Intelligent power grid risk analysis system based on incidence matrix

Abstract

The invention discloses a smart power grid risk analysis system based on an incidence matrix, and relates to the technical field of intelligent analysis, the smart power grid risk analysis system comprises a construction module, an acquisition module, an evaluation module and an optimization module, the incidence matrix is constructed, and the connection state of a topological node and a topological branch is judged through an incidence matrix marking method; and obtaining current target data according to the first identification result, calculating the weight of historical target data in a historical stable state level, constructing a stable model according to the weight, and performing optimization matching on the weight of the stable model. According to the method, the target data is selectively acquired, the stability of the system is facilitated, the expert system is introduced, the historical stable state level is more authoritative, the stable model is constructed by utilizing the historical target data and the stable state level, the risk analysis is more comprehensive and reliable, the optimization module continuously adjusts the weight of the stable model, and the risk analysis efficiency is improved. And the stability and reliability of a power grid are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent analysis, and in particular to an intelligent grid risk analysis system based on a correlation matrix. Background Art

[0002] In recent years, intelligent analysis technology has developed rapidly and has been widely used in the power grid industry. It uses big data and machine learning technologies to analyze and model historical data, predict the stability and potential risks of the power grid, deploy advanced sensors and monitoring equipment, collect power grid operation data in real time, and promptly predict and respond to power grid stability issues. It uses intelligent algorithms such as deep learning and reinforcement learning to optimize the power grid stability prediction model and improve the accuracy and reliability of the prediction.

[0003] At present, a distribution network stability evaluation method is disclosed in a Chinese invention patent with publication number CN 104700325 A. The method obtains stability evaluation by weight calculation, so as to better guide the grid to adjust and control. However, the related technology does not collect data selectively, which may easily cause instability of transmission lines and waste of storage resources, which is not conducive to the stability of the system. The predicted results are not compared with the actual results, and the prediction accuracy and applicability are lacking, which is not conducive to the objectivity of the system. Summary of the invention

[0004] The technical problem solved by the present invention is that the related technology does not collect data selectively, which easily causes instability of the transmission line and waste of storage resources, which is not conducive to the stability of the system. The predicted results are not compared with the actual results, lacking the accuracy and applicability of the prediction, which is not conducive to the objectivity of the system.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: In the first aspect, a smart grid risk analysis system based on an association matrix includes a construction module, a collection module, an evaluation module and an optimization module;

[0006] The construction module sets the electrical equipment as a topological node, sets the lines connecting each topological node or the transformers connecting each topological node as a topological branch, constructs an association matrix, and determines the connectivity status of the topological node and the topological branch by an association matrix notation method;

[0007] The acquisition module identifies the connectivity state, obtains a first identification result, acquires current target data according to the first identification result, and pre-processes the current interference data and the current target data;

[0008] The evaluation module obtains historical target data and historical stable state levels, the historical stable state levels are obtained through expert evaluation, calculates the weight of the historical target data in the historical stable state levels, constructs a stable model according to the weight, and obtains the current stable state level through the stable model;

[0009] The optimization module performs optimal matching on the weights of the stable model and updates the weights of the stable model.

[0010] As a preferred solution of the smart grid risk analysis system based on the association matrix described in the present invention, wherein: the electrical equipment includes a generator, a transformer, a busbar and a load point;

[0011] The construction logic of the association matrix includes: arranging the topological nodes as rows and arranging the branches as columns to construct the association matrix, and when the topological nodes and the topological branches are in a connection relationship, setting the corresponding elements in the association matrix to the first value, otherwise setting them to the second value;

[0012] The connectivity status includes connectivity and disconnection.

[0013] As a preferred solution of the smart grid risk analysis system based on the association matrix described in the present invention, wherein: the acquisition module identifies the connectivity state to obtain a first recognition result, the first recognition result includes meeting the acquisition condition and not meeting the acquisition condition, when the connectivity state is connected, the first recognition result is set to meet the acquisition condition, when the connectivity state is disconnected, the first recognition result is set to not meet the acquisition condition;

[0014] The logic for generating the first recognition result includes:

[0015] A first trigger condition is received, the first trigger condition is identified to obtain a first identification result, a second trigger condition is generated according to the first identification result, the second trigger condition is identified to obtain a second identification result, and a first operation is performed according to the second identification result, wherein the first trigger condition is to input a connectivity status to an acquisition module, the second trigger condition is that the first identification result meets the acquisition condition, the second identification result includes collecting the current load change, the current generator output power, the current transmission line impedance, the current voltage and the current transformer operating status, and the first operation is to start the acquisition device and transmit the current load change, the current generator output power, the current transmission line impedance, the current voltage and the current transformer operating status to the acquisition module.

[0016] As a preferred solution of the smart grid risk analysis system based on the association matrix described in the present invention, wherein: the acquisition module obtains the current target data according to the first identification result, and pre-processes the current interference data and the current target data, the current target data includes the current load change, the current generator output power, the current transmission line impedance, the current voltage and the current transformer operating status, and the pre-processing includes removing outliers, filling missing values ​​and standardizing.

[0017] As a preferred solution of the smart grid risk analysis system based on the association matrix described in the present invention, wherein: the evaluation module obtains historical target data and historical stable state level, and the historical target data includes historical load change, historical generator output power, historical transmission line impedance, historical voltage and historical transformer operation status;

[0018] The historical stable state level is obtained through expert evaluation, and the weight of the historical target data in the historical stable state level is calculated. A stable model is constructed according to the weight, and the current stable state level is obtained through the stable model. The historical stable state level includes the first level, the second level, the third level, the fourth level and the fifth level.

[0019] As a preferred solution of the smart grid risk analysis system based on the association matrix described in the present invention, the construction logic of the stability model includes:

[0020] The historical target data obtained include historical load changes, historical generator output power, historical transmission line impedance, historical voltage, historical transformer operating status and corresponding historical stable state levels. A multivariate regression analysis is performed with historical load changes, historical generator output power, historical transmission line impedance, historical voltage and historical transformer operating status as independent variables and corresponding historical stable state levels as dependent variables. The coefficients corresponding to the independent variables are set as the weights of the independent variables to construct a stable model.

[0021] As a preferred solution of the smart grid risk analysis system based on the association matrix described in the present invention, the calculation expression of the stability model is:

[0022]

[0023] Among them, y is the historical stable state level or the current stable state level, c i is the coefficient corresponding to the ith independent variable, that is, the weight corresponding to the ith independent variable, x i is the ith independent variable, and n is the number of independent variables.

[0024] As a preferred solution of the smart grid risk analysis system based on the association matrix described in the present invention, wherein: the optimization module performs optimal matching based on the weight of the stable model of the particle swarm algorithm, and updates the weight corresponding to the independent variable, and the logic of the optimal matching includes:

[0025] The number of initial population particles, the number of iterations, the inertia weight and the acceleration coefficient are set, the position and velocity of each particle are randomly initialized, and the position and velocity of the particle are used as inputs of the stabilization model;

[0026] Running the stability model to obtain a fitness evaluation value of a particle, traversing the fitness evaluation values ​​of the particles, selecting a fitness evaluation value of a particle with a maximum value, obtaining a particle position corresponding to the fitness evaluation value of the particle with the maximum value, and setting the particle position to an optimal position;

[0027] The weights corresponding to the independent variables in the stable model are updated according to the optimal position, and the calculation is terminated when the fitness evaluation value of the particle with the largest value reaches a first fitness threshold or reaches the number of iterations.

[0028] In a second aspect, the present invention provides an electronic device comprising a memory, a processor and storage in the memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps in any one of the systems described above are executed.

[0029] In a third aspect, the present invention provides a storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps in the system described in any one of the above items are executed.

[0030] The beneficial effects of the present invention are as follows: by constructing and analyzing the association matrix, the connectivity status of the equipment and lines in the power grid can be accurately judged, and the accuracy of risk analysis can be improved; by identifying the connectivity status of the power grid, the target data can be selectively obtained, and the acquisition of invalid data can be reduced, thereby reducing the storage and computing burden of the system, reducing the transmission burden of the system, and improving the computing speed of the system, which is beneficial to the stability of the system; an expert system is introduced to make the historical stability status level more authoritative; a stability model is constructed using historical target data and stability status levels, making the risk analysis more comprehensive and reliable, and enhancing the authority and practical application value of the model; the optimization module continuously adjusts the weight of the stability model, optimizes the analysis results, and adapts to the changes and uncertainties in the operation of the power grid; and through the evaluation and optimization of the stability model, it helps to improve the stability and reliability of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 A schematic diagram of the basic flow of a smart grid risk analysis system based on an association matrix provided for one embodiment of the present invention. DETAILED DESCRIPTION

[0032] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, but not all of the embodiments.

[0033] Example 1, reference Figure 1 , is an embodiment of the present invention, and provides a smart grid risk analysis system based on an association matrix, including a construction module, a collection module, an evaluation module and an optimization module;

[0034] The construction module sets the electrical equipment as a topological node, sets the lines connecting each topological node or the transformers connecting each topological node as a topological branch, constructs an association matrix, and determines the connectivity status of the topological node and the topological branch by an association matrix notation method;

[0035] The acquisition module identifies the connectivity state, obtains a first identification result, acquires current target data according to the first identification result, and pre-processes the current interference data and the current target data;

[0036] The evaluation module obtains historical target data and historical stable state levels, the historical stable state levels are obtained through expert evaluation, calculates the weight of the historical target data in the historical stable state levels, constructs a stable model according to the weight, and obtains the current stable state level through the stable model;

[0037] The optimization module performs optimal matching on the weights of the stable model and updates the weights of the stable model.

[0038] The present invention constructs and analyzes the association matrix to accurately determine the connectivity status of equipment and lines in the power grid, thereby improving the accuracy of risk analysis. By identifying the connectivity status of the power grid, the target data is selectively acquired, the acquisition of invalid data is reduced, the storage and computing burden of the system is reduced, the transmission burden of the system is reduced, the computing speed of the system is improved, and the stability of the system is improved. An expert system is introduced to make the historical stability status level more authoritative, and the stability model is constructed using historical target data and stability status levels, so that the risk analysis is more comprehensive and reliable, and the authority and practical application value of the model are enhanced. The optimization module continuously adjusts the weight of the stability model, optimizes the analysis results, and adapts to changes and uncertainties in the operation of the power grid. Through the evaluation and optimization of the stability model, the stability and reliability of the power grid are improved.

[0039] The electrical equipment includes generators, transformers, busbars and load points;

[0040] The construction logic of the association matrix includes: arranging the topological nodes as rows and arranging the branches as columns to construct the association matrix, and when the topological nodes and the topological branches are in a connection relationship, setting the corresponding elements in the association matrix to the first value, otherwise setting them to the second value;

[0041] In the specific implementation, by constructing and analyzing the association matrix, the connectivity status of equipment and lines in the power grid can be accurately determined to improve the accuracy of risk analysis.

[0042] The connectivity status includes connectivity and disconnection.

[0043] The acquisition module identifies the connectivity state and obtains a first recognition result, wherein the first recognition result includes meeting the acquisition condition and not meeting the acquisition condition. When the connectivity state is connected, the first recognition result is set to meet the acquisition condition, and when the connectivity state is disconnected, the first recognition result is set to not meet the acquisition condition.

[0044] The logic for generating the first recognition result includes:

[0045] A first trigger condition is received, the first trigger condition is identified to obtain a first identification result, a second trigger condition is generated according to the first identification result, the second trigger condition is identified to obtain a second identification result, and a first operation is performed according to the second identification result, wherein the first trigger condition is to input a connectivity status to an acquisition module, the second trigger condition is that the first identification result meets the acquisition condition, the second identification result includes collecting the current load change, the current generator output power, the current transmission line impedance, the current voltage and the current transformer operating status, and the first operation is to start the acquisition device and transmit the current load change, the current generator output power, the current transmission line impedance, the current voltage and the current transformer operating status to the acquisition module.

[0046] In specific implementation, by identifying the connectivity status of the power grid and selectively acquiring target data, the acquisition of invalid data is reduced, the storage and computing burden of the system is reduced, the transmission burden of the system is reduced, the computing speed of the system is improved, and the stability of the system is improved.

[0047] The acquisition module obtains current target data according to the first recognition result, and preprocesses the current interference data and the current target data, wherein the current target data includes the current load change, the current generator output power, the current transmission line impedance, the current voltage and the current transformer operating status, and the preprocessing includes outlier removal, missing value filling and standardization.

[0048] In a specific implementation, the standardization process makes the data distributed between 0 and 1, which is beneficial to subsequent calculations and improves the calculation speed of the system.

[0049] The evaluation module acquires historical target data and historical stable state levels, wherein the historical target data includes historical load changes, historical generator output power, historical transmission line impedance, historical voltage, and historical transformer operating status;

[0050] The historical stable state level is obtained through expert evaluation, and the weight of the historical target data in the historical stable state level is calculated. A stable model is constructed according to the weight, and the current stable state level is obtained through the stable model. The historical stable state level includes the first level, the second level, the third level, the fourth level and the fifth level.

[0051] In the specific implementation, an expert system was introduced to make the historical stability status level more authoritative.

[0052] The construction logic of the stable model includes:

[0053] The historical target data obtained include historical load changes, historical generator output power, historical transmission line impedance, historical voltage, historical transformer operating status and corresponding historical stable state levels. A multivariate regression analysis is performed with historical load changes, historical generator output power, historical transmission line impedance, historical voltage and historical transformer operating status as independent variables and corresponding historical stable state levels as dependent variables. The coefficients corresponding to the independent variables are set as the weights of the independent variables to construct a stable model.

[0054] The calculation expression of the stability model is:

[0055]

[0056] Among them, y is the historical stable state level or the current stable state level, c i is the coefficient corresponding to the ith independent variable, that is, the weight corresponding to the ith independent variable, x i is the ith independent variable, and n is the number of independent variables.

[0057] In the specific implementation, historical target data and stable state levels are used to build a stable model, which makes the risk analysis more comprehensive and reliable, and enhances the authority and practical application value of the model.

[0058] The optimization module performs optimal matching based on the weight of the stable model of the particle swarm algorithm and updates the weight corresponding to the independent variable. The logic of the optimal matching includes:

[0059] The number of initial population particles, the number of iterations, the inertia weight and the acceleration coefficient are set, the position and velocity of each particle are randomly initialized, and the position and velocity of the particle are used as inputs of the stabilization model;

[0060] Running the stability model to obtain a fitness evaluation value of a particle, traversing the fitness evaluation values ​​of the particles, selecting a fitness evaluation value of a particle with a maximum value, obtaining a particle position corresponding to the fitness evaluation value of the particle with the maximum value, and setting the particle position to an optimal position;

[0061] The weights corresponding to the independent variables in the stable model are updated according to the optimal position, and the calculation is terminated when the fitness evaluation value of the particle with the largest value reaches a first fitness threshold or reaches the number of iterations.

[0062] In specific implementation, the optimization module continuously adjusts the weights of the stability model, optimizes the analysis results, adapts to changes and uncertainties in power grid operation, and helps improve the stability and reliability of the power grid through stability model evaluation and optimization.

[0063] The present invention constructs and analyzes the association matrix to accurately determine the connectivity status of equipment and lines in the power grid, thereby improving the accuracy of risk analysis. By identifying the connectivity status of the power grid, the target data is selectively acquired, the acquisition of invalid data is reduced, the storage and computing burden of the system is reduced, the transmission burden of the system is reduced, the computing speed of the system is improved, and the stability of the system is improved. An expert system is introduced to make the historical stability status level more authoritative, and the stability model is constructed using historical target data and stability status levels, so that the risk analysis is more comprehensive and reliable, and the authority and practical application value of the model are enhanced. The optimization module continuously adjusts the weight of the stability model, optimizes the analysis results, and adapts to changes and uncertainties in the operation of the power grid. Through the evaluation and optimization of the stability model, the stability and reliability of the power grid are improved.

[0064] It should be understood by those skilled in the art that the embodiments of the present invention can be provided as methods, systems or computer program products. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program codes. Among them, the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, disk or optical disk. These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0065] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. Smart grid risk analysis system based on correlation matrix, characterized by: It includes construction module, acquisition module, evaluation module and optimization module; The construction module sets the electrical equipment as a topological node, sets the lines connecting each topological node or the transformers connecting each topological node as a topological branch, constructs an association matrix, and determines the connectivity status of the topological node and the topological branch by an association matrix notation method; The acquisition module identifies the connectivity state, obtains a first identification result, obtains current target data according to the first identification result, and pre-processes the current interference data and the current target data; The evaluation module obtains historical target data and historical stable state levels, the historical stable state levels are obtained through expert evaluation, calculates the weight of the historical target data in the historical stable state levels, constructs a stable model according to the weight, and obtains the current stable state level through the stable model; The optimization module performs optimal matching on the weights of the stable model and updates the weights of the stable model.

2. The smart grid risk analysis system based on association matrix according to claim 1, characterized in that: The electrical equipment includes generators, transformers, busbars and load points; The construction logic of the association matrix includes: arranging the topological nodes as rows and arranging the branches as columns to construct the association matrix, and when the topological nodes and the topological branches are in a connection relationship, setting the corresponding elements in the association matrix to the first value, otherwise setting them to the second value; The connectivity status includes connectivity and disconnection.

3. The smart grid risk analysis system based on association matrix according to claim 1, characterized in that: The acquisition module identifies the connectivity state and obtains a first recognition result, wherein the first recognition result includes meeting the acquisition condition and not meeting the acquisition condition. When the connectivity state is connected, the first recognition result is set to meet the acquisition condition, and when the connectivity state is disconnected, the first recognition result is set to not meet the acquisition condition. The logic for generating the first recognition result includes: A first trigger condition is received, the first trigger condition is identified to obtain a first identification result, a second trigger condition is generated according to the first identification result, the second trigger condition is identified to obtain a second identification result, and a first operation is performed according to the second identification result, wherein the first trigger condition is to input a connectivity status to an acquisition module, the second trigger condition is that the first identification result meets the acquisition condition, the second identification result includes collecting the current load change, the current generator output power, the current transmission line impedance, the current voltage and the current transformer operating status, and the first operation is to start the acquisition device and transmit the current load change, the current generator output power, the current transmission line impedance, the current voltage and the current transformer operating status to the acquisition module.

4. The smart grid risk analysis system based on association matrix according to claim 3, characterized in that: The acquisition module obtains current target data according to the first recognition result, and preprocesses the current interference data and the current target data, wherein the current target data includes the current load change, the current generator output power, the current transmission line impedance, the current voltage and the current transformer operating status, and the preprocessing includes outlier removal, missing value filling and standardization.

5. The smart grid risk analysis system based on association matrix according to claim 1, characterized in that: The evaluation module acquires historical target data and historical stable state levels, wherein the historical target data includes historical load changes, historical generator output power, historical transmission line impedance, historical voltage, and historical transformer operating status; The historical stable state level is obtained through expert evaluation, and the weight of the historical target data in the historical stable state level is calculated. A stable model is constructed according to the weight, and the current stable state level is obtained through the stable model. The historical stable state level includes the first level, the second level, the third level, the fourth level and the fifth level.

6. The smart grid risk analysis system based on association matrix according to claim 5, characterized in that: The construction logic of the stable model includes: The historical target data obtained include historical load changes, historical generator output power, historical transmission line impedance, historical voltage, historical transformer operating status and corresponding historical stable state levels. A multivariate regression analysis is performed with historical load changes, historical generator output power, historical transmission line impedance, historical voltage and historical transformer operating status as independent variables and corresponding historical stable state levels as dependent variables. The coefficients corresponding to the independent variables are set as the weights of the independent variables to construct a stable model.

7. The smart grid risk analysis system based on association matrix according to claim 1, characterized in that: The calculation expression of the stability model is: Among them, y is the historical stable state level or the current stable state level, c i is the coefficient corresponding to the ith independent variable, that is, the weight corresponding to the ith independent variable, x i is the ith independent variable, and n is the number of independent variables.

8. The smart grid risk analysis system based on association matrix according to claim 7, characterized in that: The optimization module performs optimal matching based on the weight of the stable model of the particle swarm algorithm and updates the weight corresponding to the independent variable. The logic of the optimal matching includes: The number of initial population particles, the number of iterations, the inertia weight and the acceleration coefficient are set, the position and velocity of each particle are randomly initialized, and the position and velocity of the particle are used as inputs of the stabilization model; Running the stability model to obtain a fitness evaluation value of a particle, traversing the fitness evaluation values ​​of the particles, selecting a fitness evaluation value of a particle with a maximum value, obtaining a particle position corresponding to the fitness evaluation value of the particle with the maximum value, and setting the particle position to an optimal position; The weights corresponding to the independent variables in the stable model are updated according to the optimal position, and the calculation is terminated when the fitness evaluation value of the particle with the largest value reaches a first fitness threshold or reaches the number of iterations.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the smart grid risk analysis system based on the association matrix described in any one of claims 1-8 is implemented.

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 by a processor, the smart grid risk analysis system based on the association matrix according to any one of claims 1 to 8 is implemented.

Images