[go: up one dir, main page]

CN119886567A - Intelligent power engineering management and control system and method based on big data - Google Patents

Intelligent power engineering management and control system and method based on big data Download PDF

Info

Publication number
CN119886567A
CN119886567A CN202510067978.8A CN202510067978A CN119886567A CN 119886567 A CN119886567 A CN 119886567A CN 202510067978 A CN202510067978 A CN 202510067978A CN 119886567 A CN119886567 A CN 119886567A
Authority
CN
China
Prior art keywords
data
source heterogeneous
heterogeneous data
coverage
deep learning
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.)
Pending
Application number
CN202510067978.8A
Other languages
Chinese (zh)
Inventor
王鹏宇
邓嵘
王奕镇
韦淦予
向小峰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangxi Pingban Hydropower Development Co ltd
Original Assignee
Guangxi Pingban Hydropower Development Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guangxi Pingban Hydropower Development Co ltd filed Critical Guangxi Pingban Hydropower Development Co ltd
Priority to CN202510067978.8A priority Critical patent/CN119886567A/en
Publication of CN119886567A publication Critical patent/CN119886567A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/047—Probabilistic or stochastic networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N7/00—Computing arrangements based on specific mathematical models
    • G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • Human Resources & Organizations (AREA)
  • Evolutionary Computation (AREA)
  • Economics (AREA)
  • General Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Strategic Management (AREA)
  • General Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Marketing (AREA)
  • Probability & Statistics with Applications (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Business, Economics & Management (AREA)
  • Tourism & Hospitality (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Molecular Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Mathematical Optimization (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Public Health (AREA)
  • Water Supply & Treatment (AREA)
  • Algebra (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Primary Health Care (AREA)
  • Pure & Applied Mathematics (AREA)
  • Evolutionary Biology (AREA)
  • Mathematical Analysis (AREA)
  • Development Economics (AREA)
  • Educational Administration (AREA)

Abstract

The invention discloses an intelligent management and control system and method for electric power engineering based on big data, and relates to the technical field of engineering risk management and control, wherein the intelligent management and control system comprises the steps of collecting multi-source heterogeneous data in a management and control area and dividing the multi-source heterogeneous data into suspicious data and non-suspicious data; when the multi-source heterogeneous data are non-suspicious data, carrying out fit degree analysis and coverage degree analysis on each multi-source heterogeneous data, evaluating the accuracy of the multi-source heterogeneous data, integrating the accurate data into a deep learning model according to an evaluation result, and predicting the overall management risk score of the electric power engineering through the deep learning model based on inaccurate data in the multi-source heterogeneous data. The method has the advantages that the coverage and consistency of the data are ensured through a multi-level data verification and risk assessment mechanism, the adverse effect of data distortion on power engineering management and control is fundamentally solved, and the reliability and practicability of a power engineering management and control system are remarkably improved.

Description

Intelligent power engineering management and control system and method based on big data
Technical Field
The invention relates to the technical field of engineering risk management and control, in particular to an intelligent management and control system and method for electric power engineering based on big data.
Background
Along with the rapid development of information technology, big data and artificial intelligence technology are applied to engineering management and control more and more widely, and especially in power engineering management and control, the efficiency and accuracy of engineering risk management and control can be greatly improved by utilizing real-time multi-source heterogeneous data. However, in practical application, the quality of the data becomes a key problem, the multi-source heterogeneous data often comes from different data sources including weather feature data, population density feature data and the like, and the data may have inconsistent, incomplete or distorted conditions, if the multi-source heterogeneous data is distorted in the process of training a big data analysis model, the multi-source heterogeneous data is inconsistent with the actual conditions, which may cause an engineering manager to be misled in making a decision or executing the decision, and in the emergency development process, if the multi-source heterogeneous data distortion condition cannot be predicted in advance in time, the decision maker may have understanding deviation in executing the decision, so that the risk event cannot be predicted accurately in time, and the engineering management risk is increased.
Disclosure of Invention
In order to solve the technical problems, the technical scheme solves the problems that the distortion condition of the multi-source heterogeneous data cannot be predicted in advance in time, and the decision maker can possibly cause understanding deviation in decision execution, so that risk events cannot be predicted accurately in time, and engineering management risks are increased.
In order to achieve the above purpose, the invention adopts the following technical scheme:
an intelligent management and control method for electric power engineering based on big data comprises the following steps:
Collecting multi-source heterogeneous data in a management and control area, comparing each multi-source heterogeneous data with historical multi-source heterogeneous data, and dividing the multi-source heterogeneous data into suspicious data and non-suspicious data according to a comparison result;
when the multi-source heterogeneous data are non-suspicious data, carrying out fit degree analysis on each multi-source heterogeneous data, and evaluating the integral fit degree of the multi-source heterogeneous data and the deep learning model;
when the multi-source heterogeneous data are non-suspicious data, performing coverage degree analysis on each multi-source heterogeneous data, and evaluating the overall coverage of the multi-source heterogeneous data;
comprehensively analyzing the overall fit degree of the multi-source heterogeneous data and the deep learning model and the overall coverage of the multi-source heterogeneous data, and evaluating the accuracy of the multi-source heterogeneous data;
dividing the multi-source heterogeneous data into accurate data and inaccurate data according to the evaluation result, and integrating the accurate data into a deep learning model;
based on inaccurate data in the multi-source heterogeneous data, predicting an overall management and control risk score of the power engineering through a deep learning model.
Preferably, the comparing each multi-source heterogeneous data with the historical multi-source heterogeneous data specifically includes:
Comparing the data feature vectors among different independent sources with the feature vectors of the corresponding historical data as a group of data;
Representing the new data collected at each point in time as a feature vector x n, where n is the number of features and x n represents the feature vector of the multi-source heterogeneous data currently collected;
The corresponding historical data is expressed as a characteristic vector y n,yn which represents the characteristic vector of the multi-source heterogeneous data collected in the history;
calculating the difference between the feature vectors by using a Euclidean distance calculation formula;
wherein, the Euclidean distance formula is:
Wherein d (x, y) is a difference degree value between the historical data and the current data.
Preferably, the classifying the multi-source heterogeneous data into suspicious data and non-suspicious data according to the comparison result specifically includes:
Judging whether the difference degree value between the data characteristic vectors between the independent sources and the characteristic vectors of the corresponding historical data is larger than or equal to a difference degree threshold value, if so, marking as suspicious data, and if not, marking as non-suspicious data.
Preferably, when the multi-source heterogeneous data is non-suspicious data, performing a fitness analysis on each multi-source heterogeneous data, and evaluating the overall fitness of the multi-source heterogeneous data and the deep learning model specifically includes:
Selecting characteristics capable of reflecting the relation between the data and the deep learning model from the multi-source heterogeneous data as nodes of the Bayesian network model;
For each node Ys, calculating the conditional probability thereof by a conditional probability calculation formula;
the conditional probability calculation formula is as follows:
Where P (Yp, xp) is the joint probability distribution of node Yp and all its parent nodes Xp, P (Xp) is the edge probability distribution of parent nodes Xp, and P (ys|xs) is the conditional probability of each node Ys;
calculating probability distribution for a target variable Xs under the overall target of the deep learning model;
Wherein, the probability distribution calculation formula is:
Wherein P (Xs-Ys) is probability distribution of a target variable Xs under the whole target of the deep learning model;
calculating the overall fitness deviation value of the multi-source heterogeneous data and the deep learning model through the calculated conditional probability P (ys|xs) and the probability distribution P (xs|ys) of the target variable;
The calculation formula of the fitness deviation value is as follows:
Where q is the number of data samples and D z is the fitness bias value between the multi-source heterogeneous data and the deep learning model.
Preferably, when the multi-source heterogeneous data is non-suspicious data, performing coverage analysis on each multi-source heterogeneous data, and evaluating the coverage of the whole multi-source heterogeneous data specifically includes:
dividing the collected time series data into a series of fixed length time windows, each window representing one hour of data;
calculating the coverage rate of the data sources in each time window, wherein the coverage rate is defined as the actual coverage area or time proportion of the data sources in the time window;
The coverage rate of the data source is calculated according to the following formula:
Wherein R (t) represents coverage within the time window t, A (t) is the area or time actually covered within the time window t, and A total is the total area or time;
Calculating a coverage fluctuation index based on the coverage rate in each time window, wherein the coverage fluctuation index reflects the change condition of the coverage rate between different time windows;
Wherein, the calculation formula of the coverage fluctuation index is as follows:
Where V is the coverage fluctuation index, N is the number of time windows, R N is the coverage of the N time window, and R y is the average of all time window coverage.
Preferably, the comprehensively analyzing the overall fit degree of the multi-source heterogeneous data and the deep learning model and the overall coverage of the multi-source heterogeneous data, and evaluating the accuracy of the multi-source heterogeneous data specifically includes:
normalizing the integral fitness deviation value D z of the multi-source heterogeneous data and the deep learning model and the coverage fluctuation index V, and calculating the accuracy coefficient of the multi-source heterogeneous data through the integral fitness deviation value D z of the multi-source heterogeneous data and the deep learning model after normalization and the coverage fluctuation index V;
the accuracy coefficient calculation formula of the multi-source heterogeneous data is as follows:
Wherein SA is an accuracy coefficient of multi-source heterogeneous data, a 1 and a 2 are preset scale coefficients, and a 1 and a 2 are both larger than 0.
Preferably, the dividing the multi-source heterogeneous data into accurate data and inaccurate data according to the evaluation result specifically includes:
Judging whether the accuracy coefficient SA of the multi-source heterogeneous data is larger than or equal to the accuracy coefficient threshold of the preset multi-source heterogeneous data, if so, recording the multi-source heterogeneous data as accurate data, and if not, recording the multi-source heterogeneous data as inaccurate data.
Preferably, predicting the overall management risk score of the power engineering through the deep learning model based on inaccurate data in the multi-source heterogeneous data specifically includes:
For each inaccurate data L j, calculating its deviation from the model prediction result, quantifying this deviation using a loss function S, where j represents the number of inaccurate data and j is a positive integer greater than 0;
Wherein the loss function expression is:
ej＝S(Lj,Lyj);
Where L j represents an actual observed value, ly j represents a predicted value of the deep learning model, and e j represents a predicted deviation;
summarizing the prediction deviations of all inaccurate data, and calculating an overall prediction risk score;
the total risk calculation formula is as follows:
where w j is the weight factor for each inaccurate data, e j is the predicted bias value for the j-th inaccurate data, and R is the overall predicted risk score.
Further, an intelligent management and control system for electric power engineering based on big data is provided, which is used for implementing the intelligent management and control method for electric power engineering based on big data, and specifically includes:
The multi-source heterogeneous data acquisition module is used for acquiring multi-source heterogeneous data in the management and control area;
The multi-source heterogeneous data comparison module is used for comparing each multi-source heterogeneous data with historical multi-source heterogeneous data and dividing the multi-source heterogeneous data into suspicious data and non-suspicious data according to a comparison result;
The fitness analysis module is used for carrying out fitness analysis on each multi-source heterogeneous data based on non-suspicious data and evaluating the overall fitness of the multi-source heterogeneous data and the deep learning model;
The coverage analysis module is used for analyzing the coverage degree of each multi-source heterogeneous data based on the non-suspicious data and evaluating the overall coverage of the multi-source heterogeneous data;
the accuracy dividing module divides the multi-source heterogeneous data into accurate data and inaccurate data according to the evaluation result, and integrates the accurate data into a deep learning model;
And the risk prediction module predicts the overall management risk score of the power engineering through a deep learning model based on inaccurate data in the multi-source heterogeneous data.
Compared with the prior art, the invention has the beneficial effects that:
(1) The method comprises the steps of carrying out strict comparison on real-time multi-source heterogeneous data and historical data, calculating the difference degree between new data and the historical data by using Euclidean distance, comparing the difference degree with a preset difference degree threshold value, dividing the data into suspicious data and non-suspicious data, effectively screening out data which are possibly distorted, avoiding the data from directly entering a model training link, reducing model prediction deviation caused by data distortion, and further evaluating the overall fit degree of the non-suspicious data with a deep learning model through a fit degree analysis module, further verifying the authenticity and reliability of the data through a Bayesian network model, and evaluating the coverage rate of the data in different time windows through calculating a coverage fluctuation index by a coverage analysis module so as to ensure the continuity and the integrity of the data in time and space. The steps work together to obviously improve the quality of data, thereby guaranteeing the prediction accuracy and stability of the deep learning model, enabling engineering management and control operators to rely on more reliable prediction results when making decisions, and reducing decision errors caused by data distortion. By the technical scheme, distorted data can be found and removed in time, the coverage and consistency of the data can be ensured through comprehensive analysis, and adverse effects of data distortion on power engineering management and control are fundamentally solved;
(2) According to the method, the accuracy coefficient of the multi-source heterogeneous data is calculated and compared with the preset accuracy coefficient threshold value, so that the fact that only high-accuracy data can be integrated into the deep learning model is further ensured. The mechanism not only improves the prediction performance of the model, but also enhances the robustness of the system; the method and the system can be used for judging inaccurate data, calculating deviation between the inaccurate data and a model prediction result and summarizing to obtain an overall prediction risk score, so that the influence degree of the inaccurate data on the model prediction is evaluated, when the overall prediction risk score exceeds a preset threshold, a decision maker is prompted to pay attention to potential risks and recommends taking corresponding remedial measures, the system can find and deal with the problem of data distortion at the first time, decision deviation caused by the problem of data quality is avoided, accuracy and reliability of the data in the whole engineering management and control system are guaranteed through comprehensive evaluation of the fit degree and the coverage of the data, speed and effect of emergency response are improved, in addition, model parameters can be timely adjusted through dynamic monitoring of the accuracy and the stability of the data, the data processing flow is optimized, and accordingly overall performance of the system is continuously improved.
Drawings
FIG. 1 is a flow chart of an intelligent control method of electric power engineering based on big data;
FIG. 2 is a flow chart of a method for computing differences between feature vectors in the present invention;
FIG. 3 is a flow chart of a method for evaluating the overall fitness of multi-source heterogeneous data and a deep learning model according to the present invention;
FIG. 4 is a flow chart of a method for computing risk of engineering management by a deep learning model according to the present invention.
Detailed Description
The following description is presented to enable one of ordinary skill in the art to make and use the invention. The preferred embodiments in the following description are by way of example only and other obvious variations will occur to those skilled in the art.
Example 1
Referring to fig. 1, the invention discloses an intelligent management and control method for electric power engineering based on big data, which comprises the following steps:
the multi-source heterogeneous data in the monitoring area are collected, each multi-source heterogeneous data is compared with the historical multi-source heterogeneous data, and the multi-source heterogeneous data are divided into suspicious data and non-suspicious data according to the comparison result;
when the multi-source heterogeneous data are non-suspicious data, carrying out fit degree analysis on each multi-source heterogeneous data, and evaluating the integral fit degree of the multi-source heterogeneous data and the deep learning model;
when the multi-source heterogeneous data are non-suspicious data, performing coverage degree analysis on each multi-source heterogeneous data, and evaluating the overall coverage of the multi-source heterogeneous data;
comprehensively analyzing the overall fit degree of the multi-source heterogeneous data and the deep learning model and the overall coverage of the multi-source heterogeneous data, and evaluating the accuracy of the multi-source heterogeneous data;
dividing the multi-source heterogeneous data into accurate data and inaccurate data according to the evaluation result, and integrating the accurate data into a deep learning model;
based on inaccurate data in the multi-source heterogeneous data, predicting an overall management and control risk score of the power engineering through a deep learning model.
Example 2
On the basis of the embodiment 1, various types of multi-source heterogeneous data are collected from the monitoring area;
representing the characteristics of data among different independent sources as vectors, carrying out standardization processing on each characteristic rule, and setting a vector score of each rule, wherein each characteristic rule is respectively provided with a corresponding score;
Comparing the data feature vectors among different independent sources with the feature vectors of the corresponding historical data as a group of data;
specifically, please refer to fig. 2:
Representing the new data collected at each point in time as a feature vector x n, where n is the number of features and x n represents the feature vector of the multi-source heterogeneous data currently collected;
The historical data corresponding to x n is expressed as a characteristic vector y n,yn which represents the characteristic vector of the multi-source heterogeneous data collected in a historical manner;
calculating the difference between the feature vectors by using a Euclidean distance calculation formula;
wherein, the Euclidean distance formula of calculating is:
Wherein d (x, y) is the difference degree value of the historical data and the current data;
comparing the difference degree value between the data characteristic vector between different independent sources and the characteristic vector of the corresponding historical data with a difference degree threshold value;
If the difference degree value between the data feature vectors of the independent sources and the feature vectors of the corresponding historical data is larger than or equal to the difference degree threshold value, the multi-source heterogeneous data is marked as suspicious data;
If the difference degree value between the data feature vectors of the independent sources and the feature vectors of the corresponding historical data is smaller than the difference degree threshold value, marking the multi-source heterogeneous data as non-suspicious data;
it should be noted that the larger the difference degree value between the data feature vector between different independent sources and the feature vector of the corresponding historical data, the larger the difference between the data and the historical data between different independent sources, and the higher the data suspicious degree.
Example 3
Referring to fig. 3, on the basis of embodiment 2, when the multi-source heterogeneous data is non-suspicious data, performing a fitness analysis on each multi-source heterogeneous data, and evaluating the overall fitness of the multi-source heterogeneous data and the deep learning model specifically includes:
Selecting characteristics capable of reflecting the relation between the data and the deep learning model from the multi-source heterogeneous data as nodes of the Bayesian network model;
For each node Ys, calculating the conditional probability thereof by a conditional probability calculation formula;
the conditional probability calculation formula is as follows:
Where P (Yp, xp) is the joint probability distribution of node Yp and all its parent nodes Xp, P (Xp) is the edge probability distribution of parent nodes Xp, and P (ys|xs) is the conditional probability of each node Ys;
calculating probability distribution for a target variable Xs under the overall target of the deep learning model;
Wherein, the probability distribution calculation formula is:
Wherein P (Xs-Ys) is probability distribution of a target variable Xs under the whole target of the deep learning model;
calculating the overall fitness deviation value of the multi-source heterogeneous data and the deep learning model through the calculated conditional probability P (ys|xs) and the probability distribution P (xs|ys) of the target variable;
the specific calculation formula is as follows:
wherein q is the number of data samples, and D z is the fitness deviation value between the multi-source heterogeneous data and the deep learning model;
The method is characterized in that if the degree of fit deviation between the multi-source heterogeneous data and the deep learning model is smaller, the degree of fit between the multi-source heterogeneous data and the deep learning model is higher, and if the degree of fit deviation between the multi-source heterogeneous data and the deep learning model is larger, the degree of fit between the multi-source heterogeneous data and the deep learning model is lower.
When the multi-source heterogeneous data are non-suspicious data, performing coverage degree analysis on each multi-source heterogeneous data to obtain coverage fluctuation indexes in the non-suspicious data updating process, and evaluating the overall coverage of the multi-source heterogeneous data, wherein the coverage fluctuation indexes in the non-suspicious data updating process are obtained by the following steps:
Dividing the collected time series data into a series of fixed length time windows, dividing the data of one day into 24 hour time windows, each window representing one hour of data;
calculating the coverage rate of the data sources in each time window, wherein the coverage rate is defined as the actual coverage area or time proportion of the data sources in the time window;
the coverage rate of the data source is calculated by the following formula:
Wherein R (t) represents coverage within the time window t, A (t) is the area or time actually covered within the time window t, and A total is the total area or time;
Calculating a coverage fluctuation index based on the coverage rate in each time window, wherein the coverage fluctuation index reflects the change condition of the coverage rate between different time windows;
wherein, the calculation formula of the coverage fluctuation index is:
Where V is the cover fluctuation index, N is the number of time windows, n=1, 2. R N is the coverage of the N time window, and R y is the average of all time window coverage;
It should be noted that the lower the coverage fluctuation index is, the more stable the data coverage is, and the higher the coverage fluctuation index is, the larger the fluctuation exists in the data coverage, and the fluctuation index can help us evaluate the overall coverage and stability of the data, so as to better support the operation of the power engineering management and control system.
Comprehensively analyzing the overall fit degree of the multi-source heterogeneous data and the deep learning model and the overall coverage of the multi-source heterogeneous data, calculating a data accuracy coefficient, and evaluating the accuracy of the multi-source heterogeneous data;
the data accuracy coefficient acquisition process comprises the following steps:
normalizing the integral fitness deviation value D z of the multi-source heterogeneous data and the deep learning model and the coverage fluctuation index V, and calculating the accuracy coefficient of the multi-source heterogeneous data through the integral fitness deviation value D z of the multi-source heterogeneous data and the deep learning model after normalization and the coverage fluctuation index V;
the calculation formula of the accuracy coefficient of the multi-source heterogeneous data is as follows:
Wherein SA is an accuracy coefficient of multi-source heterogeneous data, a 1 and a 2 are preset proportional coefficients, and a 1 and a 2 are both larger than 0;
It should be noted that, the overall fitness deviation value D z of the multi-source heterogeneous data and the deep learning model is in a direct proportion relationship with the coverage fluctuation index V and the accuracy coefficient SA of the multi-source heterogeneous data, and when the overall fitness deviation value D z of the multi-source heterogeneous data and the deep learning model is larger, the accuracy coefficient SA of the multi-source heterogeneous data is larger and the accuracy of the data is higher.
Example 5
Based on embodiment 4, comparing the accuracy coefficient SA of the multi-source heterogeneous data with a preset accuracy coefficient threshold of the multi-source heterogeneous data;
if the accuracy coefficient SA of the multi-source heterogeneous data is larger than or equal to the accuracy coefficient threshold of the preset multi-source heterogeneous data, the multi-source heterogeneous data is accurate and recorded as accurate data;
If the accuracy coefficient SA of the multi-source heterogeneous data is smaller than the accuracy coefficient threshold of the preset multi-source heterogeneous data, the multi-source heterogeneous data is inaccurate, and the inaccurate data is marked;
and integrating accurate data of the multi-source heterogeneous data into a deep learning model so as to facilitate the subsequent prediction of engineering management and control.
Referring to fig. 4, based on inaccurate data of multi-source heterogeneous data, a risk of engineering management and control is calculated by a deep learning model, and a specific calculation process is as follows:
For each inaccurate data L j, the deviation from the model predictions is calculated. Quantifying this deviation using a loss function S, where j represents the amount of inaccurate data and j is a positive integer greater than 0;
wherein, the loss function expression is:
ej＝S(Lj,Lyj);
Where L j represents an actual observed value, ly j represents a predicted value of the deep learning model, and e j represents a predicted deviation;
summarizing the prediction deviations of all inaccurate data, and calculating an overall prediction risk score;
The overall risk calculation formula is:
Where w j is the weight factor for each inaccurate data, e j is the predicted bias value for the j-th inaccurate data, and R is the overall predicted risk score;
comparing the overall prediction risk score R with a preset threshold value;
If the overall prediction risk score R is larger than or equal to a preset threshold value, the fact that inaccurate data has high risk for overall prediction of deep learning, and the overall prediction of the deep learning is unstable is indicated;
If the overall prediction risk score R is smaller than a preset threshold value, the fact that inaccurate data has low risk for deep learning overall prediction does not lead to unstable deep learning overall prediction.
It should be noted that the deep learning model is further optimized or corresponding remedial measures are taken by calculating the risk brought by inaccurate data.
Example 6
An intelligent management and control system for electric power engineering based on big data, comprising:
the multi-source heterogeneous data acquisition module is used for acquiring multi-source heterogeneous data in the monitoring area;
The multi-source heterogeneous data comparison module is used for comparing each multi-source heterogeneous data with the historical multi-source heterogeneous data and dividing the multi-source heterogeneous data into suspicious data and non-suspicious data according to the comparison result;
The fitness analysis module is used for carrying out fitness analysis on each multi-source heterogeneous data based on the non-suspicious data and evaluating the overall fitness of the multi-source heterogeneous data and the deep learning model;
The coverage analysis module is used for carrying out coverage degree analysis on each multi-source heterogeneous data based on the non-suspicious data and evaluating the overall coverage of the multi-source heterogeneous data;
The accuracy dividing module divides the multi-source heterogeneous data into accurate data and inaccurate data according to the evaluation result, and integrates the accurate data into a deep learning model;
and the risk prediction module is used for calculating the risk of engineering management and control by the deep learning model based on inaccurate data in the multi-source heterogeneous data.
The technical scheme comprises a multi-source heterogeneous data acquisition module, a multi-source heterogeneous data comparison module, a fit analysis module, a coverage analysis module, an accuracy prediction module and a risk prediction module, wherein the multi-source heterogeneous data acquisition module is used for acquiring multi-source heterogeneous data from a monitoring area, the multi-source heterogeneous data comparison module is used for judging the suspicious degree of data by calculating the Euclidean distance between new data and historical data and dividing the data into suspicious data and non-suspicious data, the fit analysis module is used for carrying out fit analysis on the non-suspicious data, evaluating the integral fit of the non-suspicious data with a deep learning model and calculating conditional probability through a Bayesian network model, the coverage analysis module is used for evaluating the coverage rate of the non-suspicious data in different time windows and calculating a coverage fluctuation index, the accuracy division module is used for integrating fit deviation values and coverage fluctuation indexes to calculate the accuracy coefficient of the data and dividing the data into accurate data and inaccurate data according to a preset threshold, and the risk prediction module is used for calculating the risk of project management by summarizing the depth learning model and predicting the overall risk prediction deviation and calculating the overall risk prediction score to evaluate the stability prediction model. According to the technical scheme, through the multi-step data processing and evaluation flow of the system, the data quality of the power engineering management and control system is effectively improved, and the accuracy and stability of prediction are enhanced, so that the power engineering management and control and decision making are better supported.
The above formulas are all formulas with dimensions removed and numerical values calculated, the formulas are formulas with a large amount of data collected for software simulation to obtain the latest real situation, and preset parameters in the formulas are set by those skilled in the art according to the actual situation.
The above embodiments may be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions described in accordance with embodiments of the present application are produced in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center by wired or wireless means (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains one or more sets of available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium may be a solid state disk.
It should be understood that the term "and/or" is merely an association relationship describing the associated object, and means that three relationships may exist, for example, a and/or B, and may mean that a exists alone, while a and B exist alone, and B exists alone, wherein a and B may be singular or plural. In addition, the character "/" herein generally indicates that the associated object is an "or" relationship, but may also indicate an "and/or" relationship, and may be understood by referring to the context.
It should be understood that, in various embodiments of the present application, the sequence numbers of the foregoing processes do not mean the order of execution, and the order of execution of the processes should be determined by the functions and internal logic thereof, and should not constitute any limitation on the implementation process of the embodiments of the present application.
The foregoing describes one embodiment of the present invention in detail, but the description is only a preferred embodiment of the present invention and should not be construed as limiting the scope of the invention. All equivalent changes and modifications within the scope of the present invention are intended to be covered by the present invention.

Claims (9)

1.一种基于大数据的电力工程智能管控方法，其特征在于，包括：1. A method for intelligent management and control of electric power engineering based on big data, characterized by comprising: 采集管控区域内的多源异构数据，并将每个多源异构数据与历史多源异构数据进行比较，根据比较结果将多源异构数据分为可疑数据和非可疑数据；Collect multi-source heterogeneous data within the control area, compare each multi-source heterogeneous data with historical multi-source heterogeneous data, and classify the multi-source heterogeneous data into suspicious data and non-suspicious data based on the comparison results; 当多源异构数据为非可疑数据时，对每个多源异构数据进行契合度分析，评估多源异构数据与深度学习模型的整体契合度；When the multi-source heterogeneous data is non-suspicious data, a fit analysis is performed on each multi-source heterogeneous data to evaluate the overall fit between the multi-source heterogeneous data and the deep learning model; 当多源异构数据为非可疑数据时，对每个多源异构数据进行覆盖程度分析，评估多源异构数据整体的覆盖性；When the multi-source heterogeneous data is non-suspicious data, the coverage degree analysis is performed on each multi-source heterogeneous data to evaluate the overall coverage of the multi-source heterogeneous data; 将多源异构数据与深度学习模型的整体契合度与多源异构数据整体的覆盖性进行综合分析，评估多源异构数据的准确性；Comprehensively analyze the overall fit between multi-source heterogeneous data and deep learning models and the overall coverage of multi-source heterogeneous data to evaluate the accuracy of multi-source heterogeneous data; 根据评估结果，将多源异构数据分为准确数据和不准确数据，将准确数据整合到深度学习模型中；Based on the evaluation results, the multi-source heterogeneous data are divided into accurate data and inaccurate data, and the accurate data are integrated into the deep learning model; 基于多源异构数据中的不准确数据，通过深度学习模型预测电力工程的总体管控风险分数。Based on the inaccurate data in multi-source heterogeneous data, the overall management and control risk score of the power project is predicted through a deep learning model. 2.根据权利要求1所述的一种基于大数据的电力工程智能管控方法，其特征在于，所述将每个多源异构数据与历史多源异构数据进行比较具体包括：2. According to the method of intelligent management and control of electric power engineering based on big data in claim 1, it is characterized in that the step of comparing each multi-source heterogeneous data with the historical multi-source heterogeneous data specifically comprises: 将不同独立来源之间的数据特征向量与对应的历史数据的特征向量视为一组数据进行比较；The data feature vectors between different independent sources and the feature vectors of corresponding historical data are regarded as a set of data for comparison; 将每个时间点收集到的新数据表示成特征向量xn，其中n是特征的数量，xn表示当前收集到的多源异构数据的特征向量；The new data collected at each time point is represented as a feature vector x n , where n is the number of features and x n represents the feature vector of the currently collected multi-source heterogeneous data; 其中，xn对应的历史数据表示成特征向量yn，yn表示历史收集到的多源异构数据的特征向量；Among them, the historical data corresponding to xn is expressed as a feature vector yn , and yn represents the feature vector of multi-source heterogeneous data collected historically; 使用欧式距离计算公式，计算特征向量之间差异；Use the Euclidean distance calculation formula to calculate the difference between feature vectors; 其中，所述欧式距离计算公式为：The Euclidean distance calculation formula is: 其中，d(x，y)为历史数据和当前数据的差异程度值。Among them, d(x, y) is the difference between historical data and current data. 3.根据权利要求2所述的一种基于大数据的电力工程智能管控方法，其特征在于，所述根据比较结果将多源异构数据分为可疑数据和非可疑数据具体为：3. According to the method of intelligent management and control of electric power engineering based on big data in claim 2, it is characterized in that the step of dividing the multi-source heterogeneous data into suspicious data and non-suspicious data according to the comparison result is as follows: 判断独立来源之间的数据特征向量与对应的历史数据的特征向量之间的差异程度值是否大于等于差异度阈值，若是，则记为可疑数据，若否，则记为非可疑数据。It is determined whether the difference between the data feature vectors of the independent sources and the feature vectors of the corresponding historical data is greater than or equal to the difference threshold. If so, it is recorded as suspicious data; if not, it is recorded as non-suspicious data. 4.根据权利要求3所述的一种基于大数据的电力工程智能管控方法，其特征在于，所述当多源异构数据为非可疑数据时，对每个多源异构数据进行契合度分析，评估多源异构数据与深度学习模型的整体契合度具体包括：4. According to the method of intelligent control of electric power engineering based on big data in claim 3, it is characterized in that when the multi-source heterogeneous data is non-suspicious data, the fit analysis is performed on each multi-source heterogeneous data, and the overall fit evaluation of the multi-source heterogeneous data and the deep learning model specifically includes: 从多源异构数据中选择能够反映数据与深度学习模型之间关系的特征，作为贝叶斯网络模型的节点；Select features that can reflect the relationship between data and deep learning models from multi-source heterogeneous data as nodes of the Bayesian network model; 对于每个节点Ys，通过条件概率计算公式计算其条件概率；For each node Ys, calculate its conditional probability using the conditional probability calculation formula; 其中，所述条件概率计算公式为： Wherein, the conditional probability calculation formula is: 式中，P(Yp，Xp)是节点Yp和其所有父节点Xp的联合概率分布，P(Xp)是父节点Xp的边缘概率分布，P(Ys∣Xs)为每个节点Ys的条件概率；Where P(Yp, Xp) is the joint probability distribution of node Yp and all its parent nodes Xp, P(Xp) is the marginal probability distribution of parent node Xp, and P(Ys|Xs) is the conditional probability of each node Ys; 对于深度学习模型整体目标下的目标变量Xs，计算概率分布；For the target variable Xs under the overall goal of the deep learning model, calculate the probability distribution; 其中，概率分布计算公式为： The probability distribution calculation formula is: 式中，P(Xs∣Ys)为深度学习模型整体目标下目标变量Xs的概率分布；Where P(Xs|Ys) is the probability distribution of the target variable Xs under the overall goal of the deep learning model; 通过计算得到的条件概率P(Ys∣Xs)和目标变量的概率分布P(Xs∣Ys)，计算多源异构数据与深度学习模型整体契合度偏差值；By calculating the conditional probability P(Ys|Xs) and the probability distribution P(Xs|Ys) of the target variable, the deviation value of the overall fit between multi-source heterogeneous data and the deep learning model is calculated; 其中，契合度偏差值计算公式为：The calculation formula of the fit deviation value is: 其中，q是数据样本的数量，Dz为多源异构数据与深度学习模型之间的契合度偏差值。Among them, q is the number of data samples, and Dz is the deviation value of the fit between multi-source heterogeneous data and the deep learning model. 5.根据权利要求4所述的一种基于大数据的电力工程智能管控方法，其特征在于，所述当多源异构数据为非可疑数据时，对每个多源异构数据进行覆盖程度分析，评估多源异构数据整体的覆盖性具体包括：5. According to the method of intelligent control of electric power engineering based on big data in claim 4, it is characterized in that when the multi-source heterogeneous data is non-suspicious data, the coverage degree analysis is performed on each multi-source heterogeneous data, and the evaluation of the overall coverage of the multi-source heterogeneous data specifically includes: 将收集到的时间序列数据分成一系列固定长度的时间窗口，每个窗口代表一个小时的数据；Divide the collected time series data into a series of fixed-length time windows, each of which represents one hour of data; 在每个时间窗口内计算数据源的覆盖率，覆盖率定义为在该时间窗口内数据源实际覆盖的区域或时间比例；The coverage rate of the data source is calculated in each time window. The coverage rate is defined as the area or time proportion actually covered by the data source in the time window. 所述数据源的覆盖率的计算公式为：The calculation formula for the coverage of the data source is: 式中，R(t)表示时间窗口t内的覆盖率，A(t)是时间窗口t内实际覆盖的区域或时间，Atotal是总的区域或时间；Where R(t) represents the coverage rate in time window t, A(t) is the area or time actually covered in time window t, and A total is the total area or time; 基于每个时间窗口内的覆盖率，计算覆盖波动指数，覆盖波动指数反映了覆盖率在不同时间窗口之间的变化情况；Based on the coverage rate in each time window, the coverage fluctuation index is calculated. The coverage fluctuation index reflects the changes in coverage rate between different time windows. 其中，所述覆盖波动指数的计算公式为：The calculation formula of the coverage volatility index is: 式中，V是覆盖波动指数，N是时间窗口的数量，RN是第N个时间窗口的覆盖率，Ry是所有时间窗口覆盖率的平均值。Where V is the coverage fluctuation index, N is the number of time windows, RN is the coverage rate of the Nth time window, and Ry is the average coverage rate of all time windows. 6.根据权利要求5所述的一种基于大数据的电力工程智能管控方法，其特征在于，所述将多源异构数据与深度学习模型的整体契合度与多源异构数据整体的覆盖性进行综合分析，评估多源异构数据的准确性具体包括：6. According to the method of intelligent control of electric power engineering based on big data in claim 5, it is characterized in that the overall fit between multi-source heterogeneous data and deep learning model and the overall coverage of multi-source heterogeneous data are comprehensively analyzed to evaluate the accuracy of multi-source heterogeneous data, which specifically includes: 将多源异构数据与深度学习模型的整体契合度偏差值Dz与覆盖波动指数V进行归一化处理，通过归一化处理后的多源异构数据与深度学习模型的整体契合度偏差值Dz与覆盖波动指数V计算多源异构数据的准确性系数；The overall fit deviation value Dz and the coverage fluctuation index V of the multi-source heterogeneous data and the deep learning model are normalized, and the accuracy coefficient of the multi-source heterogeneous data is calculated by the overall fit deviation value Dz and the coverage fluctuation index V of the multi-source heterogeneous data and the deep learning model after normalization; 所述，多源异构数据的准确性系数计算公式为：The accuracy coefficient calculation formula for multi-source heterogeneous data is as follows: 其中，SA为多源异构数据的准确性系数，a1和a2为预设比例系数，且a1和a2均大于0。Wherein, SA is the accuracy coefficient of multi-source heterogeneous data, a1 and a2 are preset proportional coefficients, and a1 and a2 are both greater than 0. 7.根据权利要求6所述的一种基于大数据的电力工程智能管控方法，其特征在于，所述根据评估结果，将多源异构数据分为准确数据和不准确数据具体包括：7. The method for intelligent management and control of electric power engineering based on big data according to claim 6 is characterized in that the step of dividing the multi-source heterogeneous data into accurate data and inaccurate data according to the evaluation results specifically comprises: 判断若多源异构数据的准确性系数SA是否大于等于预设多源异构数据的准确性系数阈值，若是，记为准确数据，若否，记为不准确数据。It is determined whether the accuracy coefficient SA of the multi-source heterogeneous data is greater than or equal to a preset accuracy coefficient threshold of the multi-source heterogeneous data. If so, it is recorded as accurate data; if not, it is recorded as inaccurate data. 8.根据权利要求7所述的一种基于大数据的电力工程智能管控方法，其特征在于，所述基于多源异构数据中的不准确数据，通过深度学习模型预测电力工程的总体管控风险分数具体包括：8. According to the method of intelligent control of electric power engineering based on big data in claim 7, it is characterized in that the prediction of the overall control risk score of the electric power engineering through the deep learning model based on the inaccurate data in the multi-source heterogeneous data specifically includes: 对于每一个不准确数据Lj，计算其与模型预测结果之间的偏差，使用损失函数S来量化这种偏差，其中，j表示不准确数据的数量，j为大于0的正整数；For each inaccurate data L j , calculate the deviation between it and the model prediction result, and use the loss function S to quantify this deviation, where j represents the number of inaccurate data and j is a positive integer greater than 0; 其中，所述损失函数表达式为：Wherein, the loss function expression is: ej＝S(Lj,Lyj)；e j =S(L j ,Ly j ); 式中，Lj表示是实际的观测值，Lyj表示深度学习模型的预测值，ej是预测偏差；In the formula, Lj represents the actual observed value, Lyj represents the predicted value of the deep learning model, and ej is the prediction deviation; 将所有不准确数据的预测偏差汇总起来，计算总体预测风险分数；The prediction deviations of all inaccurate data are summed up to calculate the overall prediction risk score; 所述总体风险计算公式为：The overall risk calculation formula is: 式中，wj是每个不准确数据的权重因子，ej是第j个不准确数据的预测偏差值，R是总体预测风险分数。Where wj is the weight factor of each inaccurate data, ej is the prediction deviation value of the jth inaccurate data, and R is the overall prediction risk score. 9.一种基于大数据的电力工程智能管控系统，其特征在于，用于实现如权利要求1-8任一项所述的基于大数据的电力工程智能管控方法，具体包括：9. An intelligent management and control system for electric power engineering based on big data, characterized in that it is used to implement the intelligent management and control method for electric power engineering based on big data as described in any one of claims 1 to 8, specifically comprising: 多源异构数据采集模块，所述多源异构数据采集模块用于采集管控区域内的多源异构数据；A multi-source heterogeneous data acquisition module, which is used to collect multi-source heterogeneous data in the control area; 多源异构数据比较模块，所述多源异构数据比较模块用于将每个多源异构数据与历史多源异构数据进行比较，根据比较结果将多源异构数据分为可疑数据和非可疑数据；A multi-source heterogeneous data comparison module, which is used to compare each multi-source heterogeneous data with the historical multi-source heterogeneous data, and classify the multi-source heterogeneous data into suspicious data and non-suspicious data according to the comparison result; 契合度分析模块，所述契合度分析模块基于非可疑数据，对每个多源异构数据进行契合度分析，评估多源异构数据与深度学习模型的整体契合度；A fit analysis module, which performs fit analysis on each multi-source heterogeneous data based on non-suspicious data to evaluate the overall fit between the multi-source heterogeneous data and the deep learning model; 覆盖性分析模块，所述覆盖性分析模块基于非可疑数据，对每个多源异构数据进行覆盖程度分析，评估多源异构数据整体的覆盖性；A coverage analysis module, which performs coverage analysis on each multi-source heterogeneous data based on non-suspicious data to evaluate the overall coverage of the multi-source heterogeneous data; 准确性划分模块，所述准确性划分模块根据评估结果，将多源异构数据分为准确数据和不准确数据，将准确数据整合到深度学习模型中；An accuracy division module, which divides the multi-source heterogeneous data into accurate data and inaccurate data according to the evaluation results, and integrates the accurate data into the deep learning model; 风险预测模块，所述风险预测模块基于多源异构数据中的不准确数据，通过深度学习模型预测电力工程的总体管控风险分数。A risk prediction module predicts the overall management and control risk score of the power project through a deep learning model based on inaccurate data in multi-source heterogeneous data.
CN202510067978.8A 2025-01-16 2025-01-16 Intelligent power engineering management and control system and method based on big data Pending CN119886567A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202510067978.8A CN119886567A (en) 2025-01-16 2025-01-16 Intelligent power engineering management and control system and method based on big data

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202510067978.8A CN119886567A (en) 2025-01-16 2025-01-16 Intelligent power engineering management and control system and method based on big data

Publications (1)

Publication Number Publication Date
CN119886567A true CN119886567A (en) 2025-04-25

Family

ID=95442573

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202510067978.8A Pending CN119886567A (en) 2025-01-16 2025-01-16 Intelligent power engineering management and control system and method based on big data

Country Status (1)

Country Link
CN (1) CN119886567A (en)

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100070455A1 (en) * 2008-09-12 2010-03-18 Navigenics, Inc. Methods and Systems for Incorporating Multiple Environmental and Genetic Risk Factors
CN111163057A (en) * 2019-12-09 2020-05-15 中国科学院信息工程研究所 A user identification system and method based on heterogeneous information network embedding algorithm
CN115470843A (en) * 2022-08-30 2022-12-13 广东电网有限责任公司广州供电局 A Method of Power Data Fusion Based on String Matching
CN116341902A (en) * 2023-03-08 2023-06-27 浙江大学 A BERT-based method and device for automatic risk rating of power grid field operations
CN117473571A (en) * 2023-11-10 2024-01-30 青岛中企英才集团商业管理有限公司 Data information security processing method and system
CN117688464A (en) * 2024-02-04 2024-03-12 国网上海市电力公司 A hidden danger analysis method and system based on multi-source sensor data
CN118469520A (en) * 2024-07-09 2024-08-09 昆明海巍科技有限公司 Multi-target management architecture implementation method based on project sub-term tree structure
CN118504939A (en) * 2024-07-17 2024-08-16 国网浙江省电力有限公司杭州供电公司 Power grid fault electricity protection maintenance plan making method, device, equipment and medium
CN118941075A (en) * 2024-07-17 2024-11-12 单静怡 A modular risk prediction method, device and storage medium for power distribution terminal
CN119168364A (en) * 2024-08-28 2024-12-20 国网湖北省电力有限公司宜昌供电公司 Security assessment method for industrial control equipment of power Internet of Things based on multimodal large model

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100070455A1 (en) * 2008-09-12 2010-03-18 Navigenics, Inc. Methods and Systems for Incorporating Multiple Environmental and Genetic Risk Factors
CN111163057A (en) * 2019-12-09 2020-05-15 中国科学院信息工程研究所 A user identification system and method based on heterogeneous information network embedding algorithm
CN115470843A (en) * 2022-08-30 2022-12-13 广东电网有限责任公司广州供电局 A Method of Power Data Fusion Based on String Matching
CN116341902A (en) * 2023-03-08 2023-06-27 浙江大学 A BERT-based method and device for automatic risk rating of power grid field operations
CN117473571A (en) * 2023-11-10 2024-01-30 青岛中企英才集团商业管理有限公司 Data information security processing method and system
CN117688464A (en) * 2024-02-04 2024-03-12 国网上海市电力公司 A hidden danger analysis method and system based on multi-source sensor data
CN118469520A (en) * 2024-07-09 2024-08-09 昆明海巍科技有限公司 Multi-target management architecture implementation method based on project sub-term tree structure
CN118504939A (en) * 2024-07-17 2024-08-16 国网浙江省电力有限公司杭州供电公司 Power grid fault electricity protection maintenance plan making method, device, equipment and medium
CN118941075A (en) * 2024-07-17 2024-11-12 单静怡 A modular risk prediction method, device and storage medium for power distribution terminal
CN119168364A (en) * 2024-08-28 2024-12-20 国网湖北省电力有限公司宜昌供电公司 Security assessment method for industrial control equipment of power Internet of Things based on multimodal large model

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
彭露瑶: "基于数据空间的电网工程造价管控研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》, no. 04, 15 April 2024 (2024-04-15), pages 038 - 89 *
王臻等: "新型电力系统多源异构数据融合技术研究现状及展望", 《中国电力》, vol. 56, no. 04, 7 March 2023 (2023-03-07), pages 1 - 15 *
邓彬: "电网运行风险评估及管控研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》, no. 07, 15 July 2014 (2014-07-15), pages 042 - 546 *

Similar Documents

Publication Publication Date Title
CN117372165A (en) A data supervision method and system based on financial risk control business
CN108241901A (en) A kind of transformer Forewarn evaluation method and device based on prediction data
CN117094184B (en) Modeling method, system and medium of risk prediction model based on intranet platform
CN119419727B (en) Power load prediction and optimization method based on artificial intelligence
CN120257113B (en) An intelligent data management system and method based on multi-source data acquisition
CN118364963A (en) Building material price prediction method based on LSTM neural network
CN119740054A (en) Data processing methods, devices, equipment, media and products
CN118694673A (en) A life cycle risk management method based on neural network algorithm
CN119863286B (en) Manufacturing cost consultation data arrangement analysis system based on cloud platform
CN118469520B (en) Multi-target management architecture implementation method based on project sub-term tree structure
CN120046992A (en) Audit informatization processing method and system for enterprise data assets
CN119884540A (en) Dynamic truck scale metering method with automatic parameter fitting function
CN119886567A (en) Intelligent power engineering management and control system and method based on big data
CN117633652A (en) A method and system for diagnosing abnormal electricity bills based on Bayesian network model
CN120745954B (en) Subway outbound passenger flow prediction method and device for large-scale activities and storage medium
CN120896146B (en) Power load scene generation method and system integrating cross-season data
CN119416989B (en) A method, system, storage medium and program product for predicting operation and maintenance costs
CN119441800B (en) Enterprise management data management method based on big data analysis
CN120373906B (en) Complex system control decision method and system integrating WRT and SPT
CN119204450B (en) A public service data analysis system based on artificial intelligence
CN121525816A (en) A knowledge graph construction method based on semantic networks
CN121279865A (en) Work efficiency analysis method, computer device, and computer-readable storage medium
CN121389824A (en) A method and electronic device for calculating carbon footprint uncertainty
CN118656604A (en) A method for analyzing environmental adaptability of road and bridge steel formwork
CN121306479A (en) A Hospital Deployment and Scheduling Method and System Based on a Large-Scale AI Model for Dynamic Load Prediction

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