Power grid operation optimization method, system and equipment considering multi-dimensional indexes and medium

Abstract

The invention relates to the technical field of power grid operation optimization, in particular to a power grid operation optimization method, system, equipment and medium considering a multi-dimensional index, and the method comprises the steps: collecting the original operation data of a power grid in real time, and carrying out the preprocessing of the original operation data of the power grid, and obtaining the preprocessed operation data of the power grid; constructing a multi-dimensional performance evaluation index system according to characteristics and requirements of power grid operation; according to the multi-dimensional performance evaluation index system, comprehensively evaluating the preprocessed power grid operation data by using a multivariate statistical analysis method to obtain a power grid operation performance evaluation index; and based on the power grid operation performance evaluation index, optimizing and adjusting the power grid operation state by using an optimization algorithm. According to the method, comprehensive and accurate monitoring and optimization of the operation state of the power grid are realized by comprehensively considering the multi-dimensional indexes, the operation stability and efficiency of the power grid are improved, and the safety and reliability of power supply are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid operation optimization, and in particular to a power grid operation optimization method, system, equipment and medium taking into account multi-dimensional indicators. Background Art

[0002] In the power industry, the stability and efficiency of grid operation are the key to ensuring safe and reliable power supply. With the continuous growth of electricity demand and the increasing complexity of the grid structure, higher requirements are placed on the monitoring and optimization of grid operation status. Traditional grid operation management mainly relies on the monitoring of single or limited indicators, such as basic electrical parameters such as voltage, current, and power, but these indicators are difficult to fully and accurately reflect the overall operation status of the grid.

[0003] Existing grid operation monitoring technologies often only focus on a few key electrical parameters, ignoring other multidimensional factors in grid operation, which have a significant impact on the stability and efficiency of grid operation. Existing technologies make it difficult to achieve comprehensive and accurate monitoring of grid operation status. In addition, performance, as one of the important indicators for measuring grid operation status, has not received sufficient attention in existing technologies. Traditional grid operation performance evaluation methods often only focus on the power supply reliability and economy of the grid, while ignoring other important aspects of grid operation, such as safety, stability and environmental protection. The limitations of this performance evaluation method lead to an incomplete evaluation of the grid operation status, making it difficult to accurately reflect the actual operation status of the grid.

[0004] In summary, the existing power grid operation monitoring and optimization technology is difficult to meet the needs of modern power grid operation management. Therefore, there is an urgent need for a power grid operation optimization method that can comprehensively consider multi-dimensional indicators to achieve comprehensive and accurate monitoring and optimization of the power grid operation status, improve the stability and efficiency of power grid operation, and ensure the safety and reliability of power supply. Summary of the invention

[0005] In order to solve the above technical problems, the present invention provides a power grid operation optimization method, system, device and medium taking into account multi-dimensional indicators.

[0006] In a first aspect, the present invention provides a method for optimizing power grid operation by considering multi-dimensional indicators, the method comprising the following steps:

[0007] Collecting original grid operation data in real time, and preprocessing the original grid operation data to obtain preprocessed grid operation data;

[0008] Construct a multi-dimensional performance evaluation indicator system based on the characteristics and needs of power grid operation;

[0009] According to the multi-dimensional performance evaluation index system, a multivariate statistical analysis method is used to comprehensively evaluate the pre-processed power grid operation data to obtain a power grid operation performance evaluation index;

[0010] Based on the power grid operation performance evaluation index, an optimization algorithm is used to optimize and adjust the power grid operation status.

[0011] In a further implementation scheme, the step of constructing a multi-dimensional performance evaluation index system according to the characteristics and requirements of power grid operation includes:

[0012] Determine the evaluation dimensions according to the characteristics and requirements of the power grid operation; the evaluation dimensions include electrical performance dimension, safety dimension, stability dimension and economic dimension;

[0013] Determine the multi-dimensional performance evaluation indicators under each evaluation dimension, and use the coefficient of variation method to preliminarily assign weights to each evaluation dimension to obtain the initial dimension weights;

[0014] Taking the evaluation dimension as the target layer and the multi-dimensional performance evaluation index as the criterion layer, the hierarchical analysis method is used to construct a multi-level analysis structure model;

[0015] The multi-level analysis structural model is used to calculate the relative importance of different multi-dimensional performance evaluation indicators under each evaluation dimension and construct a judgment matrix;

[0016] Calculate the indicator weight of each multi-dimensional performance evaluation indicator under its corresponding evaluation dimension according to the judgment matrix;

[0017] Multiply the indicator weight of each multi-dimensional performance evaluation indicator by the initial dimension weight of the dimension to which it belongs to obtain a comprehensive weight;

[0018] The comprehensive weights of various multi-dimensional performance evaluation indicators are summarized to form a multi-dimensional performance evaluation indicator system.

[0019] In a further embodiment, the step of calculating the indicator weight of each multi-dimensional performance evaluation indicator under the corresponding evaluation dimension according to the judgment matrix includes:

[0020] Calculate the maximum eigenvector of the judgment matrix and obtain the indicator weights of each multi-dimensional performance evaluation indicator under its corresponding evaluation dimension.

[0021] In a further embodiment, the step of determining the multi-dimensional performance evaluation indicators under each evaluation dimension includes:

[0022] Obtain all candidate indicators related to all evaluation dimensions from the historical operation data of the power grid and the real-time operation data of the power grid to form a preliminary candidate indicator set;

[0023] Performing data cleaning on the preliminary candidate indicator set to obtain a target candidate indicator set;

[0024] Traverse each evaluation dimension, use the Pearson correlation coefficient to calculate the correlation between each target candidate indicator and the weighted average of all target candidate indicators under the evaluation dimension to which it belongs, and determine the indicator correlation coefficient of each target candidate indicator;

[0025] According to the indicator correlation coefficient, the target candidate indicators under each evaluation dimension are sorted, and several target candidate indicators with the highest correlation with each evaluation dimension are screened out to form a key indicator set;

[0026] The minimum redundancy maximum correlation algorithm is used to screen out the optimal indicator combination under each evaluation dimension from the key indicator set as the multi-dimensional performance evaluation indicator under each evaluation dimension.

[0027] In a further embodiment, the step of comprehensively evaluating the pre-processed power grid operation data using a multivariate statistical analysis method according to the multi-dimensional performance evaluation index system to obtain a power grid operation performance evaluation index comprises:

[0028] Calculate the covariance matrix of all indicator data in the multi-dimensional performance evaluation indicator system, and solve the eigenvalues ​​of the covariance matrix and their corresponding eigenvectors;

[0029] According to the eigenvalues, the eigenvectors corresponding to the first k largest eigenvalues ​​are selected as principal components using the elbow rule;

[0030] Projecting the pre-processed power grid operation data onto the principal component, calculating the score of the pre-processed power grid operation data on the principal component, and obtaining the principal component score;

[0031] The scores of the principal components are weighted and summed according to their variance contribution rates to obtain the power grid operation performance evaluation index.

[0032] In a further embodiment, the variance contribution of a principal component is equal to the ratio of the eigenvalue of the principal component to the sum of the total eigenvalues.

[0033] In a further embodiment, the step of optimizing and adjusting the grid operation state using an optimization algorithm based on the grid operation performance evaluation index includes:

[0034] Determine the optimization variable according to the power grid operation performance evaluation index, and randomly generate an initial population according to the optimization variable; each individual in the initial population represents the power grid operation state;

[0035] Taking the maximization of the power grid operation performance evaluation index as the optimization goal, the initial population is iteratively optimized using a genetic algorithm;

[0036] In each iteration, the power grid operation performance evaluation index of each individual is calculated to obtain the fitness value;

[0037] According to the fitness value, excellent individuals are selected to perform crossover and mutation operations to generate a new generation of population, and the above iterative process is repeated until the fitness value converges;

[0038] The individual with the highest fitness value is selected from the final population as the optimal solution, and the actual operation state of the power grid is adjusted according to the optimal solution.

[0039] In a second aspect, the present invention provides a power grid operation optimization system considering multi-dimensional indicators, the system comprising:

[0040] The data acquisition module is used to collect the original operation data of the power grid in real time, and pre-process the original operation data of the power grid to obtain pre-processed power grid operation data;

[0041] The indicator construction module is used to build a multi-dimensional performance evaluation indicator system based on the characteristics and requirements of power grid operation;

[0042] A comprehensive evaluation module, used to comprehensively evaluate the pre-processed power grid operation data using a multivariate statistical analysis method according to the multi-dimensional performance evaluation index system to obtain a power grid operation performance evaluation index;

[0043] The operation optimization module is used to optimize and adjust the operation status of the power grid using an optimization algorithm based on the power grid operation performance evaluation index.

[0044] In a third aspect, the present invention further provides a computer device, comprising a processor and a memory, wherein the processor is connected to the memory, the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory so that the computer device performs the steps of implementing the above method.

[0045] In a fourth aspect, the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program implements the steps of the above method when executed by a processor.

[0046] The present invention provides a method, system, device and medium for optimizing the operation of a power grid taking into account multi-dimensional indicators. The method collects the original operation data of the power grid in real time, and pre-processes the original operation data of the power grid to obtain pre-processed power grid operation data; constructs a multi-dimensional performance evaluation index system according to the characteristics and requirements of the power grid operation; uses a multivariate statistical analysis method to comprehensively evaluate the pre-processed power grid operation data according to the multi-dimensional performance evaluation index system to obtain a power grid operation performance evaluation index; and uses an optimization algorithm to optimize and adjust the power grid operation state based on the power grid operation performance evaluation index. Compared with the prior art, the method realizes comprehensive and accurate monitoring and optimization of the power grid operation state by comprehensively considering multi-dimensional indicators, improves the stability and efficiency of the power grid operation, and ensures the safety and reliability of the power supply. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a schematic flow chart of a method for optimizing power grid operation considering multi-dimensional indicators provided by an embodiment of the present invention;

[0048] Figure 2 It is a block diagram of a power grid operation optimization system considering multi-dimensional indicators provided by an embodiment of the present invention;

[0049] Figure 3 It is a schematic diagram of the structure of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0050] The following specifically illustrates the implementation mode of the present invention in conjunction with the accompanying drawings. The embodiments are provided for illustrative purposes only and cannot be understood as limiting the present invention. The accompanying drawings are provided for reference and illustration only and do not constitute a limitation on the scope of patent protection of the present invention, because many changes can be made to the present invention without departing from the spirit and scope of the present invention.

[0051] refer to Figure 1 , the embodiment of the present invention provides a method for optimizing power grid operation considering multi-dimensional indicators, such as Figure 1 As shown, the method comprises the following steps:

[0052] S1. Collecting original grid operation data in real time, and preprocessing the original grid operation data to obtain preprocessed grid operation data.

[0053] This embodiment installs smart meters and sensors at various nodes of the power grid, obtains real-time data such as the power grid operation status, power load, power loss, etc. through the smart meters and sensors, obtains the original power grid operation data, and performs data cleaning on the original power grid operation data. For records with a small number of missing values ​​and little impact on the analysis results, they are deleted from the original power grid operation data, and the missing values ​​are filled by statistical methods such as the mean, median or mode. Finally, the minimum-maximum normalization or decimal calibration method is used to scale the data to a range of a mean of 0 and a standard deviation of 1. Data normalization and standardization can improve the accuracy and comparability of data analysis. This embodiment integrates and preprocesses data from different data sources to obtain more complete and accurate preprocessed power grid operation data, providing an accurate and complete data basis for subsequent power grid operation optimization analysis.

[0054] S2. Construct a multi-dimensional performance evaluation indicator system based on the characteristics and requirements of power grid operation.

[0055] In this embodiment, the steps of constructing a multi-dimensional performance evaluation index system according to the characteristics and requirements of power grid operation include:

[0056] Determine the evaluation dimensions according to the characteristics and requirements of the power grid operation; the evaluation dimensions include electrical performance dimension, safety dimension, stability dimension and economic dimension;

[0057] Determine the multi-dimensional performance evaluation indicators under each evaluation dimension, and use the coefficient of variation method to preliminarily assign weights to each evaluation dimension to obtain the initial dimension weights;

[0058] Taking the evaluation dimension as the target layer and the multi-dimensional performance evaluation index as the criterion layer, the hierarchical analysis method is used to construct a multi-level analysis structure model;

[0059] The multi-level analysis structural model is used to calculate the relative importance of different multi-dimensional performance evaluation indicators under each evaluation dimension and construct a judgment matrix;

[0060] Calculate the indicator weight of each multi-dimensional performance evaluation indicator under its corresponding evaluation dimension according to the judgment matrix;

[0061] Multiply the indicator weight of each multi-dimensional performance evaluation indicator by the initial dimension weight of the dimension to which it belongs to obtain a comprehensive weight;

[0062] The comprehensive weights of various multi-dimensional performance evaluation indicators are summarized to form a multi-dimensional performance evaluation indicator system.

[0063] This embodiment determines the basic characteristics and main requirements of the power grid by analyzing the historical operation data and current operation status of the power grid. The basic characteristics may include voltage level, load characteristics, and failure rate. The main requirements may include improving power supply reliability and reducing losses. According to the analysis results, the electrical performance dimension (such as voltage qualification rate, power factor, etc.), safety dimension (such as accident rate, equipment failure rate, etc.), stability dimension (such as frequency stability, voltage fluctuation, etc.) and economic dimension (such as operating cost, energy efficiency ratio, etc.) are determined as core evaluation dimensions, and historical indicator data under each evaluation dimension are collected to ensure the integrity and representativeness of the data. The historical indicator data under each evaluation dimension are calculated for each evaluation dimension. The coefficient of variation of each evaluation dimension is obtained by the ratio of the standard deviation of the historical indicator data to the average value. The coefficient of variation method is an objective weighting method. It weights each evaluation dimension according to the degree of variation between the historical indicator data and the target value under each evaluation dimension. The larger the coefficient of variation, the greater the fluctuation of the indicator within the evaluation dimension, and the greater the impact on the overall evaluation. This embodiment uses a normalization method to assign a preliminary weight, i.e., an initial dimension weight, to each evaluation dimension according to the size of the coefficient of variation. At the same time, this embodiment determines the multidimensional performance evaluation indicator under each evaluation dimension for each evaluation dimension. In this embodiment, the step of determining the multidimensional performance evaluation indicator under each evaluation dimension includes:

[0064] Obtain all candidate indicators related to all evaluation dimensions from the historical operation data of the power grid and the real-time operation data of the power grid to form a preliminary candidate indicator set;

[0065] Performing data cleaning on the preliminary candidate indicator set to obtain a target candidate indicator set;

[0066] Traverse each evaluation dimension, use the Pearson correlation coefficient to calculate the correlation between each target candidate indicator and the weighted average of all target candidate indicators under the evaluation dimension to which it belongs, and determine the indicator correlation coefficient of each target candidate indicator;

[0067] According to the indicator correlation coefficient, the target candidate indicators under each evaluation dimension are sorted, and several target candidate indicators with the highest correlation with each evaluation dimension are screened out to form a key indicator set;

[0068] The minimum redundancy maximum correlation algorithm is used to screen out the optimal indicator combination under each evaluation dimension from the key indicator set as the multi-dimensional performance evaluation indicator under each evaluation dimension.

[0069] In the process of determining the multi-dimensional performance evaluation indicators under each evaluation dimension, in order to ensure that the selected indicators are both representative and can accurately reflect the operation status of the power grid, this embodiment obtains all candidate indicators related to all evaluation dimensions from the historical operation data of the power grid and the real-time operation data of the power grid based on the operation characteristics and needs of the power grid. For example, the electrical performance dimension may include indicators such as voltage qualification rate, power factor and harmonic distortion rate; the safety dimension may include indicators such as equipment failure rate, accident rate and line tripping rate. All extracted candidate indicators are sorted into a preliminary candidate indicator set, and the data in the preliminary candidate indicator set are checked. For indicators with a large number of missing values, they are deleted or filled by interpolation methods, etc., and outliers in the data are identified and processed, such as by using box plot method, Z score method, etc., to ensure the accuracy and reliability of the data, and the indicator data is standardized to eliminate the impact of dimensional differences on subsequent analysis. After data cleaning, the remaining candidate indicators are sorted into a target candidate indicator set.

[0070] For the target candidate indicator under each evaluation dimension, this embodiment calculates its weighted average value as the benchmark value of the dimension. The weighted average value can be weighted according to the importance of the indicator or the weight in the historical data. For each target candidate indicator, the Pearson correlation coefficient between it and the weighted average value of all target candidate indicators under the evaluation dimension to which it belongs is calculated. The Pearson correlation coefficient is a statistic that measures the degree of linear correlation between two variables, and its value range is between -1 and 1. The calculated Pearson correlation coefficient is used as the indicator correlation coefficient of the target candidate indicator to measure its correlation with the evaluation dimension to which it belongs. According to the size of the indicator correlation coefficient, the target candidate indicators under each evaluation dimension are sorted. According to the sorting results, several target candidate indicators with the highest correlation with each evaluation dimension are selected to form a key indicator set. The number of screening can be determined according to actual needs, with a minimum of The redundant maximum correlation (mRMR) algorithm is a feature selection algorithm that aims to select a feature subset with the greatest correlation with the target variable and the least mutual redundancy from a candidate feature set. This embodiment uses a key indicator set as input and uses the mRMR algorithm for feature selection. The mRMR algorithm first selects the indicator with the greatest correlation with the target variable (i.e., the evaluation dimension), and then gradually adds indicators with the least redundancy with the selected indicators and a greater correlation with the target variable until the stopping condition is met (such as reaching a preset number of indicators or a redundancy threshold). After screening by the mRMR algorithm, the optimal indicator combination under each evaluation dimension is obtained. These indicator combinations are used as multi-dimensional performance evaluation indicators under each evaluation dimension. Through the above steps, this embodiment can systematically determine the multi-dimensional performance evaluation indicators under each evaluation dimension, providing strong support for subsequent power grid operation performance evaluation.

[0071] Then, this embodiment divides the hierarchical structure according to the multidimensional performance evaluation indicators under each evaluation dimension. Specifically, this embodiment uses the evaluation dimension as the target layer and the multidimensional performance evaluation indicator as the criterion layer to form a hierarchical structure, and adopts the analytic hierarchy process (AHP) to construct a multi-level analysis structure model, clarify the logical relationship between the levels, calculate the relative importance between different multidimensional performance evaluation indicators under each evaluation dimension, construct a judgment matrix under each evaluation dimension, and use algorithms such as the power method or the sum-product method to calculate the maximum eigenvector of the judgment matrix, normalize the maximum eigenvector, obtain the indicator weight of each multidimensional performance evaluation indicator under its own evaluation dimension, multiply the indicator weight of each indicator under its own evaluation dimension by the initial dimension weight of the evaluation dimension to obtain the comprehensive weight of the indicator, summarize the comprehensive weights of all multidimensional performance evaluation indicators, and form a complete multidimensional performance evaluation indicator system. Through the above steps, this embodiment can construct a multidimensional performance evaluation indicator system that not only meets the operation characteristics of the power grid, but also meets the management needs of the power grid, and provide strong support for the continuous optimization and efficient operation of the power grid.

[0072] S3. Based on the multi-dimensional performance evaluation index system, a multivariate statistical analysis method is used to comprehensively evaluate the pre-processed power grid operation data to obtain a power grid operation performance evaluation index.

[0073] In this embodiment, the step of comprehensively evaluating the pre-processed power grid operation data using a multivariate statistical analysis method according to the multi-dimensional performance evaluation index system to obtain a power grid operation performance evaluation index includes:

[0074] Calculate the covariance matrix of all indicator data in the multi-dimensional performance evaluation indicator system, and solve the eigenvalues ​​of the covariance matrix and their corresponding eigenvectors;

[0075] According to the eigenvalues, the eigenvectors corresponding to the first k largest eigenvalues ​​are selected as principal components using the elbow rule;

[0076] Projecting the pre-processed power grid operation data onto the principal component, calculating the score of the pre-processed power grid operation data on the principal component, and obtaining the principal component score;

[0077] The main component scores are weighted and summed according to the variance contribution rate of the main component to obtain the power grid operation performance evaluation index; the variance contribution rate of the main component is equal to the ratio of the eigenvalue of the main component to the sum of the total eigenvalues.

[0078] This embodiment calculates the covariance matrix of all indicator data in the multi-dimensional performance evaluation indicator system. The covariance matrix describes the linear correlation between the indicator data. This embodiment uses the eigenvalue decomposition method to solve the eigenvalues ​​of the covariance matrix and their corresponding eigenvectors. The eigenvalues ​​reflect the importance of each principal component, and the eigenvectors indicate the direction of each principal component. For example, assuming that there are 5 power grid operation indicators (such as voltage stability, current load rate, power factor, loss rate, reliability), the preprocessed data matrix is ​​X(n×5), where n is the number of samples. The covariance matrix is ​​calculated, and then its eigenvalues ​​and eigenvectors are solved. The elbow diagram after eigenvalue sorting is drawn according to the size of the eigenvalues. , observe the elbow diagram, select the eigenvalues ​​before the elbow position as the eigenvalues ​​of the principal component, and the eigenvectors corresponding to these eigenvalues ​​are the selected principal component directions. Usually, the eigenvalues ​​before the elbow position change greatly, and the eigenvalues ​​after change less. In this embodiment, the preprocessed power grid operation data is projected onto the selected principal component direction to obtain the principal component score matrix Z (n × k), where each column of Z represents a principal component score, and each row represents the score of a sample on the principal component. Finally, the ratio of the eigenvalue of the principal component to the sum of the total eigenvalues ​​is calculated to obtain the variance contribution rate of each principal component. The principal component scores are weighted and summed according to the variance contribution rate to obtain the power grid operation performance evaluation index of each sample.

[0079] S4. Based on the power grid operation performance evaluation index, an optimization algorithm is used to optimize and adjust the power grid operation status.

[0080] In this embodiment, the step of optimizing and adjusting the power grid operation state by using an optimization algorithm based on the power grid operation performance evaluation index includes:

[0081] Determine the optimization variable according to the power grid operation performance evaluation index, and randomly generate an initial population according to the optimization variable; each individual in the initial population represents the power grid operation state;

[0082] Taking the maximization of the power grid operation performance evaluation index as the optimization goal, the initial population is iteratively optimized using a genetic algorithm;

[0083] In each iteration, the power grid operation performance evaluation index of each individual is calculated to obtain the fitness value;

[0084] According to the fitness value, excellent individuals are selected to perform crossover and mutation operations to generate a new generation of population, and the above iterative process is repeated until the fitness value converges;

[0085] The individual with the highest fitness value is selected from the final population as the optimal solution, and the actual operation state of the power grid is adjusted according to the optimal solution.

[0086] Specifically, the optimization variables are determined according to the power grid operation performance evaluation index. These optimization variables have a direct impact on the power grid operation performance. The optimization variables may include the output power of the generator, the power flow distribution of the transmission line, the input amount of the reactive compensation equipment, etc. According to the determined optimization variables, an initial population including multiple individuals is randomly generated. Each individual represents a power grid operation state. The maximization of the power grid operation performance evaluation index is taken as the optimization goal. The initial population is iteratively optimized using a genetic algorithm. Each iteration finds an individual that is closer to the optimal solution. In this embodiment, excellent individuals are selected according to the fitness value for crossover and mutation operations to generate For the new generation population, in each iteration, for each individual in the population, it is necessary to calculate its corresponding power grid operation performance evaluation index, that is, the fitness value. According to the fitness value, a certain number of excellent individuals are selected as parents, the parent individuals are paired, and some genes are exchanged to generate offspring individuals. The offspring individuals are randomly mutated to introduce new genetic information. The offspring individuals generated by crossover and mutation operations form a new generation population. Repeat the above steps until the fitness value converges, and select the individual with the highest fitness value from the final population as the optimal solution. The variable values ​​of the optimal solution are applied to the power grid to adjust the actual operation status of the power grid.

[0087] The embodiment of the present invention provides a method for optimizing the operation of a power grid taking into account multi-dimensional indicators. The method collects the original operation data of the power grid in real time, and pre-processes the original operation data of the power grid to obtain pre-processed power grid operation data; constructs a multi-dimensional performance evaluation index system according to the characteristics and requirements of the power grid operation; uses a multivariate statistical analysis method to comprehensively evaluate the pre-processed power grid operation data according to the multi-dimensional performance evaluation index system to obtain a power grid operation performance evaluation index; and uses an optimization algorithm to optimize and adjust the power grid operation state based on the power grid operation performance evaluation index. Compared with the prior art, the method realizes comprehensive and accurate monitoring and optimization of the power grid operation state by comprehensively considering multi-dimensional indicators, improves the stability and efficiency of the power grid operation, and ensures the safety and reliability of the power supply.

[0088] It should be noted that the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0089] In one embodiment, Figure 2 As shown, an embodiment of the present invention provides a power grid operation optimization system considering multi-dimensional indicators, the system comprising:

[0090] The data acquisition module 101 is used to collect the original operation data of the power grid in real time, and pre-process the original operation data of the power grid to obtain pre-processed power grid operation data;

[0091] An indicator construction module 102 is used to construct a multi-dimensional performance evaluation indicator system according to the characteristics and requirements of power grid operation;

[0092] A comprehensive evaluation module 103 is used to comprehensively evaluate the pre-processed power grid operation data using a multivariate statistical analysis method according to the multi-dimensional performance evaluation index system to obtain a power grid operation performance evaluation index;

[0093] The operation optimization module 104 is used to optimize and adjust the operation status of the power grid by using an optimization algorithm based on the power grid operation performance evaluation index.

[0094] For the specific definition of a power grid operation optimization system considering multi-dimensional indicators, please refer to the above-mentioned definition of a power grid operation optimization method considering multi-dimensional indicators, which will not be repeated here. A person of ordinary skill in the art will appreciate that the various modules and steps described in conjunction with the embodiments disclosed in this application can be implemented in hardware, software, or a combination of both. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0095] The embodiment of the present invention provides a power grid operation optimization system that considers multi-dimensional indicators. The system collects the original power grid operation data in real time through the data acquisition module, and pre-processes the original power grid operation data to obtain pre-processed power grid operation data; the indicator construction module constructs a multi-dimensional performance evaluation indicator system according to the characteristics and requirements of the power grid operation; the comprehensive evaluation module uses a multivariate statistical analysis method to comprehensively evaluate the pre-processed power grid operation data according to the multi-dimensional performance evaluation indicator system to obtain a power grid operation performance evaluation index; the operation optimization module optimizes and adjusts the power grid operation status based on the power grid operation performance evaluation index using an optimization algorithm. Compared with the prior art, the system realizes comprehensive and accurate monitoring and optimization of the power grid operation status by comprehensively considering multi-dimensional indicators, improves the stability and efficiency of the power grid operation, and ensures the safety and reliability of power supply.

[0096] Figure 3 A computer device provided by an embodiment of the present invention includes a memory, a processor and a transceiver, which are connected via a bus; the memory is used to store a set of computer program instructions and data, and can transmit the stored data to the processor, and the processor can execute the program instructions stored in the memory to perform the steps of the above method.

[0097] The memory may include a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories; the processor may be a central processing unit, a microprocessor, an application-specific integrated circuit, a programmable logic device, or a combination thereof. By way of example but not limitation, the programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic, or any combination thereof.

[0098] Additionally, the memory may be a physically separate unit or may be integrated with the processor.

[0099] It can be understood by those skilled in the art that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have the same component arrangement.

[0100] In one embodiment, the present invention provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the above method are implemented.

[0101] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can 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 can be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., an SSD), etc.

[0102] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing related hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods.

[0103] The above-mentioned embodiments only express several preferred implementation modes of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for ordinary technicians in the technical field, several improvements and substitutions can be made without departing from the technical principles of the present invention, and these improvements and substitutions should also be regarded as the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be based on the protection scope of the claims.

Claims

1. A method for optimizing power grid operation considering multi-dimensional indicators, characterized in that: The following steps are involved: Collecting original grid operation data in real time, and preprocessing the original grid operation data to obtain preprocessed grid operation data; Construct a multi-dimensional performance evaluation indicator system based on the characteristics and needs of power grid operation; According to the multi-dimensional performance evaluation index system, a multivariate statistical analysis method is used to comprehensively evaluate the pre-processed power grid operation data to obtain a power grid operation performance evaluation index; Based on the power grid operation performance evaluation index, an optimization algorithm is used to optimize and adjust the power grid operation status.

2. A method for optimizing power grid operation considering multi-dimensional indicators according to claim 1, characterized in that: The steps of constructing a multi-dimensional performance evaluation index system according to the characteristics and requirements of power grid operation include: Determine the evaluation dimensions according to the characteristics and requirements of the power grid operation; the evaluation dimensions include electrical performance dimension, safety dimension, stability dimension and economic dimension; Determine the multi-dimensional performance evaluation indicators under each evaluation dimension, and use the coefficient of variation method to preliminarily assign weights to each evaluation dimension to obtain the initial dimension weights; Taking the evaluation dimension as the target layer and the multi-dimensional performance evaluation index as the criterion layer, the hierarchical analysis method is used to construct a multi-level analysis structure model; The multi-level analysis structural model is used to calculate the relative importance of different multi-dimensional performance evaluation indicators under each evaluation dimension and construct a judgment matrix; Calculate the indicator weight of each multi-dimensional performance evaluation indicator under its corresponding evaluation dimension according to the judgment matrix; Multiply the indicator weight of each multi-dimensional performance evaluation indicator by the initial dimension weight of the dimension to which it belongs to obtain a comprehensive weight; The comprehensive weights of various multi-dimensional performance evaluation indicators are summarized to form a multi-dimensional performance evaluation indicator system.

3. A method for optimizing power grid operation considering multi-dimensional indicators as claimed in claim 2, characterized in that: The step of calculating the indicator weight of each multi-dimensional performance evaluation indicator under the corresponding evaluation dimension according to the judgment matrix includes: Calculate the maximum eigenvector of the judgment matrix and obtain the indicator weights of each multi-dimensional performance evaluation indicator under its corresponding evaluation dimension.

4. A method for optimizing power grid operation considering multi-dimensional indicators as claimed in claim 2, characterized in that: The step of determining the multi-dimensional performance evaluation indicators under each evaluation dimension includes: Obtain all candidate indicators related to all evaluation dimensions from the historical operation data of the power grid and the real-time operation data of the power grid to form a preliminary candidate indicator set; Performing data cleaning on the preliminary candidate indicator set to obtain a target candidate indicator set; Traverse each evaluation dimension, use the Pearson correlation coefficient to calculate the correlation between each target candidate indicator and the weighted average of all target candidate indicators under the evaluation dimension to which it belongs, and determine the indicator correlation coefficient of each target candidate indicator; According to the indicator correlation coefficient, the target candidate indicators under each evaluation dimension are sorted, and several target candidate indicators with the highest correlation with each evaluation dimension are screened out to form a key indicator set; The minimum redundancy maximum correlation algorithm is used to screen out the optimal indicator combination under each evaluation dimension from the key indicator set as the multi-dimensional performance evaluation indicator under each evaluation dimension.

5. A method for optimizing power grid operation considering multi-dimensional indicators as claimed in claim 1, characterized in that: The step of comprehensively evaluating the pre-processed power grid operation data using a multivariate statistical analysis method according to the multi-dimensional performance evaluation index system to obtain a power grid operation performance evaluation index comprises: Calculate the covariance matrix of all indicator data in the multi-dimensional performance evaluation indicator system, and solve the eigenvalues ​​of the covariance matrix and their corresponding eigenvectors; According to the eigenvalues, the eigenvectors corresponding to the first k largest eigenvalues ​​are selected as principal components using the elbow rule; Projecting the pre-processed power grid operation data onto the principal component, calculating the score of the pre-processed power grid operation data on the principal component, and obtaining the principal component score; The scores of the principal components are weighted and summed according to their variance contribution rates to obtain the power grid operation performance evaluation index.

6. A method for optimizing power grid operation by considering multi-dimensional indicators as claimed in claim 5, characterized in that: The variance contribution of a principal component is equal to the ratio of the eigenvalue of the principal component to the sum of the total eigenvalues.

7. A method for optimizing power grid operation considering multi-dimensional indicators according to claim 1, characterized in that: The step of optimizing and adjusting the power grid operation state by using an optimization algorithm based on the power grid operation performance evaluation index comprises: Determine the optimization variable according to the power grid operation performance evaluation index, and randomly generate an initial population according to the optimization variable; each individual in the initial population represents the power grid operation state; Taking the maximization of the power grid operation performance evaluation index as the optimization goal, the initial population is iteratively optimized using a genetic algorithm; In each iteration, the power grid operation performance evaluation index of each individual is calculated to obtain the fitness value; According to the fitness value, excellent individuals are selected to perform crossover and mutation operations to generate a new generation of population, and the above iterative process is repeated until the fitness value converges; The individual with the highest fitness value is selected from the final population as the optimal solution, and the actual operation state of the power grid is adjusted according to the optimal solution.

8. A power grid operation optimization system considering multi-dimensional indicators, characterized in that: The system comprises: The data acquisition module is used to collect the original operation data of the power grid in real time, and pre-process the original operation data of the power grid to obtain pre-processed power grid operation data; The indicator construction module is used to build a multi-dimensional performance evaluation indicator system based on the characteristics and requirements of power grid operation; A comprehensive evaluation module, used to comprehensively evaluate the pre-processed power grid operation data using a multivariate statistical analysis method according to the multi-dimensional performance evaluation index system to obtain a power grid operation performance evaluation index; The operation optimization module is used to optimize and adjust the operation status of the power grid using an optimization algorithm based on the power grid operation performance evaluation index.

9. A computer device, characterized in that: The computer device comprises a processor and a memory, wherein the processor is connected to the memory, the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the computer device executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed, the method according to any one of claims 1 to 7 is implemented.

Images