicting wireless channel data, electronic device, computer readable medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN118659848B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN119094064B (en) * | 2024-10-29 | 2025-03-11 | 中兴通讯股份有限公司 | Channel model modeling method, device, equipment, storage medium and program product |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1251706A (en) * | 1997-02-14 | 2000-04-26 | 蜂窝电信有限公司 | Method and apparatus for wireless communication method for digital signals |
JP2013197831A (en) * | 2012-03-19 | 2013-09-30 | Mitsubishi Electric Corp | Radio communication device |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7551579B2 (en) * | 2006-05-08 | 2009-06-23 | Skyhook Wireless, Inc. | Calculation of quality of wlan access point characterization for use in a wlan positioning system |
US8886574B2 (en) * | 2012-06-12 | 2014-11-11 | Siemens Aktiengesellschaft | Generalized pattern recognition for fault diagnosis in machine condition monitoring |
WO2019205111A1 (en) * | 2018-04-27 | 2019-10-31 | 深圳市汇顶科技股份有限公司 | Method for merging data, apparatus, and device |
CN116032395B (en) * | 2021-10-25 | 2025-08-29 | 中国移动通信集团终端有限公司 | Wireless channel dynamic modeling method, device and electronic device |
CN114244459B (en) * | 2021-11-29 | 2022-10-25 | 西安电子科技大学 | Method, system, equipment and terminal for simulating wireless channel in marine environment |
-
2024
- 2024-01-02 CN CN202410014103.7A patent/CN118659848B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1251706A (en) * | 1997-02-14 | 2000-04-26 | 蜂窝电信有限公司 | Method and apparatus for wireless communication method for digital signals |
JP2013197831A (en) * | 2012-03-19 | 2013-09-30 | Mitsubishi Electric Corp | Radio communication device |
Also Published As
Publication number | Publication date |
---|---|
CN118659848A (en) | 2024-09-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109963287B (en) | Antenna direction angle optimization method, device, equipment and medium | |
US10374902B2 (en) | Method for clustering wireless channel MPCs based on a KPD doctrine | |
US20200143002A1 (en) | Data acquisition point deployment method and system | |
CN109951807A (en) | Fusion RSS and CSI indoor positioning method based on WiFi signal | |
US9369845B2 (en) | Methods and systems of assigning estimated positions and attributes to wireless access points in a positioning system | |
US11206555B2 (en) | Method for implementing antenna azimuth correction based on user data | |
Mirowski et al. | KL-divergence kernel regression for non-Gaussian fingerprint based localization | |
JP5123897B2 (en) | Indoor / outdoor determination apparatus and indoor / outdoor determination method | |
CN108174343B (en) | Wireless positioning method and system for power indoor communication operation and maintenance scene | |
CN107241700B (en) | Indoor positioning method based on CSI space-frequency characteristics and reference point location clustering algorithm | |
CN103533647B (en) | A kind of radio frequency map adaptive location method based on sub-clustering mechanism and robustness regression | |
CN106102161A (en) | Based on the data-optimized indoor orientation method of focusing solutions analysis | |
CN107241696B (en) | Multipath effect distinguishing method and distance estimation method based on channel state information | |
CN109874104B (en) | User position positioning method, device, equipment and medium | |
CN118659848B (en) | Predicting wireless channel data, electronic device, computer readable medium | |
CN108650626A (en) | A kind of fingerprinting localization algorithm based on Thiessen polygon | |
CN111770528B (en) | Line-of-sight and non-line-of-sight identification method and device based on channel parameter extraction method | |
CN113191224A (en) | Unmanned aerial vehicle signal extraction and identification method and system | |
CN115100376A (en) | Electromagnetic spectrum map implementation method based on improved inverse distance interpolation method | |
CN107677989A (en) | A kind of indoor location localization method that RSSI removal noises are carried out based on RSSI maximums | |
CN104821854A (en) | Multidimensional spectrum sensing method for multiple main users based on random sets | |
CN105519213B (en) | System and method for carrying out positioning and traffic density estimation by segmentation and calibration sampling | |
CN108919182B (en) | Target positioning method based on support set and expectation maximization in WIFI environment | |
CN109121081B (en) | An Indoor Localization Method Based on Location Candidate Set and EM Algorithm | |
CN108445443B (en) | KNN-based fingerprint point clustering method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |