A power quality partitioned treatment method based on time series and data driving

Abstract

The application discloses a power quality partition governance method based on time series and data driving, belongs to the technical field of power quality partition governance, and solves the problems of poor dynamicity and adaptability and low calculation efficiency in the existing power quality governance process. The method comprises the following steps: collecting voltage data of multiple sampling points of each node of a power grid in succession and processing the voltage data, so that the power quality time series of each node is obtained; obtaining the behavior similarity distance between different nodes according to the power quality time series of each node; calculating the comprehensive coupling degree between corresponding nodes according to the behavior similarity distance between different nodes; dividing the power grid into regions according to the comprehensive coupling degree between different nodes; and performing the cooperative governance of the corresponding power grid region based on the leading node of each power grid region.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power quality zoned governance, and particularly relates to a power quality zoned governance method based on time series and data driving. BACKGROUND

[0002] With the rapid development of power systems, power quality problems have increasingly become an important factor affecting the stability of power systems, the safe operation of equipment, and the efficiency of industrial production. Whether the power quality is good or not directly relates to the stability of the power grid, the safe operation of equipment, and the efficiency of production. Power quality disturbances are usually manifested as voltage deviation, frequency fluctuation, harmonic pollution, and flicker, which can cause equipment failure, electrical equipment damage, and production efficiency decline, and even can cause large-scale power system failure.

[0003] Currently, the main governance methods for power quality are local governance, global governance, and zoned governance. Local governance handles local power quality problems by installing compensation devices, filters, and other equipment at key nodes of the power system. However, this method is limited to a specific area and cannot cope with the propagation effect of power quality pollution in the power grid. Global governance optimizes the power quality of each node in the power grid through overall modeling, but due to the large scale of the power grid and the complexity of power quality pollution factors, the governance process has a large amount of calculation, and there is a problem of poor timeliness in dealing with dynamic power quality problems.

[0004] Zoned governance is a governance method based on the coupling relationship of power quality at nodes of the power grid. The idea is to divide the power grid into several governance areas, and the nodes within each area have a strong coupling degree, while the coupling degree between different areas is low. Zoned governance can use targeted governance strategies according to the specific power quality situation of different areas. However, existing power quality zoned governance methods rely mainly on electrical distance or static power grid models and do not effectively consider the dynamic changes and propagation characteristics of power quality disturbances. Traditional methods rely on manually designed features and rules for spatiotemporal feature analysis of power quality, lack dynamic optimization strategies based on data driving, and cannot adapt to real-time changes in power quality problems.

[0005] In recent years, with the continuous development of big data and artificial intelligence technology, data-driven power quality governance methods have received widespread attention. By collecting and analyzing real-time power quality data at grid nodes, the time-domain characteristics, frequency-domain characteristics, and spatial distribution patterns of power quality disturbances can be accurately identified, enabling dynamic monitoring and optimization of power quality. Based on machine learning, deep learning, and other data mining techniques, many data-driven power quality zoning governance methods have been proposed, which can divide regions and make intelligent decisions based on real-time data, improving the efficiency and accuracy of power quality governance. However, existing technologies still face some challenges, such as the need for large amounts of labeled data for training, difficulty in feature selection, and complex model training, which limit their application in power grid. SUMMARY

[0006] In view of the above analysis, the embodiments of the present application aim to provide a power quality zoning governance method based on time series and data driving, to solve the problems of poor dynamicity and adaptability, and low computational efficiency in the existing power quality governance process.

[0007] The present application discloses a power quality zoning governance method based on time series and data driving, the method comprising:

[0008] Collecting and processing voltage data of multiple consecutive sampling points at each node of the power grid to obtain power quality time series of each node;

[0009] Obtaining the behavior similarity distance between different nodes according to the power quality time series of each node;

[0010] Calculating the comprehensive coupling degree between corresponding nodes according to the behavior similarity distance between different nodes, and dividing the power grid into regions according to the comprehensive coupling degree between different nodes;

[0011] Performing collaborative governance of each power grid region based on the dominant node of each power grid region.

[0012] Based on the above scheme, the present application further improves as follows:

[0013] Further, the comprehensive coupling degree between nodes and is represented as:

[0014] (1)

[0015] wherein, represents the behavior similarity distance between nodes and , represents the comprehensive coupling degree between nodes​ and the physical electrical distance between nodes , represent the importance weight of node , respectively. , is a scale parameter for adjusting the contribution of different factors.

[0016] Further, according to the comprehensive coupling degree between different nodes, the power grid is divided into regions, and the following operations are performed:

[0017] According to the comprehensive coupling degree between each two nodes in the power grid, a comprehensive coupling degree matrix of all nodes in the power grid is constructed; the comprehensive coupling degree matrix is taken as the adjacency matrix of a graph;

[0018] According to the adjacency matrix, a Laplacian matrix is calculated;

[0019] The Laplacian matrix is subjected to eigenvalue decomposition to construct a new feature space;

[0020] In the new feature space, a K-means clustering algorithm is applied to cluster the nodes in the power grid, so as to realize the regional division of the power grid.

[0021] Further, the power quality time series of each node is obtained by performing the following operations:

[0022] The voltage data of each node at a plurality of consecutive sampling points are collected by a power grid monitoring system to form the original voltage waveform data of the corresponding node;

[0023] According to the original voltage waveform data of each node, a plurality of power quality indexes of the corresponding node are calculated, including voltage deviation, harmonic voltage content rate and three-phase imbalance;

[0024] Each item of power quality index of each node is subjected to standardization processing respectively, and is arranged in sequence according to the sampling point order to construct the power quality subsequence of the corresponding power quality index.

[0025] Further, the behavior similarity distance between different nodes is obtained by performing the following operations:

[0026] Each item of power quality subsequence of each node is subjected to piecewise linear representation and linear regression fitting to obtain a plurality of piecewise time subsequences of the corresponding power quality subsequence;

[0027] For each item of power quality subsequence, time series pattern matching is performed on the piecewise time subsequences between different nodes to obtain the behavior similarity distance between different nodes.

[0028] Further, the node and behavior similarity distance between is expressed as:

[0029] (2)

[0030] wherein, , , respectively represent the DTW distance of the power quality time sub-sequence of voltage deviation index, harmonic content index, three-phase imbalance index between nodes and .

[0031] Further, the matching distance of the segmented time sub-sequence and of the same item of power quality time sub-sequence at index , at index , at index is expressed as:

[0032] (3)

[0033] wherein, represents the cumulative matching distance between the first data points of and the first data points of , is the weighted distance between the data of at index and the data of at index ; represents the time weight factor of at index , represents the time weight factor of at index ;

[0034] Assuming the lengths of the segmented time sub-sequences , are , , respectively, the matching distance between the segmented time sub-sequences , is represented as:

[0035] The matching distances between all segmented time sub-sequences of different nodes in the same item of power quality time sub-sequence are summed up to obtain the DTW distance between the corresponding nodes in the same item of power quality time sub-sequence.

[0036] Further, the weighted distance is represented as:

[0037] (4)

[0038] wherein, denotes the data of the segmented time subsequence of the node at index . denotes the data of the segmented time subsequence of the node at index .

[0039] Further, the collaborative governance of the corresponding power grid partition is performed by:

[0040] For each power grid partition, the various power quality indicators of the dominant node are monitored in real time, and if the triggering condition of the corresponding power quality indicator is met, the collaborative action instruction of the corresponding power quality indicator dimension is triggered in the corresponding power grid partition;

[0041] The power quality governance device of the corresponding power quality indicator dimension in the corresponding power grid partition performs power quality governance according to the corresponding collaborative action instruction, thereby realizing the collaborative governance of the corresponding power grid partition.

[0042] Further, the node with the maximum average value of the comprehensive coupling degree with all other nodes in each power grid partition is selected as the dominant node.

[0043] Compared with the prior art, the present application can at least achieve one of the following beneficial effects:

[0044] In view of the existing research problems, the present application proposes a power quality partition governance method based on time series and data driving. The method combines time series analysis, similarity analysis and clustering algorithm, accurately extracts the time-frequency features and spatial features of power quality by monitoring the power quality data of each node in the power grid in real time, and realizes accurate partitioning of the power grid based on the coupling degree between nodes. The node with the maximum coupling degree is selected as the dominant control node in each region, and finally an intelligent system is formed which can dynamically adjust the governance region and optimize the strategy according to the real-time monitoring data. Through the data-driven modeling method, the present application can dynamically adjust the governance region and optimize the governance strategy, effectively cope with the complexity and variability of power quality disturbances in the power grid, thereby improving the stability and power supply quality of the power grid, and solving the problems of poor dynamicity and adaptability, low calculation efficiency in the existing power quality governance process.

[0045] The present application relates to power quality governance technology, especially a power quality partition governance strategy combining data driving and time sequence pattern recognition. The technology realizes regional governance of power quality pollution through data-driven modeling method, combined with time sequence analysis and self-supervised learning, especially for power quality problems caused by high permeability distributed photovoltaic access and power electronic load. First, based on power quality monitoring data of each node of the distribution network, time sequence feature extraction and pattern recognition technology is used to analyze power quality time sequence and extract local trend features and time features. Then, through similarity analysis and clustering algorithm, the coupling relationship of power quality pollution between nodes is identified, and the power quality governance area is divided according to the coupling degree. Then, according to the area division, the dominant control node of each area is determined, and targeted governance measures such as passive filter, capacitor and other devices are implemented. Through these methods, the present application can effectively realize the collaborative governance of power quality pollution and ensure the stability and high-quality power supply of the power system.

[0046] In the present application, the above technical solutions can be combined with each other to realize more preferred combination solutions. Other features and advantages of the present application will be described in the subsequent specification, and some advantages will become apparent from the specification or by implementing the present application. The purpose and other advantages of the present application can be achieved and obtained from the contents specifically pointed out in the specification and the drawings. BRIEF DESCRIPTION OF DRAWINGS

[0047] The accompanying drawings are included to provide a further understanding of the present application and are incorporated in and constitute a part of this specification, illustrate embodiments of the present application and serve to explain the principles of the present application, but are not intended to limit the scope of the present application.

[0048] Figure 1 A flowchart of the power quality partition governance method based on time sequence and data driving provided by the embodiment of the present application is shown. DETAILED DESCRIPTION

[0049] The preferred embodiments of the present application will be specifically described below in conjunction with the drawings, wherein the drawings constitute a part of this application and are used to illustrate the principles of the embodiments of the present application, but are not intended to limit the scope of the present application.

[0050] One specific embodiment of the present application discloses a power quality partition governance method based on time sequence and data driving, and a flowchart is shown as Figure 1

[0051] Step S1: Collect voltage data of each node of the power grid at a plurality of sampling points respectively and process to obtain power quality time sequence of each node.

[0052] The power quality time sequence constructed in this embodiment includes a plurality of power quality time sub-sequences, and the specific implementation process is described as follows.​

[0053] Step S11: Collecting voltage data of each node of the power grid at multiple sampling points using a power grid monitoring system to form raw voltage waveform data of the corresponding node.

[0054] In the implementation process, the obtained raw voltage waveform data can be preprocessed to ensure data integrity and accuracy. For example, Kalman filtering algorithm can be used to remove noise in the voltage data. Kalman filtering algorithm can dynamically adjust filtering parameters according to noise characteristics, accurately remove measurement errors or abnormal fluctuations caused by environmental factors, adapt to different noise environments, and improve the filtering accuracy of subsequent calculations. If there are missing data in the collected voltage data, a generative adversarial network (GANs) can be used to generate high-quality filling data, better preserving the regularity and complex relationship of the voltage data, ensuring data integrity and laying a foundation for accurate calculation of subsequent power quality indicators. In addition, for periodic fluctuations, wavelet packet transform (WPT) is used to provide higher time-frequency resolution than Fourier transform, effectively separating high-frequency noise and low-frequency trends, and improving data quality and accuracy of subsequent analysis.

[0055] Step S12: Calculating multiple power quality indicators of each node according to the raw voltage waveform data of each node, including voltage deviation, harmonic voltage content rate, and three-phase imbalance.

[0056] Voltage deviation defined as the deviation of the measured voltage from the system nominal voltage, and the calculation formula is:

[0057] (1)

[0058] wherein, is the measured voltage, is the system nominal voltage.

[0059] Harmonic voltage content rate defined as the ratio of the effective value of harmonic voltage to the effective value of fundamental voltage, reflecting the distortion degree of voltage waveform, and the calculation formula is:

[0060] (2)

[0061] wherein, is the effective value of the fundamental voltage, is the effective value of the th harmonic voltage, is the highest harmonic number calculated; in the implementation process, Fourier transform of the raw voltage waveform data can be performed to obtain , and .

[0062] Three-phase voltage imbalance The degree of three-phase voltage amplitude or phase asymmetry is defined, usually represented by the ratio of negative sequence component to positive sequence component, and the calculation formula is:

[0063] (3)

[0064] wherein, is the positive sequence voltage component, is the negative sequence voltage component. In the specific implementation process, Fourier transform and sequence component extraction are performed on the original voltage waveform data, so that and are obtained. Among them, the positive sequence voltage component refers to the component in the three-phase voltage which is symmetrical and the phase difference is 120° in turn, and is usually used to describe the balanced three-phase system. The negative sequence voltage component refers to the component in the three-phase voltage which is symmetrical and the phase difference is-120° in turn, and is usually used to describe the unbalanced three-phase system.

[0065] Step S13: respectively standardizing each item of power quality index of each node, and arranging in turn according to the sampling point sequence, to build the power quality subsequence of the corresponding power quality index.

[0066] In the specific implementation process, the following standardization formula can be used:

[0067] (4)

[0068] wherein, is an item of power quality index of node , , respectively represent the minimum value and the maximum value of all nodes in the corresponding power quality index. Through this process, the power quality data can be normalized to the interval [-1, 1], to ensure the stability of the subsequent data analysis process.

[0069] Based on the above description, it can be known that the power quality time sequence constructed by the embodiment specifically includes the voltage deviation subsequence, the harmonic voltage content rate subsequence and the three-phase imbalance subsequence.

[0070] Step S2: obtaining the behavior similarity distance between different nodes according to the power quality time sequence of each node.

[0071] Step S21: respectively performing piecewise linear representation and linear regression fitting on each item of power quality subsequence of each node, to obtain a plurality of segmented time subsequences of the corresponding power quality subsequence.

[0072] Specifically, the local trend feature of each power quality time sub-sequence is extracted by piecewise linear representation (PLR). Each power quality sub-sequence is divided into multiple time periods, and each time period is fitted by linear regression method, so as to extract the local trend feature of the time sequence. This process helps to reduce the redundant data in the original time sequence and can highlight the key trend of power quality change.

[0073] Step S22: For each power quality sub-sequence, time series pattern matching is performed on the segmented time sub-sequences between different nodes to obtain the behavior similarity distance between different nodes.

[0074] In the traditional DTW algorithm, the matching distance of the time series is usually equal, but in the power quality time sequence, the time points of voltage sag, flicker and other dramatic changes carry more information than the smooth period. The introduction of the weight factor combined with the change amplitude and trend strength of the time series can improve the matching accuracy of the key moment.

[0075] For any segmented time sub-sequence of node , the time weight factor at index can be defined as:

[0076] (5)

[0077] wherein, , are adjustment coefficients; denotes the data of the segmented time sub-sequence of node at index ; , respectively denote the maximum value and the minimum value in the segmented time sub-sequence; denotes the second-order difference of , which represents the trend change strength; denotes the maximum value of the second-order difference of all data in the segmented time sub-sequence.

[0078] In the specific real-time process, formula (5) is used for the importance of any segmented time sub-sequence at a specific index, exemplarily, , respectively take 0.7 and 0.3.

[0079] (6)

[0080] Based on the DTW algorithm, the segmented time sub-sequences (the segmented time corresponds to the same observation time period) of nodes and in the same power quality time sub-sequence can be calculated In the index Place, In the index Matching distance at time Represented as:

[0081] (7)

[0082] in, express The former Data points and The former The cumulative matching distance between data points yes In the index Data at the location and In the index Weighted distance between data points; express In the index The time weighting factor at that point express In the index The time weighting factors at each point can be calculated based on formula (5).

[0083] The DTW algorithm allows indexing and The values ​​are not equal to handle minor time delays that may exist between different nodes. Weighted distance. Represented as:

[0084] (8)

[0085] This algorithm uses dynamic programming to minimize the total distance of the matching paths, thus obtaining the optimal time series alignment. Assume segmented time subsequences... , The lengths are respectively , The length of a subsequence refers to the cumulative distance from the beginning of the sequence to the current index. Represents piecewise time subsequences , The matching distance between nodes reflects the matching distance between nodes. and The degree of similarity between the power quality behaviors of the two in a certain dimension.

[0086] The matching distances between different nodes in the same power quality time series are summed to obtain the DTW distance between the corresponding nodes in the same power quality time series, which reflects the node's DTW distance. and the similarity degree of the power quality behavior of a certain dimension between nodes.

[0087] The DTW distances of each power quality sub-sequence between nodes are weighted and fused to obtain the behavior similarity distance between the corresponding nodes.

[0088] Node and the behavior similarity distance is expressed as:

[0089] (9)

[0090] wherein, , , respectively represent the DTW distance of the power quality time sub-sequence of the voltage deviation index, the harmonic content index, and the three-phase imbalance index between nodes and .

[0091] , , respectively represent the global importance weight of the voltage deviation index, the harmonic content index, and the three-phase imbalance index, , , and the sum of

[0092] Step S3: According to the behavior similarity distance between different nodes, the comprehensive coupling degree between the corresponding nodes is calculated; and according to the comprehensive coupling degree between different nodes, the power grid is regionally divided.

[0093] The embodiment is based on node coupling degree to divide the power grid. Therefore, it is necessary to first calculate a coupling degree index that can comprehensively reflect the strength of the association between nodes.

[0094] First, the importance weight of each node is calculated. The weight factor of node is expressed as:

[0095] (10)

[0096] wherein, represents the power quality comprehensive fluctuation rate of node , , , , respectively represent the standard deviation of voltage deviation, harmonic voltage content rate, and three-phase imbalance; is a smoothing coefficient to avoid zero denominator, and the value is 0.01 here; denotes the total number of nodes in the power grid.

[0097] node and comprehensive coupling degree is represented as:

[0098] (11)

[0099] wherein, denotes the physical electrical distance (the shortest electrical distance calculated by Dijkstra algorithm ) between node and ; , denote the importance weight of node , respectively; , is a scale parameter for adjusting the contribution of different factors. The higher the value of the comprehensive coupling degree, the closer the association between the two nodes, and the more they should be divided into the same region.

[0100] According to the comprehensive coupling degree between each pair of nodes in the power grid, a comprehensive coupling degree matrix of all nodes in the power grid is constructed; based on the comprehensive coupling degree matrix, a clustering algorithm is used to divide the power grid into regions. Preferably, the spectral clustering (Spectral Clustering) algorithm is used to realize the regional division in this embodiment, which can effectively process the graph partitioning problem based on the similarity (coupling degree) between nodes. This algorithm can abstract all nodes and their coupling relationships in the power grid into a weighted undirected graph, and realize the optimal partitioning through the following specific steps.

[0101] Step S31: Take the comprehensive coupling degree matrix as the adjacency matrix of the graph, and the matrix element denotes the comprehensive coupling degree of the power grid node and node , that is, the weight of the edge. The higher the weight, the closer the association between the two nodes in the power quality behavior.

[0102] Step S32: According to the adjacency matrix , calculate the Laplacian matrix.

[0103] Specifically, according to the adjacency matrix , a diagonal matrix is constructed, and the element on the diagonal line is the sum of all elements in the first row of the adjacency matrix , that is, , which physically represents node The total coupling strength with all other nodes in the network.

[0104] Subsequently, the Laplace matrix is ​​calculated. Its definition is The Laplace matrix contains information about the structure and connectivity of a graph and is the core of spectral analysis.

[0105] Step S33: Perform eigenvalue decomposition on the Laplacian matrix to construct a new feature space.

[0106] The Laplacian matrix is ​​obtained by performing eigenvalue decomposition. The former The smallest eigenvalues ​​and their corresponding eigenvectors ,in, It is a pre-defined number of areas into which the power grid is to be divided.

[0107] This By combining the feature vectors column-wise, a new feature vector is obtained. 3D feature matrix .

[0108] Feature matrix The A line is a A dimensional vector, considered as a power grid node. Coordinate representation in a new, low-dimensional feature space. This process achieves dimensionality reduction of node relationships by preserving the most essential structural information of the graph. The feature matrix... of indivual The dimensional vector serves as a new feature space.

[0109] Step S34: Apply the K-means clustering algorithm in the new feature space to cluster the nodes in the power grid and realize the regional division of the power grid.

[0110] Specifically, the feature matrix of line (i.e.) indivual Using a 3D vector as input, the standard K-means clustering algorithm is applied to divide it into 3D vectors. Each cluster is a set of several nodes, forming a power grid partition, thus realizing the regional division of the power grid, that is, constituting a power quality management partition.

[0111] Through the above steps, this invention transforms the complex graph segmentation problem based on coupling degree into a clustering problem that is easier to handle in low-dimensional Euclidean space, thereby enabling the automatic division of the power grid into... An internal node is strongly coupled, and the regional power quality management partition is weakly coupled.

[0112] Step S4: Based on the dominant node of each power grid partition, the corresponding power grid partition is cooperatively managed.

[0113] After completing the power grid area division, in order to achieve efficient cooperative management of each power grid partition, a dominant node needs to be determined for each power grid partition, which is the core of solving the power quality problem of the corresponding power grid partition.

[0114] Specifically, the node with the maximum average value of the comprehensive coupling degree with all other nodes in each power grid partition is determined as the dominant node, and the formula is described as follows. For the first power grid partition, the dominant node is determined by the following formula :

[0115] (12)

[0116] wherein represents the number of nodes in the first power grid partition set . The formula calculates the comprehensive coupling degree of each node in the first power grid partition to all other nodes in the region, and selects the node with the maximum average value of the comprehensive coupling degree as the dominant node of the corresponding power grid partition.

[0117] The dominant node is the "core" or "propagation source" of the power quality problem in the region, and it is most closely related to other nodes in the region. Therefore, the effect of managing the dominant node can be most effectively transmitted and radiated to other nodes in the entire region.

[0118] Preferably, in this embodiment, a set of cooperative management strategies is established and implemented for each power grid partition, which converts static analysis results into dynamic control practices. By defining clear control logic for each region in advance, precise response to power quality problems is achieved, and the specific implementation process is described as follows.

[0119] Step S41: For each power grid partition, real-time monitoring of various power quality indicators of the dominant node is performed, and if the trigger condition of the corresponding power quality indicator is met, the cooperative action instruction of the corresponding power quality indicator dimension is triggered in the corresponding power grid partition.

[0120] In the specific implementation process, a regional status monitoring and triggering mechanism is first established, with the leading nodes of each power grid sub-region serving as the core monitoring points and status representatives of the corresponding power quality status. The monitoring system continuously collects and analyzes various power quality indicators of the leading nodes, including voltage deviation, at a preset sampling period not exceeding 200ms. Harmonic voltage content Three-phase voltage imbalance .

[0121] A collaborative governance rule base containing multi-level response rules is constructed for each power grid region. This rule base takes real-time monitoring data from the leading node as input and automatically determines whether regional collaborative governance needs to be initiated based on preset thresholds that comply with the State Grid's safe operation guidelines. The rule base includes specific control procedures for different power quality disturbances, ensuring the accuracy and reliability of control. This embodiment also provides an example of a collaborative rule base, detailed below.

[0122] (1) Regarding the voltage over-limit problem, the rule base includes voltage collaborative compensation rules, and the trigger condition is set as follows: if a voltage deviation of the dominant node is detected. The amplitude is greater than the voltage control upper limit threshold set at 7%. Or below the voltage control lower limit threshold set at -7%. Furthermore, this state lasts for more than the preset duration of 2 seconds. When this happens, a collaborative compensation action is triggered.

[0123] (2) Regarding the harmonic pollution problem, the rule base includes harmonic collaborative suppression rules, the trigger condition of which is set as follows: if the harmonic voltage content of the dominant node is detected. Greater than the set harmonic control threshold of 5% When this happens, the collaborative filtering action is triggered.

[0124] (3) In response to the three-phase imbalance problem, the rule base also includes imbalance collaborative governance rules, the trigger condition of which is set as follows: if a three-phase voltage imbalance is detected at the dominant node. Greater than the set imbalance control threshold of 2% When this happens, an imbalance compensation action is triggered.

[0125] When any rule in the rule base is triggered, the system will generate a clear control objective and issue a unified coordinated action command to all relevant controllable governance devices within the area corresponding to that rule. The control objective is to restore the corresponding power quality indicators of the leading node that triggered the problem to within a safe threshold. Specifically, this means... To recover to below 5%, or To recover to below 4%, or Restored to within 1.5%.

[0126] Step S42: The power quality management equipment of the corresponding power quality index dimension in the corresponding power grid partition executes power quality management according to the corresponding cooperative action instruction, to realize cooperative management of the corresponding power grid partition.

[0127] Specifically, the cooperative action instruction can be distinguished according to the triggered rule type. If it is voltage out-of-limit, cooperative compensation instructions are issued to all reactive power compensation equipment in the region, such as static reactive power compensator STATCOM, to compensate the reactive power in the power system, improve the power factor, and reduce the grid loss. If it is harmonic over-limit, cooperative filtering instructions are issued to all active power filters APF in the region to dynamically compensate harmonic current, improve power quality, and reduce harmonic pollution. If it is three-phase imbalance over-limit, cooperative instructions for injecting negative sequence compensation current are issued to the management equipment with independent phase control capability in the region to adjust the phase of voltage and current through phase control, for solving voltage imbalance, flicker and other problems.

[0128] Through the above process, the complex analysis results in the early stage are converted into a set of clear, automated, and capable of coping with multiple disturbance scenarios control logic, which provides a clear basis for subsequent device deployment and adjustment.

[0129] In the specific implementation process, the present embodiment can also select and deploy devices according to the management task. When any of the above management rules is triggered, the system determines the type of device that needs to be started or deployed in the corresponding power grid partition according to the type of the triggered rule. The deployment logic follows the following hierarchical decision principle to ensure the targeted deployment of management resources:

[0130] (13)

[0131] wherein, represents the type of device deployed or started in the power grid partition , , , the maximum harmonic content rate, the maximum voltage deviation and the maximum three-phase imbalance degree monitored in the region respectively, , , are the corresponding management thresholds, consistent with the triggering threshold in step S4. The above formula defines which type of management resource should be mobilized first when a specific power quality problem occurs.

[0132] The power quality treatment device can perform a dynamic closed-loop feedback adjustment process in the process of performing power quality treatment according to the corresponding cooperative action instruction. The compensation rate or output power of the deployed or started power quality treatment device is not fixed, but is adjusted in real time according to the treatment effect. The closed-loop feedback adjustment process includes the following operations: the power quality treatment device starts to execute the cooperative action instruction; at the same time, the system continuously monitors the change of the corresponding power quality index of the leading node at a higher frequency not higher than 50 ms. The system dynamically adjusts the compensation rate of all cooperative action devices in the region through a proportional-integral (PI) controller according to the error between the real-time monitoring value of the leading node index and the set control target . The calculation formula of the compensation rate can be expressed as:

[0133] (14)

[0134] wherein, is the compensation rate instruction issued to the power quality treatment device, is the real-time error between the monitoring value and the target value, and are the proportional and integral coefficients of the PI controller. The closed-loop adjustment process continues until the power quality index of the leading node is stabilized in the preset safe range, the cooperative treatment process is ended, and the system returns to the normal monitoring state. Based on the above operations, the power quality treatment devices in each region can be specifically deployed and closed-loop adjusted to ensure the rapidity and stability of the treatment effect.

[0135] In summary, the present application has the following effects:

[0136] (1) The present application can effectively identify the space-time characteristics of power quality disturbances without a large amount of prior knowledge by introducing a data-driven modeling method combined with time series analysis and pattern recognition technology, and can provide accurate basis for the formulation of power quality treatment strategies.

[0137] (2) The clustering algorithm and node coupling degree analysis method used in the present application can accurately divide the treatment regions in the power grid, ensure that the node power quality characteristics in each region are highly consistent, and effectively reduce the redundant adjustment in cross-region treatment, thereby improving the treatment efficiency.

[0138] (3) The present application introduces the leading node of each power grid partition and performs cooperative treatment of the corresponding power grid partition accordingly, ensuring that the treatment measures can quickly adapt and automatically adjust in the dynamic environment of power grid power quality change, thereby improving the flexibility and real-time performance of the treatment.

[0139] Those skilled in the art can understand that all or part of the processes of the above-mentioned embodiment methods can be completed by instructing the relevant hardware by a computer program, and the program can be stored in a computer readable storage medium. The computer readable storage medium is a disk, an optical disk, a read-only memory, a random access memory, etc.

[0140] The above description is merely preferred specific embodiments of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical scope disclosed by the present application, which should be covered within the protection scope of the present application.

Claims

1. A power quality zoning management method based on time series and data-driven approaches, characterized in that, The method includes: Voltage data from multiple consecutive sampling points at each node of the power grid are collected and processed to obtain the power quality time series of each node; the power quality time series includes power quality time subsequences of voltage deviation index, harmonic content index, and three-phase imbalance index; Based on the power quality time series of each node, the behavioral similarity distance between different nodes is obtained; Calculate the comprehensive coupling degree between corresponding nodes based on the behavioral similarity distance between different nodes; and divide the power grid into regions based on the comprehensive coupling degree between different nodes. Collaborative governance of each power grid partition is carried out based on the dominant node of each power grid partition. node and Overall coupling degree between Represented as: (1) in, Represents a node and Behavioral similarity distance between them Represents a node and The physical electrical distance between them; , Representing nodes respectively , Importance weights; , This is a scaling parameter used to adjust the contribution of different factors; The behavioral similarity distance between different nodes can be obtained by performing the following operations: Piecewise linear representation and linear regression fitting are performed on each power quality subsequence of each node to obtain multiple piecewise time subsequences of the corresponding power quality subsequence; For each power quality subsequence, time series pattern matching is performed on the segmented time subsequences between different nodes to obtain the behavioral similarity distance between different nodes. node and Behavioral similarity distance between Represented as: (2) in, , , Representing nodes respectively and The DTW distance between the power quality time series in terms of voltage deviation index, harmonic content index, and three-phase imbalance index; , , These represent the global importance weights of the voltage deviation index, harmonic content index, and three-phase imbalance index, respectively. , , The sum of is 1.

2. The power quality zoning management method based on time series and data-driven approach according to claim 1, characterized in that, Based on the overall coupling degree between different nodes, the power grid is divided into regions, and the following steps are performed: Based on the comprehensive coupling degree between each pair of nodes in the power grid, construct the comprehensive coupling degree matrix of all nodes in the power grid; Use the overall coupling degree matrix as the adjacency matrix of the graph; Calculate the Laplace matrix based on the adjacency matrix; Perform eigenvalue decomposition on the Laplacian matrix to construct a new feature space; The K-means clustering algorithm is applied in the new feature space to cluster the nodes in the power grid, thereby realizing the regional division of the power grid.

3. The power quality zoning management method based on time series and data-driven approaches according to claim 1 or 2, characterized in that, The power quality time series of each node is obtained by performing the following operations: Using a power grid monitoring system, voltage data from multiple consecutive sampling points at each node of the power grid are collected to form the raw voltage waveform data of the corresponding node. Based on the original voltage waveform data of each node, calculate a number of power quality indicators for the corresponding node, including: voltage deviation, harmonic voltage content and three-phase imbalance. Each power quality index of each node is standardized and arranged in the order of sampling points to construct a power quality subsequence of the corresponding power quality index.

4. The power quality zoning management method based on time series and data-driven approach according to claim 3, characterized in that, node and Piecewise time subsequences in the same power quality time subsequence In the index Place, In the index Matching distance at time Represented as: (3) in, express The former Data points and The former The cumulative matching distance between data points yes In the index Data at the location and In the index Weighted distance between data points; express In the index The time weighting factor at that point express In the index The time weighting factor at the location; Assuming piecewise time subsequences , The lengths are respectively , , Represents piecewise time subsequences , The matching distance between them; The matching distances between different nodes in the same power quality time subsequence are summed to obtain the DTW distance between the corresponding nodes in the same power quality time subsequence.

5. The power quality zoning management method based on time series and data-driven approach according to claim 4, characterized in that, Weighted distance Represented as: (4) in, Represents a node The segmented time subsequence in the index Data at the location, Represents a node The segmented time subsequence in the index Data from [location].

6. The power quality zoning management method based on time series and data-driven approach according to claim 3, characterized in that, The following steps are used to achieve coordinated governance of the corresponding power grid zones: For each power grid partition, the power quality indicators of the dominant node are monitored in real time. If the triggering conditions of the corresponding power quality indicator are met, the corresponding power quality indicator dimension of the corresponding power grid partition is triggered to trigger the coordinated action command. Power quality management equipment for the corresponding power quality indicators within the corresponding power grid zone executes power quality management according to the corresponding coordinated action instructions, thereby achieving coordinated management of the corresponding power grid zone.

7. The power quality zoning management method based on time series and data-driven approach according to claim 6, characterized in that, Within each power grid section, the node with the highest average overall coupling degree with all other nodes is designated as the dominant node.

Images