A coordinated control method and system for a distributed power capacitor compensation device

Abstract

The present invention discloses a method and system for coordinated control of distributed power capacitor compensation devices, which relates to the field of electrical engineering. The method includes: interacting with the target power grid, acquiring multiple distributed power capacitor compensation devices, and constructing a compensation device topology network; extracting a power consumption data set based on the historical power consumption records of the target control area; performing common-state division of the compensation device topology network, and obtaining the common-state division results; constructing a coordinated controller through the power consumption data set and the common-state division results; activating the compensation device topology network to collect the distributed power consumption data of the target control area, inputting it into the coordinated controller, and performing coordinated control of multiple distributed power capacitor compensation devices. The method solves the technical problem that the existing control of distributed power capacitor compensation devices lacks global considerations, resulting in poor compensation effects, and achieves the technical effect of realizing global coordinated control of distributed power capacitor compensation devices and improving compensation quality.

Description

Technical Field

[0001] The present application relates to the field of electrical engineering, and in particular to a coordinated control method and system for a distributed power capacitor compensation device. Background Art

[0002] With the continuous development of power systems and the improvement of their intelligence level, distributed power capacitor compensation devices are widely used to improve the power factor of power grids, reduce line losses, and improve power quality. These compensation devices are usually scattered in different locations of the power grid and operate independently to compensate for reactive power in local power grids. For the control of distributed power capacitor compensation devices, a single control strategy or a simple collaborative control method based on local information is currently mainly used. Since existing methods often only focus on the performance of a single or local compensation device and ignore the global optimization of the entire power system, it is difficult to achieve the optimal compensation effect in a complex and changeable power system environment.

[0003] In the current related technologies, the control of distributed power capacitor compensation devices has the technical problem of lack of global consideration leading to poor compensation effect. Summary of the invention

[0004] The present application provides a collaborative control method and system for a distributed power capacitor compensation device, adopts an interactive target power grid, constructs a compensation device topology network, extracts power consumption data sets based on historical power consumption records, performs common-state division of the compensation device topology network, obtains multiple common-state division classes, constructs a collaborative controller containing multiple collaborative control strategies, collects real-time power consumption data, and inputs the data into the collaborative controller for collaborative control, thereby achieving the technical effect of realizing global collaborative control of distributed power capacitor compensation devices and improving compensation quality.

[0005] The present application provides a coordinated control method for a distributed power capacitor compensation device, comprising:

[0006] Interact with the target power grid, obtain multiple distributed power capacitor compensation devices in the target control area, and build a compensation device topology network;

[0007] Extract the power consumption dataset based on the historical power consumption records of the target control area;

[0008] According to the electric power consumption data set, performing common-state division of the topological network of the compensation device to obtain a common-state division result, wherein the common-state division result includes a plurality of common-state division classes;

[0009] Constructing a collaborative controller through the power consumption data set and the common state division result, wherein the collaborative controller includes a plurality of collaborative control strategies;

[0010] The compensation device topology network is activated to collect distributed power consumption data in the target control area, and the data is input into the collaborative controller to perform collaborative control of multiple distributed power capacitor compensation devices.

[0011] In a possible implementation, the target power grid is interacted with, multiple distributed power capacitor compensation devices in the target control area are obtained, a compensation device topology network is constructed, and the following processing is performed:

[0012] Establish a communication connection with the target power grid and obtain the configuration file of the regional compensation device;

[0013] Based on the regional compensation device configuration file, extract the location information, parameter information and status information of multiple distributed power capacitor compensation devices in the target control area, and store them as basic device information;

[0014] Analyze and determine the connection relationship and communication mode of multiple distributed power capacitor compensation devices in the target control area, and build a compensation device network;

[0015] The basic information of the device is updated to the compensation device network to obtain a compensation device topology network.

[0016] In a possible implementation, based on the electric power consumption data set, the common-state division of the compensation device topology network is performed, the common-state division result is obtained, and the following processing is performed:

[0017] Preprocessing the electric power consumption data set to obtain a standard electric power consumption data set;

[0018] Initializing a common-mode partitioning algorithm, and inputting the standard power consumption data set for common-mode partitioning to obtain a classified power consumption data set, wherein the classified power consumption data set includes a plurality of power consumption data groups;

[0019] Based on the association relationship between the plurality of the power consumption data groups and the plurality of the common-state division classes, a plurality of common-state division classes are mapped and established, and stored as the common-state division result.

[0020] In a possible implementation, before performing the common-state division of the compensation device topology network according to the power consumption data set, the following processing is performed:

[0021] Analyze the electric power consumption data set to obtain a common-state partition key feature set;

[0022] The key feature set is divided according to the common state to perform reduction processing on the power consumption data set.

[0023] In a possible implementation, the power consumption data set is analyzed to obtain a common state division key feature set, and the following processing is performed:

[0024] Based on the principle of standardization, the electric power consumption data set is decentralized;

[0025] According to the decentralization result, a standard data matrix is ​​constructed with the number of data items in the electric power consumption data set as the number of rows of the matrix and the number of electricity consumption data indicator categories in the electric power consumption data set as the number of columns of the matrix;

[0026] Establishing a correlation matrix of the standard data matrix, calculating the characteristic roots and eigenvectors of the correlation matrix, and obtaining a correlation matrix feature set;

[0027] According to the variance contribution scores of the correlation matrix feature set, a variance contribution accumulation sequence is accumulated, wherein the variance contribution accumulation sequence includes a plurality of variance contribution accumulation scores, and the variance contribution accumulation scores have a feature class label;

[0028] Based on the preset contribution rate constraint, the variance contribution cumulative score is screened according to the variance contribution cumulative sequence, and the feature class mark of the screening result is extracted to generate the common state partition key feature set.

[0029] In a possible implementation, a collaborative controller is constructed by using the power consumption data set and the common state division result to perform the following processing:

[0030] Randomly select from the common-state partition results to obtain a first common-state partition class;

[0031] According to the first common state classification class and based on the common state classification result, calling a first power consumption data group;

[0032] Based on the first power consumption data group, obtaining a first collaborative control strategy through a supervised training method;

[0033] The first collaborative control strategy is stored in the collaborative controller.

[0034] In a possible implementation, a plurality of distributed power capacitor compensation devices are coordinated and controlled to perform the following processing:

[0035] Analyze the distributed power consumption data to determine the real-time common state classification class;

[0036] According to the real-time common state classification, traverse the multiple collaborative control strategies in the collaborative controller to perform control matching;

[0037] Based on the control matching result, activating and calling the collaborative controller to make a control decision;

[0038] The compensation device topology network sends the control decision result to multiple distributed power capacitor compensation devices for coordinated control.

[0039] The present application also provides a coordinated control system for a distributed power capacitor compensation device, comprising:

[0040] A compensation device topology network construction module, which is used to interact with the target power grid, obtain multiple distributed power capacitor compensation devices in the target control area, and construct a compensation device topology network;

[0041] An electric power consumption data set extraction module, the electric power consumption data set extraction module is used to extract an electric power consumption data set based on the historical electricity consumption records of the target control area;

[0042] A common state division module, the common state division module is used to perform common state division of the compensation device topology network according to the power consumption data set, and obtain a common state division result, wherein the common state division result includes a plurality of common state division classes;

[0043] A collaborative controller construction module, the collaborative controller construction module is used to construct a collaborative controller through the power consumption data set and the common state division result, wherein the collaborative controller includes a plurality of collaborative control strategies;

[0044] A collaborative control module is used to activate the compensation device topology network to collect distributed power consumption data in the target control area, input the data into the collaborative controller, and perform collaborative control of multiple distributed power capacitor compensation devices.

[0045] It is intended to propose a collaborative control method and system for a distributed power capacitor compensation device proposed in this application. Through the interactive target power grid, multiple distributed power capacitor compensation devices in the target control area are obtained to construct a compensation device topology network. Then, based on the historical power consumption records of the target control area, the power consumption data set is extracted. Then, based on the power consumption data set, the compensation device topology network is co-modified to obtain the co-modified division result, wherein the co-modified division result includes multiple co-modified division classes. Then, through the power consumption data set and the co-modified division result, a collaborative controller is constructed, wherein the collaborative controller includes multiple collaborative control strategies. Finally, the compensation device topology network is activated to collect the distributed power consumption data of the target control area, and the data is input into the collaborative controller to perform collaborative control of multiple distributed power capacitor compensation devices, thereby achieving the technical effect of realizing global collaborative control of distributed power capacitor compensation devices and improving compensation quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0047] Figure 1 A schematic flow chart of a coordinated control method of a distributed power capacitor compensation device provided in an embodiment of the present application;

[0048] Figure 2 A schematic diagram of the structure of a collaborative control system of a distributed power capacitor compensation device provided in an embodiment of the present application.

[0049] Explanation of the reference numerals: compensation device topology network construction module 10 , power consumption data set extraction module 20 , common state division module 30 , collaborative controller construction module 40 , collaborative control module 50 . DETAILED DESCRIPTION

[0050] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0051] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0052] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0053] The present application embodiment provides a method for coordinated control of a distributed power capacitor compensation device, such as Figure 1 As shown, the method includes:

[0054] Step S100, interact with the target power grid, obtain multiple distributed power capacitor compensation devices in the target control area, and build a compensation device topology network. Specifically, establish a connection with the target power grid to make communication smooth, and the target power grid refers to a specific power grid area or system that needs to be controlled and optimized. Obtain the current operating status, topology, and possible control interface of the target power grid. Identify the specific locations of all distributed power capacitor compensation devices in the target control area (a specific area or range where power capacitor compensation and collaborative control are required), collect the basic parameters of each distributed power capacitor compensation device, such as model, capacity, rated voltage and current, etc., and obtain the current operating status and control mode of each distributed power capacitor compensation device, wherein the distributed power capacitor compensation device is a device that is dispersedly installed at different locations of the target power grid and is used to compensate for reactive power in the target power grid, improve power factor, and reduce line loss. According to the physical connection relationship between the distributed power capacitor compensation devices (such as cables, busbars, etc.), draw a topology diagram, evaluate the communication capabilities between the distributed power capacitor compensation devices, determine the communication protocol and channel, mark the communication links and interfaces in the topology diagram, and form a complete compensation device topology network.

[0055] In a possible implementation, step S100 further includes step S110, establishing a communication connection with the target power grid and obtaining a regional compensation device configuration file. Specifically, a dedicated communication line or network protocol (such as TCP / IP) is used to establish a stable communication connection with the target power grid, and a request is sent to the management system of the target power grid to obtain a regional compensation device configuration file, that is, a file containing configuration information, parameter settings, operating status and other data of the distributed power capacitor compensation device. Step S120, based on the regional compensation device configuration file, extracts the location information, parameter information and status information of multiple distributed power capacitor compensation devices in the target control area, and stores them as basic device information. Specifically, the regional compensation device configuration file is opened and parsed to extract the location information (information on the specific location in the power grid), such as longitude and latitude or specific address, parameter information (data on various parameters required for operation), such as rated voltage, rated current, capacitance value, etc., and status information (data on the current operating status), such as current operating mode, whether online, fault status, etc. The extracted information is sorted and stored as basic device information. Step S130, analyze and determine the connection relationship and communication mode of multiple distributed power capacitor compensation devices in the target control area, and construct a compensation device network. Specifically, according to the location information in the basic information of the device, analyze the physical connection relationship between each distributed power capacitor compensation device, combine the communication configuration information in the regional compensation device configuration file, determine the communication mode (such as wired communication, wireless communication, etc.) between each distributed power capacitor compensation device, and use graph theory or network topology analysis methods to construct a compensation device network including distributed power capacitor compensation device nodes and communication links. Step S140, update the basic information of the device to the compensation device network, and obtain the compensation device topology network. Specifically, match the basic information of the device (location information, parameter information, status information) obtained in step S120 with the compensation device network constructed in step S130, and update the information of each distributed power capacitor compensation device node in the compensation device network, so that the distributed power capacitor compensation device node information is consistent with the basic information of the device. After completing the above steps, the compensation device network obtained is the required compensation device topology network. This implementation method extracts and stores basic information about the device, making it easier to monitor, manage, and maintain the distributed power capacitor compensation device, thereby achieving a technical effect that helps improve the stability and efficiency of the target power grid.

[0056] Step S200, based on the historical electricity consumption records of the target control area, extract the power consumption data set. Specifically, access the historical electricity consumption database of the target control area, extract key information in the historical electricity consumption records (recording the operating data of the target power grid in the past period of time), such as load changes, power factor, voltage fluctuations, etc., clean and pre-process the data, eliminate outliers and missing data, and integrate the processed data into a power consumption data set.

[0057] Step S300, based on the power consumption data set, the compensation device topology network is divided into common states, and the common state division results are obtained, wherein the common state division results include multiple common state division classes. The common state division refers to dividing the distributed power capacitor compensation devices into sets or categories with similar states according to their operating characteristics. Specifically, statistical methods or machine learning algorithms are used to extract features related to the operating state of the distributed power capacitor compensation devices from the power consumption data set, such as voltage fluctuations, current changes, power factors, etc. According to the extracted features, similarity measurement methods such as Euclidean distance, cosine similarity, etc. are used to calculate the similarity between the operating states of different distributed power capacitor compensation devices, and clustering algorithms such as K-means, hierarchical clustering, etc. are used to perform cluster analysis on the distributed power capacitor compensation devices. According to the similarity calculation results and clustering results, the distributed power capacitor compensation devices are divided into multiple common state division classes, and the distributed power capacitor compensation devices in each common state division class have similar operating characteristics. The common state division results are output in the form of tables, charts, etc.

[0058] In a possible implementation, step S300 further includes step S310, preprocessing the electric power consumption data set to obtain a standard electric power consumption data set. Specifically, remove missing values, abnormal values ​​and duplicate data in the electric power consumption data set, clean the electric power consumption data set, and keep the data complete and accurate. Standardize the numerical data in the electric power consumption data set, scale the data so that it falls into a small specific interval, eliminate the dimensional differences between different indicators, and enable indicators of different units or magnitudes to be compared and weighted. According to the operating characteristics of the distributed power capacitor compensation device and the requirements of common mode division, select relevant features from the original data set to construct a standard electric power consumption data set. Step S320, initialize the common mode division algorithm, input the standard electric power consumption data set for common mode division, and obtain a classified power consumption data set, wherein the classified power consumption data set includes multiple power consumption data groups. Specifically, the common mode partitioning algorithm is an algorithm for partitioning data into subsets or clusters with similar characteristics, such as a clustering-based algorithm (such as a k-means algorithm) or a graph-based algorithm (such as a spectral clustering algorithm). Set necessary parameters for the common mode partitioning algorithm, such as the number of clusters, the number of iterations, the similarity measurement method, etc., input the standard power consumption data set into the initialized common mode partitioning algorithm, execute the algorithm for common mode partitioning, and after the algorithm is executed, output the classified power consumption data set, which includes multiple power consumption data groups, each of which represents a common mode partitioning class. Step S330, based on the association relationship between the multiple power consumption data groups and the multiple common mode partitioning classes, map and establish multiple common mode partitioning classes, and store them as the common mode partitioning results. Specifically, analyze the association relationship between each power consumption data group and the common mode partitioning class, determine the category to which each power consumption data group belongs, and establish a mapping relationship between the power consumption data group and the common mode partitioning class based on the association relationship analysis result, and store the mapping relationship as the common mode partitioning result. This implementation method improves the quality and consistency of the data by preprocessing and standardizing the power consumption data set, provides a reliable data basis for common-state division, and achieves the technical effect of improving the accuracy of common-state division.

[0059] In a possible implementation, before performing the common-mode partitioning of the topological network of the compensation device according to the power consumption data set, step S300 further includes step S340, analyzing the power consumption data set to obtain the common-mode partitioning key feature set. Specifically, extract the original features related to the operating state and performance of the distributed power capacitor compensation device from the power consumption data set, use statistical methods or machine learning techniques to analyze the correlation between the features, identify the features that are highly relevant to the common-mode partitioning task, and evaluate the importance of each feature in the common-mode partitioning through a feature selection algorithm (such as a method based on information gain, model performance improvement, etc.). According to the feature importance evaluation result, select the feature that contributes most to the common-mode partitioning to form the common-mode partitioning key feature set. Step S350, perform a reduction process on the power consumption data set with the common-mode partitioning key feature set. Specifically, according to the common-mode partitioning key feature set, screen out the data records that are critical to the common-mode partitioning task. If the dimension of the data set is too high, reduce the number of features through dimensionality reduction techniques (such as principal component analysis, linear discriminant analysis, etc.) while retaining key information. Further remove redundant data, noise data and outliers. The data set after reduction processing is verified to ensure that key information is retained and does not affect the results of subsequent common-mode division. This implementation method performs key feature analysis and reduction processing on the power consumption data set before performing common-mode division of the compensation device topology network, reducing data redundancy and noise interference, improving data processing efficiency and accuracy, and providing better data input for the subsequent common-mode division algorithm, achieving a technical effect that helps improve the accuracy and efficiency of common-mode division.

[0060] In a possible implementation, step S340 further includes step S341, based on the principle of standardization, the power consumption data set is decentralized. Specifically, each feature in the power consumption data set is decentralized, the data is converted into a numerical value with a unified dimension or range, and the dimension difference between different features is eliminated, for example, by subtracting the mean of each feature and dividing it by its standard deviation. After the decentralized processing, the center point (mean) of the power consumption data set is moved to the origin, that is, the mean of each feature becomes 0. Step S342, according to the decentralized result, the number of data in the power consumption data set is the number of rows of the matrix, and the number of power consumption data indicator classes in the power consumption data set is the number of columns of the matrix, to construct a standard data matrix. Specifically, the standard data matrix is ​​a two-dimensional array for storing processed standardized data, the number of rows of the standard data matrix is ​​equal to the number of decentralized data, and the number of columns is equal to the number of power consumption data indicator classes. The decentralized data is filled into the standard data matrix in the order of rows and columns. Step S343, establish the correlation matrix of the standard data matrix, calculate the characteristic root and characteristic vector of the correlation matrix, and obtain the correlation matrix feature set. Specifically, according to the standard data matrix, calculate the correlation coefficient between each feature and construct the correlation matrix. Perform characteristic decomposition on the correlation matrix, solve its characteristic root (i.e., the variance of the principal component) and the corresponding characteristic vector (i.e., the direction of the principal component). Combine the characteristic root and the characteristic vector into a correlation matrix feature set for principal component analysis. Step S344, according to the variance contribution score of the correlation matrix feature set, accumulate and obtain the variance contribution cumulative sequence, wherein the variance contribution cumulative sequence includes multiple variance contribution cumulative scores, and the variance contribution cumulative score has a feature class mark. Specifically, for each principal component (i.e., each characteristic root), calculate its variance contribution score, i.e., the proportion of the variance of the principal component to the total variance, reflecting the importance of the principal component. According to the order of the characteristic roots (e.g., arranged in descending order by the size of the variance), the variance contribution scores are accumulated to form a variance contribution cumulative sequence, which is used to determine the number of principal components that need to be retained, and each variance contribution cumulative score corresponds to a feature class mark. Step S345, based on the preset contribution rate constraint, the variance contribution cumulative score is screened according to the variance contribution cumulative sequence, and the feature class mark of the screening result is extracted to generate the common mode partition key feature set. Specifically, according to actual needs and experience, a contribution rate constraint (used to determine the threshold value of the number of principal components to be retained) is set to determine how many principal components to retain to achieve a sufficient variance contribution rate. From the variance contribution cumulative sequence, find the first cumulative score that is greater than or equal to the contribution rate threshold, and determine its corresponding feature class mark. Extract the corresponding feature class marks in the screening results to form the common mode partition key feature set. The features in the common mode partition key feature set are obtained by screening after principal component analysis, and are the most important features for common mode partition while maintaining a sufficient variance contribution rate.This implementation method uses principal component analysis to screen out the key feature set for common mode partitioning, which is the most important feature set for common mode partitioning while maintaining sufficient information. These features can more accurately reflect the main changes and patterns of the power consumption data set. At the same time, reducing the number of features reduces the computational complexity, thereby achieving the technical effect of improving the efficiency and accuracy of subsequent common mode partitioning.

[0061] Step S400, constructing a collaborative controller through the power consumption data set and the common state division result, wherein the collaborative controller includes multiple collaborative control strategies. Specifically, the relationship between the power consumption data set and the common state division result is analyzed, and the power consumption data set is grouped or classified according to the common state division result. According to the characteristics of the power consumption data set and the common state division result, multiple collaborative control strategies are designed, and the collaborative control strategy refers to the specific method and rules for realizing collaborative control, and these collaborative control strategies include rule-based control, optimization-based control, learning-based control, etc. Each collaborative control strategy includes a control target, a control logic, and required input and output data. According to the designed collaborative control strategy, the overall structure of the collaborative controller is constructed, and the collaborative controller is a device or system for coordinating and controlling the operation of multiple distributed power capacitor compensation devices. By integrating multiple collaborative control strategies, the collaborative control of the system is realized, and the performance, stability and reliability of the system are improved. The overall structure of the collaborative controller includes the input, output and internal data processing flow of the collaborative controller. According to the actual application scenario and requirements, various parameters of the collaborative controller are configured, including parameters of the control strategy, parameters of data processing, etc.

[0062] In a possible implementation, step S400 further includes step S410, randomly selecting from the common mode division results to obtain a first common mode division class. Specifically, from the common mode division results, randomly select a common mode as the first common mode division class, and mark the first common mode division class as the target common mode currently being processed. Step S420, according to the first common mode division class, based on the common mode division results, call the first electricity consumption data group. Specifically, according to the identifier of the first common mode division class, filter out the electricity consumption data belonging to the common mode category from the electric power consumption data set, and use the filtered electricity consumption data as the first electricity consumption data group. Step S430, based on the first electricity consumption data group, obtain a first collaborative control strategy through a supervised training method. Specifically, a supervised learning algorithm (a machine learning method that uses labeled training data to train a model so that the model can predict the corresponding output based on the input data) is used to train the model using the first power consumption data group as training data. Based on the training results, a collaborative control strategy for the first common mode classification class is obtained, that is, a first collaborative control strategy, which is used to control or optimize the power consumption corresponding to the first common mode classification class. Step S440, store the first collaborative control strategy in the collaborative controller. Specifically, the trained first collaborative control strategy is saved in the storage module of the collaborative controller, and the control strategy library of the collaborative controller is updated to include the new control strategy. This implementation method can use different power consumption requirements by training the collaborative control strategy separately for each common mode classification class, and uses actual power consumption data to train the collaborative control strategy, so that the collaborative control strategy can be closer to the actual situation, thereby achieving the technical effect of improving the accuracy and effectiveness of control.

[0063] Step S500, activate the compensation device topology network to collect the distributed power consumption data of the target control area, input the data into the collaborative controller, and perform collaborative control of multiple distributed power capacitor compensation devices. Specifically, activate the data acquisition function in the compensation device topology network, and each distributed power capacitor compensation device acquires the distributed power consumption data of the target control area in real time through sensors and acquisition equipment according to the settings. The distributed power consumption data is the target power grid parameter data collected by each distributed power capacitor compensation device, such as voltage, current, power factor, etc. The collected distributed power consumption data is transmitted to the collaborative controller through the communication network. The collaborative controller receives the data, parses and processes it, and extracts key information for collaborative control. The collaborative controller calculates the control instructions of each distributed power capacitor compensation device based on the input distributed power consumption data and the built-in collaborative control strategy, and sends the control instructions to the corresponding distributed power capacitor compensation device through the compensation device topology network. After receiving the control instructions, the distributed power capacitor compensation device performs the corresponding capacitor compensation operation to compensate for reactive power in the best way, thereby realizing collaborative control of the power in the target control area. The embodiment of the present application adopts an interactive target power grid, constructs a compensation device topology network, extracts power consumption data sets based on historical power consumption records, performs common-state division of the compensation device topology network, obtains multiple common-state division classes, constructs a collaborative controller containing multiple collaborative control strategies, collects real-time power consumption data, and inputs the collaborative controller for collaborative control, etc., to achieve the technical effect of realizing global collaborative control of distributed power capacitor compensation devices and improving compensation quality.

[0064] In a possible implementation, the coordinated control of multiple distributed power capacitor compensation devices is performed, and step S500 further includes step S510, analyzing the distributed power consumption data and determining the real-time common state division class. Specifically, extract key parameters such as voltage, current, power factor, etc. in the distributed power consumption data, apply data analysis algorithms or models, perform real-time analysis on the extracted parameters, identify the operating state and characteristics of the current power system, and determine the real-time common state division class that best matches the current operating state based on the analysis results. Step S520, according to the real-time common state division class, traverse the multiple collaborative control strategies in the collaborative controller for control matching. Specifically, obtain multiple collaborative control strategies stored in the collaborative controller, traverse these collaborative control strategies, analyze the common state division category and control logic applicable to each collaborative control strategy, match the real-time common state division class with each collaborative control strategy, and find the collaborative control strategy that best meets the current power system requirements. Step S530, based on the control matching result, activate and call the collaborative controller to make a control decision. Specifically, according to the control matching result, the collaborative control strategy to be activated is determined, the corresponding module or algorithm in the collaborative controller is activated, and the real-time distributed power consumption data is input. The collaborative controller performs control decision calculations based on the input data and the collaborative control strategy to generate control instructions or parameters. Step S540, the compensation device topology network sends the control decision results to multiple distributed power capacitor compensation devices for collaborative control. Specifically, the control decision results generated by the collaborative controller are transmitted through the compensation device topology network. After receiving the control decision results, each distributed power capacitor compensation device performs the corresponding capacitor compensation operation to achieve collaborative control of the power system. This implementation method can accurately reflect the current state of the power system by analyzing the distributed power consumption data collected in real time, and achieves the technical effect of ensuring the real-time and accuracy of collaborative control decisions.

[0065] In the above, refer to Figure 1 A coordinated control method for a distributed power capacitor compensation device according to an embodiment of the present invention is described in detail. Figure 2 A coordinated control system of a distributed power capacitor compensation device according to an embodiment of the present invention is described.

[0066] A coordinated control system of a distributed power capacitor compensation device according to an embodiment of the present invention is used to solve the technical problem that the existing distributed power capacitor compensation device control lacks global considerations, resulting in poor compensation effects, so as to achieve global coordinated control of the distributed power capacitor compensation device and improve the compensation quality. A coordinated control system of a distributed power capacitor compensation device includes: a compensation device topology network construction module 10, an electric power consumption data set extraction module 20, a common state partitioning module 30, a coordinated controller construction module 40, and a coordinated control module 50.

[0067] The compensation device topology network construction module 10 is used to interact with the target power grid, obtain multiple distributed power capacitor compensation devices in the target control area, and construct a compensation device topology network;

[0068] The power consumption data set extraction module 20 is used to extract the power consumption data set based on the historical power consumption records of the target control area;

[0069] The common state division module 30 is used to perform common state division of the compensation device topology network according to the power consumption data set, and obtain a common state division result, wherein the common state division result includes a plurality of common state division classes;

[0070] The collaborative controller construction module 40 is used to construct a collaborative controller through the power consumption data set and the common state division result, wherein the collaborative controller includes multiple collaborative control strategies;

[0071] The collaborative control module 50 is used to activate the compensation device topology network to collect distributed power consumption data in the target control area, input the data into the collaborative controller, and perform collaborative control of multiple distributed power capacitor compensation devices.

[0072] Below, the specific configuration of the compensation device topology network construction module 10 will be described in detail. As described above, the target power grid is interacted with, multiple distributed power capacitor compensation devices in the target control area are obtained, and a compensation device topology network is constructed. The compensation device topology network construction module 10 may further include: a communication connection establishment unit is used to establish a communication connection with the target power grid and obtain a regional compensation device configuration file; a device basic information extraction unit is used to extract the location information, parameter information and status information of multiple distributed power capacitor compensation devices in the target control area based on the regional compensation device configuration file, and store it as device basic information; a compensation device network construction unit is used to analyze and determine the connection relationship and communication method of multiple distributed power capacitor compensation devices in the target control area, and construct a compensation device network; a compensation device topology network acquisition unit is used to update the device basic information to the compensation device network and obtain the compensation device topology network.

[0073] The specific configuration of the common mode division module 30 will be described in detail below. As described above, according to the electric power consumption data set, the compensation device topology network common mode division is performed to obtain the common mode division result. The common mode division module 30 may further include: a preprocessing unit for preprocessing the electric power consumption data set to obtain a standard electric power consumption data set; a common mode division unit for initializing the common mode division algorithm, and inputting the standard electric power consumption data set for common mode division to obtain a classified power consumption data set, wherein the classified power consumption data set includes a plurality of power consumption data groups; a common mode division class establishment unit for mapping and establishing a plurality of common mode division classes based on the association relationship between the plurality of power consumption data groups and the plurality of common mode division classes, and storing them as the common mode division result.

[0074] Among them, before performing common-mode division of the compensation device topology network according to the electric power consumption data set, the common-mode division module 30 may further include: a common-mode division key feature set acquisition unit for analyzing the electric power consumption data set to obtain the common-mode division key feature set; a reduction processing unit for performing reduction processing on the electric power consumption data set with the common-mode division key feature set.

[0075] Among them, the power consumption data set is analyzed to obtain the common mode partition key feature set, and the common mode partition key feature set acquisition unit may further include: a decentralization subunit is used to decentralize the power consumption data set based on the standardization principle; a standard data matrix construction subunit is used to construct a standard data matrix according to the decentralization result, with the number of data items in the power consumption data set as the number of rows of the matrix, and the number of power consumption data indicator classes in the power consumption data set as the number of columns of the matrix; a correlation matrix feature set acquisition subunit is used to establish the correlation matrix of the standard data matrix, calculate the characteristic roots and characteristic vectors of the correlation matrix, and obtain the correlation matrix feature set; a variance contribution cumulative sequence acquisition subunit is used to accumulate and obtain the variance contribution cumulative sequence according to the variance contribution scores of the correlation matrix feature set, wherein the variance contribution cumulative sequence includes multiple variance contribution cumulative scores, and the variance contribution cumulative scores have feature class tags; a screening subunit is used to screen the variance contribution cumulative scores according to the variance contribution cumulative sequence based on a preset contribution rate constraint, and extract the feature class tags of the screening results to generate the common mode partition key feature set.

[0076] The specific configuration of the collaborative controller construction module 40 will be described in detail below. As described above, a collaborative controller is constructed by using the power consumption data set and the common mode division result. The collaborative controller construction module 40 may further include: a random selection unit for randomly selecting from the common mode division result to obtain a first common mode division class; a first power consumption data group calling unit for calling the first power consumption data group based on the common mode division result according to the first common mode division class; a first collaborative control strategy acquisition unit for acquiring a first collaborative control strategy based on the first power consumption data group through a supervised training method; and a storage unit for storing the first collaborative control strategy in the collaborative controller.

[0077] The specific configuration of the collaborative control module 50 will be described in detail below. As described above, the collaborative control of multiple distributed power capacitor compensation devices is performed, and the collaborative control module 50 may further include: a real-time common state classification class determination unit is used to analyze the distributed power consumption data and determine the real-time common state classification class; a control matching unit is used to traverse the multiple collaborative control strategies in the collaborative controller for control matching according to the real-time common state classification class; a collaborative controller calling unit is used to activate and call the collaborative controller for control decision-making based on the control matching result; and a collaborative control unit is used in the compensation device topology network to send the control decision result to multiple distributed power capacitor compensation devices for collaborative control.

[0078] A collaborative control system of a distributed power capacitor compensation device provided in an embodiment of the present invention can execute a collaborative control method of a distributed power capacitor compensation device provided in any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

[0079] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0080] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A coordinated control method for a distributed power capacitor compensation device, characterized in that: The method comprises: Interact with the target power grid, obtain multiple distributed power capacitor compensation devices in the target control area, and build a compensation device topology network; Extract the power consumption dataset based on the historical power consumption records of the target control area; According to the electric power consumption data set, performing common-state division of the topological network of the compensation device to obtain a common-state division result, wherein the common-state division result includes a plurality of common-state division classes; Constructing a collaborative controller through the power consumption data set and the common state division result, wherein the collaborative controller includes a plurality of collaborative control strategies; Activate the compensation device topology network to collect distributed power consumption data of the target control area, input the data into the collaborative controller, and perform collaborative control of multiple distributed power capacitor compensation devices; Wherein, before performing the common-state division of the compensation device topology network according to the electric power consumption data set, it also includes: Analyze the electric power consumption data set to obtain a common-state partition key feature set; Dividing the key feature set by the common state, and performing reduction processing on the power consumption data set; The power consumption data set is analyzed to obtain a common-state partition key feature set, including: Based on the principle of standardization, the electric power consumption data set is decentralized; According to the decentralization result, a standard data matrix is ​​constructed with the number of data items in the electric power consumption data set as the number of rows of the matrix and the number of electricity consumption data indicator categories in the electric power consumption data set as the number of columns of the matrix; Establishing a correlation matrix of the standard data matrix, calculating the characteristic roots and eigenvectors of the correlation matrix, and obtaining a correlation matrix feature set; According to the variance contribution scores of the correlation matrix feature set, a variance contribution accumulation sequence is accumulated, wherein the variance contribution accumulation sequence includes a plurality of variance contribution accumulation scores, and the variance contribution accumulation scores have a feature class label; Based on a preset contribution rate constraint, the variance contribution cumulative score is screened according to the variance contribution cumulative sequence, and the feature class mark of the screening result is extracted to generate the common state partition key feature set; Among them, performing common-mode division of the topology network of the compensation device according to the electric power consumption data set and obtaining the common-mode division result includes: Preprocessing the electric power consumption data set to obtain a standard electric power consumption data set; Initializing a common-mode partitioning algorithm, and inputting the standard power consumption data set for common-mode partitioning to obtain a classified power consumption data set, wherein the classified power consumption data set includes a plurality of power consumption data groups; Based on the association relationship between the multiple electricity consumption data groups and the multiple common-mode division classes, multiple common-mode division classes are mapped and established, and stored as the common-mode division result. Specifically, the association relationship between each electricity consumption data group and the common-mode division class is analyzed to determine the category to which each electricity consumption data group belongs. Based on the association relationship analysis results, a mapping relationship between the electricity consumption data group and the common-mode division class is established, and the mapping relationship is stored as the common-mode division result.

2. A coordinated control method for a distributed power capacitor compensation device according to claim 1, characterized in that: Interact with the target power grid, obtain multiple distributed power capacitor compensation devices in the target control area, and build a compensation device topology network, including: Establish a communication connection with the target power grid and obtain the configuration file of the regional compensation device; Based on the regional compensation device configuration file, extract the location information, parameter information and status information of multiple distributed power capacitor compensation devices in the target control area, and store them as basic device information; Analyze and determine the connection relationship and communication mode of multiple distributed power capacitor compensation devices in the target control area, and build a compensation device network; The basic information of the device is updated to the compensation device network to obtain a compensation device topology network.

3. A coordinated control method for a distributed power capacitor compensation device according to claim 1, characterized in that: A collaborative controller is constructed by using the power consumption data set and the common state division result, including: Randomly select from the common-state partition results to obtain a first common-state partition class; According to the first common state classification class and based on the common state classification result, calling a first power consumption data group; Based on the first power consumption data group, obtaining a first collaborative control strategy through a supervised training method; The first collaborative control strategy is stored in the collaborative controller.

4. A coordinated control method for a distributed power capacitor compensation device according to claim 1, characterized in that: Coordinated control of multiple distributed power capacitor compensation devices, including: Analyze the distributed power consumption data to determine the real-time common state classification class; According to the real-time common state classification, traverse the multiple collaborative control strategies in the collaborative controller to perform control matching; Based on the control matching result, activating and calling the collaborative controller to make a control decision; The compensation device topology network sends the control decision result to multiple distributed power capacitor compensation devices for coordinated control.

5. A coordinated control system for a distributed power capacitor compensation device, characterized in that: The system is used to implement a coordinated control method for a distributed power capacitor compensation device according to any one of claims 1 to 4, and the system comprises: A compensation device topology network construction module, which is used to interact with the target power grid, obtain multiple distributed power capacitor compensation devices in the target control area, and construct a compensation device topology network; An electric power consumption data set extraction module, the electric power consumption data set extraction module is used to extract an electric power consumption data set based on the historical electricity consumption records of the target control area; A common state division module, the common state division module is used to perform common state division of the compensation device topology network according to the power consumption data set, and obtain a common state division result, wherein the common state division result includes a plurality of common state division classes; A collaborative controller construction module, the collaborative controller construction module is used to construct a collaborative controller through the power consumption data set and the common state division result, wherein the collaborative controller includes a plurality of collaborative control strategies; A collaborative control module is used to activate the compensation device topology network to collect distributed power consumption data in the target control area, input the data into the collaborative controller, and perform collaborative control of multiple distributed power capacitor compensation devices.

Images