Phase-change switch control method and device based on graph neural network, equipment and medium

Abstract

The embodiment of the invention discloses a phase-change switch control method and device based on a graph neural network, equipment and a medium. The method comprises the following steps: acquiring state data and equipment connection relationships of each piece of power equipment in a power system; determining graph structure data according to the state data and the equipment connection relationship; determining three-phase unbalanced working condition information and an equipment detection report based on the graph structure data and a graph neural network model; and determining a phase-change switch control strategy according to the equipment detection report, and controlling a phase-change switch based on the phase-change switch control strategy so as to adjust three-phase load balance. According to the technical scheme, the three-phase imbalance problem of each node in the power grid is accurately identified by using the graph structure data processing capability of the graph neural network, the influence of imbalance on the power grid is effectively reduced through the rapid action of the phase-change switch, and the fault processing capability and the operation stability of the power grid are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the field of power control management technology, and in particular to a phase-changing switch control method, device, equipment and medium based on a graph neural network. Background Art

[0002] In the power system, three-phase imbalance is a common problem. Due to factors such as users' electricity consumption characteristics and large load changes, distribution transformers often experience three-phase load imbalance during operation. This imbalance will not only affect the life of the transformer and increase the loss of the transformer, but also lead to a series of problems such as grid voltage drop, flicker, low power factor, and increased line loss. Therefore, solving the three-phase imbalance problem is of great significance to ensuring the safe and stable operation of the power system. Graph neural network is a neural network that specializes in processing graph structure data. It can capture complex relationships and information in the graph structure. In the control and management of phase-changing switches under three-phase unbalanced conditions, graph neural networks can use their powerful data processing capabilities and real-time response capabilities to ensure that the system can respond to changes in three-phase loads in real time.

[0003] In the prior art, under three-phase unbalanced conditions, it is necessary to respond quickly and adjust the state of the phase-changing switch to restore the three-phase balance. However, due to the limitation of the equipment response speed, the actual response speed is difficult to meet the needs of rapid changes in the power grid, and it is difficult to quickly locate abnormal behaviors under three-phase unbalanced conditions, thereby reducing the response efficiency of the system. Summary of the invention

[0004] The present invention provides a phase-changing switch control method, device, equipment and medium based on a graph neural network. By utilizing the graph structure data processing capability of the graph neural network, the three-phase imbalance problem of each node in the power grid can be accurately identified, and the impact of the imbalance on the power grid can be effectively reduced through the rapid action of the phase-changing switch, thereby significantly improving the fault handling capability and operation stability of the power grid.

[0005] According to one aspect of the present invention, a commutation switch control method based on a graph neural network is provided, comprising:

[0006] Obtain status data and equipment connection relationships of each power device in the power system;

[0007] Determine graph structure data according to the state data and the device connection relationship;

[0008] Determine three-phase unbalanced operating condition information and equipment detection report based on the graph structure data and the graph neural network model;

[0009] A phase-changing switch control strategy is determined according to the device detection report, and the phase-changing switch is controlled based on the phase-changing switch control strategy to adjust the three-phase load balance.

[0010] According to another aspect of the present invention, a phase-changing switch control device based on a graph neural network is provided, comprising:

[0011] A data acquisition module is used to obtain the status data and device connection relationship of each power device in the power system;

[0012] A graph structure data determination module, used to determine graph structure data according to the state data and the device connection relationship;

[0013] A working condition information determination module, used to determine three-phase unbalanced working condition information and equipment detection report based on the graph structure data and the graph neural network model;

[0014] The phase-changing switch control module is used to determine the phase-changing switch control strategy according to the equipment detection report, and control the phase-changing switch based on the phase-changing switch control strategy to adjust the three-phase load balance.

[0015] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0016] at least one processor; and

[0017] a memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the phase-changing switch control method based on graph neural network described in any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the phase-changing switch control method based on graph neural network described in any embodiment of the present invention when executed.

[0020] The technical solution of the embodiment of the present invention obtains the status data and device connection relationship of each power device in the power system; determines the graph structure data according to the status data and the device connection relationship; determines the three-phase unbalanced working condition information and the equipment detection report based on the graph structure data and the graph neural network model; determines the phase-changing switch control strategy according to the equipment detection report, and controls the phase-changing switch based on the phase-changing switch control strategy to adjust the three-phase load balance. This technical solution, by utilizing the graph structure data processing capability of the graph neural network, accurately identifies the three-phase imbalance problem of each node in the power grid, effectively reduces the impact of imbalance on the power grid through the rapid action of the phase-changing switch, and significantly improves the fault handling capability and operation stability of the power grid.

[0021] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 is a flow chart of a phase-changing switch control method based on a graph neural network provided according to Embodiment 1 of the present invention;

[0024] Figure 2 is a flow chart of a phase-changing switch control method based on a graph neural network provided according to the second embodiment of the present invention;

[0025] Figure 3 is a structural schematic diagram of a phase-changing switch control device based on a graph neural network provided according to Embodiment 3 of the present invention;

[0026] Figure 4 It is a schematic diagram of the structure of an electronic device provided according to Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "first", "second", "target" and "original" in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device 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 units that are not clearly listed or inherent to these processes, methods, products or devices.

[0029] Embodiment 1

[0030] Figure 1 This is a flow chart of a phase-changing switch control method based on a graph neural network provided according to the first embodiment of the present invention. This embodiment can be applied to the control of phase-changing in a three-phase unbalanced working condition in a power system. The method can be executed by a phase-changing switch control device based on a graph neural network. The phase-changing switch control device based on a graph neural network can be implemented in the form of hardware and / or software. The phase-changing switch control device based on a graph neural network can be configured in an electronic device with data processing capabilities. Figure 1 As shown, the method includes:

[0031] The technical solution of this embodiment can be executed by a phase-changing switch control and management system based on a graph neural network; wherein the phase-changing switch control and management system based on a graph neural network includes a control and management platform, and the control and management platform is communicatively connected with a data acquisition and processing module, a graph structure construction module, a graph neural network model module, an anomaly detection and positioning module, a control strategy generation module, and an execution module, etc. wherein electrical signals are connected between the modules.

[0032] S110, obtaining status data and device connection relationships of each power device in the power system.

[0033] Among them, each power device may include sensors and power devices included in the power system. Each sensor may include a current sensor, a voltage sensor, a power sensor, etc. The state data may be understood as the state data obtained by preprocessing the raw data of each power device after collection. The state data may include current, voltage, power, and phase-changing switch state information, etc. The device connection relationship may be understood as the location of each power device in the power system and the connection relationship between them. In this embodiment, the topological information of the power system may be collected, including the location of each device and the connection relationship between the devices, and the rated capacity, rated voltage, and rated power parameters of each device may be obtained, wherein the devices may include busbars, generators, transformers, switchgear, and load points; the location of each device and the connection relationship between them are obtained through system design documents, on-site measurements, or automatic topology recognition technology.

[0034] In this embodiment, the data acquisition and processing module collects original status data from sensors and equipment in the power system and pre-processes the collected original data to obtain status data of each power device in the power system.

[0035] In this embodiment, optionally, status data of each power device in the power system is obtained, including: respectively obtaining original status data of each power device in the power system; performing preprocessing operations on the original status data to obtain preprocessed status data; and integrating the preprocessed status data of each power device to obtain the status data of the power device.

[0036] Among them, the original state data can be understood as the original state information of current, voltage, power and phase-changing switch collected from sensors and state monitoring equipment through a preset sampling frequency. The preprocessing operation may include preprocessing including data cleaning, data filtering and data standardization operations. The preprocessed state data can be understood as the state data obtained after data cleaning, data filtering and data standardization. In this embodiment, the preprocessed state data of each power device is also integrated to form complete state data.

[0037] In this embodiment, the data acquisition and processing module establishes a communication connection with various sensors in the power system and the state monitoring equipment of the phase-changing switch, and then collects the original state data from the sensors and the state monitoring equipment through a preset sampling frequency and performs preprocessing and integration operations to obtain the state data of the power equipment. Among them, the original data exists in the form of a time series, recording the operating state of the power grid within a certain period of time.

[0038] Specifically, the collected raw data is preprocessed, wherein the preprocessing includes data cleaning, data filtering and data standardization. Data cleaning is used to check whether there are missing values ​​in the data. Missing values ​​can be processed by filling (such as mean filling, median filling, interpolation, etc.) or deleting (if the missing ratio is too high). Statistical methods (such as Z-score, IQR, etc.) or model-based methods (such as isolation forest) are used to detect outliers in the data, and the outliers are corrected or deleted. Data filtering is used to remove high-frequency noise and retain low-frequency signals to make the data smoother and reduce data fluctuations caused by sensor noise or power grid fluctuations. Data standardization is used to scale the data so that it falls into a small specific interval (such as between 0 and 1), accelerate the convergence speed of the model, and improve the training efficiency of the model. By calculating the mean and standard deviation of the data, the data is converted into a distribution with a mean of 0 and a standard deviation of 1, eliminating the influence of different dimensions on model training.

[0039] In addition, in this embodiment, data from different sensors and devices can be integrated to form a complete data set, abnormal data in the data set can be labeled, and the processed data can be stored in a data warehouse for subsequent access and analysis.

[0040] In this embodiment, through such a setting, the collected raw data is preprocessed. After the preprocessing step, the noise and outliers in the raw data are eliminated, and the data quality is further improved. At the same time, the standardized processing of the data can make data of different dimensions comparable and analyzed on the same scale, providing clean and effective input data for the subsequent graph neural network model. In this embodiment, the preprocessing includes cleaning, filtering, and standardization operations to eliminate noise, improve data quality, provide the system with necessary input data, ensure that the control decision is based on the latest power grid status, and ensure that the data input to the graph neural network is clean and effective, thereby improving the accuracy and stability of the model.

[0041] S120. Determine graph structure data according to the status data and device connection relationship.

[0042] The graph structure data can be understood as graph data constructed based on the connection relationship between power devices and the corresponding status data. In this embodiment, the graph structure construction module can be used to convert the physical structure and device relationship of the power grid into a graph structure according to the topological structure of the power system and the connection relationship between devices, and construct the corresponding graph structure data, wherein nodes represent devices, edges represent the connection relationship between devices, and status data can be attribute information of nodes.

[0043] In this embodiment, optionally, graph structure data is determined based on status data and device connection relationships, including: determining each power device as a node, defining the connection relationship between devices as an edge; assigning corresponding attribute data to nodes and edges based on status data; and constructing graph structure data based on nodes, edges and attribute information.

[0044] The device connection relationship includes the location of each power device and the connection relationship between the devices; the graph structure data includes nodes and edges; specifically, the nodes can represent the devices in the power system, and the edges represent the physical connection between the devices. The attribute data corresponding to the nodes can include the physical location and operating status of the devices, and the attribute data corresponding to the edges can include the connection strength and transmission capacity.

[0045] Specifically, in this embodiment, the graph structure elements are defined, the nodes and edges in the graph are determined, and a unique identifier is assigned to each device as a node according to the equipment list of the power system, and an edge is defined for each pair of connected devices according to the connection relationship of the equipment. The node contains the unique identifier, type, and parameter information of the equipment, and each edge can contain the node ID, connection type, and connection parameter information of the connection; and the corresponding attribute information is assigned to each node and edge according to the state data. Then, the graph database is used to initialize the graph, create an empty graph structure, traverse all devices and connections, add them as nodes and edges to the graph, and construct the graph structure data in combination with the attribute information of the nodes and edges.

[0046] In this embodiment, the graph structure data can also be compared with the original topology information to check whether each node and edge in the graph is accurate, the graph structure data can be preprocessed, and the preprocessed graph structure data can be stored in the graph database to facilitate access and processing by the graph neural network.

[0047] Through such a setting in the present embodiment, graph structure data can be constructed through the status data of the equipment and the connection relationship between the equipment, and the complex relationship of the power system can be expressed in the form of a graph, providing the topological information of the power grid to the graph neural network, so as to facilitate efficient processing by the graph neural network.

[0048] S130. Determine three-phase unbalanced operating condition information and equipment detection report based on graph structure data and graph neural network model.

[0049] Among them, the graph neural network model can be a trained neural network model, which can be used to process the three-phase unbalanced working condition information and the corresponding equipment detection report corresponding to the graph structure data output. The three-phase unbalanced working condition information can be obtained by identifying the preprocessed graph structure data through the graph neural network model. The equipment detection report can be a detection report generated by using the graph neural network to quickly detect abnormal behaviors in the power system and identify the causes of the three-phase imbalance based on the three-phase unbalanced industrial control information.

[0050] Specifically, in this embodiment, the graph neural network model module can be used to utilize the trained graph neural network model to learn and infer the preprocessed graph structure data, identify the three-phase unbalanced working condition, and predict the optimal phase-changing switch control strategy; through the anomaly detection and positioning module, the graph neural network can be used to quickly detect and locate abnormal behaviors in the power system, identify the causes of the three-phase imbalance, and generate corresponding equipment detection reports.

[0051] S140, determining a phase-changing switch control strategy according to the equipment detection report, and controlling the phase-changing switch based on the phase-changing switch control strategy to adjust the three-phase load balance.

[0052] Among them, the phase-changing switch control strategy can be a strategy for generating a phase-changing switch operation according to the equipment detection report. Specifically, in this embodiment, the control strategy generation module is used to obtain the equipment detection report by identifying and locating abnormal behaviors based on the three-phase unbalanced industrial control information output by the graph neural network model, and then a specific phase-changing switch control strategy is generated according to the equipment detection report. Then, the execution module is used to convert the control instructions corresponding to the phase-changing switch control strategy generated in the control strategy generation module into specific operation commands to control the actual action of the phase-changing switch to adjust the three-phase load balance.

[0053] The technical solution of the embodiment of the present invention obtains the status data and device connection relationship of each power device in the power system; determines the graph structure data according to the status data and the device connection relationship; determines the three-phase unbalanced working condition information and the equipment detection report based on the graph structure data and the graph neural network model; determines the phase-changing switch control strategy according to the equipment detection report, and controls the phase-changing switch based on the phase-changing switch control strategy to adjust the three-phase load balance. This technical solution, by utilizing the graph structure data processing capability of the graph neural network, accurately identifies the three-phase imbalance problem of each node in the power grid, effectively reduces the impact of imbalance on the power grid through the rapid action of the phase-changing switch, and significantly improves the fault handling capability and operation stability of the power grid.

[0054] Embodiment 2

[0055] Figure 2 This is a flow chart of a phase-changing switch control method based on a graph neural network according to the second embodiment of the present invention. This embodiment is optimized based on the above embodiment. The specific optimization is: determining the three-phase unbalanced operating condition information and the equipment detection report based on the graph structure data and the graph neural network model, including: inputting the graph structure data into the graph neural network model to obtain the three-phase unbalanced operating condition information; generating the equipment detection report based on the three-phase unbalanced operating condition information and the graph neural network model. Figure 2 As shown, the method includes:

[0056] S210: Acquire status data and device connection relationships of each power device in the power system.

[0057] S220: Determine graph structure data according to the status data and the device connection relationship.

[0058] S230. Input the graph structure data into the graph neural network model to obtain three-phase unbalanced operating condition information.

[0059] In this embodiment, the graph structure data can be input into the graph neural network model, and the node features and edge features can be extracted through the graph neural network model. Then, the node vector and edge vector are determined based on the node features and edge features, and the imbalance index data is determined based on the node vector and edge vector. The three-phase imbalance information of the node is identified based on the imbalance index data.

[0060] In this embodiment, optionally, the graph structure data is input into the graph neural network model to obtain the three-phase unbalanced operating condition information, including: inputting the graph structure data into the graph neural network model to extract node features and edge features; determining the feature vector of each node and the feature vector of each edge based on the node features and edge features; performing aggregation processing based on the neighbor node feature vector of each node to obtain the target node feature vector; performing aggregation processing based on the neighbor edge feature vector of each edge to obtain the target edge feature vector; determining the imbalance index according to the target node feature vector and the target edge feature vector, and identifying the three-phase unbalanced operating condition information of the node based on the imbalance index.

[0061] Among them, the node features may include the voltage, current and power factor of the node. The edge features may include the resistance, reactance and transmission capacity of the edge. The feature vector of each node may be the corresponding node feature vector determined by inputting the extracted node features into the graph neural network model. The feature vector of the edge may be the corresponding edge feature vector determined by inputting the extracted edge features into the graph neural network model for processing. The neighbor node feature vector may be understood as the feature vector of the neighbor node of the node. The neighbor edge feature vector may be the feature vector of the neighbor edge of the edge. Aggregation processing may be aggregating the neighbor edge features of each edge through the graph neural network. The target node feature vector may be a new node feature vector obtained by aggregating the neighbor node features of each node through the graph neural network. The target edge feature vector is a new edge feature vector obtained by aggregating the neighbor edge features of each edge. The imbalance index may be an imbalance index of the node, which is used to reflect whether there is an imbalance problem at the node.

[0062] Specifically, in this embodiment, preprocessed graph structure data is extracted from the graph database, and features are extracted for each node and edge. In the model training stage, this embodiment can label the nodes and edges in the graph structure to indicate whether there is a three-phase imbalance problem. The layer structure of the graph neural network model is designed, including an input layer, a hidden layer, and an output layer, wherein the hidden layer is used to extract high-level features of the graph, and the output layer is used to generate prediction results. The preprocessed graph structure data and the extracted node and edge features are input into the graph convolutional network model. Select the ReLU activation function and the Adam optimizer, and use the labeled graph structure data as the training set for model training to build a graph neural network model.

[0063] In this embodiment, the graph structure data to be processed can be input into the trained graph neural network model, and the graph structure data can be traversed to determine the feature vector x for each node i. i , including voltage V i 、Current I i , Power Factor PF i , for each edge (i, j), determine its eigenvector as e ij , including resistor R ij Reactance X ij , Transmission Capacity C ij By using the graph neural network model to aggregate the neighbor node features of each node i, its new node feature vector h is calculated. i , that is, the target node feature vector h i , and calculate the new edge feature vector by aggregating the neighbor edge features of each edge (i, j) through the graph neural network model That is, the target edge feature vector

[0064] In this embodiment, the unbalance index can be determined according to the target node feature vector and the target edge feature vector, and the specific method of identifying the three-phase unbalanced working condition information of the node based on the unbalance index can be to calculate the unbalance index z of the node i through the target node feature vector and the target edge feature vector. i , analyze the feature differences and average transmission capacity between the node and its neighbors, and set the threshold θ. i If θ is greater than θ, it is identified that there is a three-phase imbalance problem at node i, and the three-phase imbalance industrial control information is determined. In this embodiment, the optimal phase-changing switch control strategy can also be calculated for the imbalance index zi of each node i.

[0065] Furthermore, the target node feature vector h i The calculation formula is:

[0066]

[0067] Among them, hi is the new node feature vector, ReLU is the rectified linear unit activation function, is the set of neighbor nodes of node i, W is the learnable weight matrix, x i is the feature vector of node i, x j is the feature vector of node j, e ij is the eigenvector of edge (i, j);

[0068] Target edge feature vector The calculation formula is:

[0069]

[0070] in, is the new edge eigenvector, is the concatenation and combination of the feature vector of node i and the feature vector of node j, U is the weight matrix used for edge feature update, and e ij is the eigenvector of edge (i, j);

[0071] Imbalance index z i The calculation formula is:

[0072]

[0073] Among them, z i is the unbalance index of node i, which is used to evaluate whether there is a three-phase unbalance problem at the node. i is the new node feature vector of node i, h j is the new node feature vector of node j, is the new edge feature vector of edge (i, j), k is the number of nodes directly connected to the target node i in the graph structure, is the new edge eigenvector of edge (i, k), when z i When it is larger, it indicates that there is a three-phase unbalance problem at node i.

[0074] The calculation formula of the optimal commutation switch control strategy in this embodiment can be:

[0075]

[0076] Among them, s i is the switching control strategy of node i, α and β are adjustable parameters in the control strategy, softmax(·) is the softmax function used to ensure the probability distribution of the output, z j is the imbalance index of node j, s i The value range is between 0 and 1. i When it is close to 1, it means that the possibility of adopting a certain control strategy is very high.

[0077] Through such a setting in this embodiment, the three-phase unbalanced industrial control information can be identified through the graph neural network, intelligent decision-making can be achieved, the three-phase unbalanced problem can be responded to quickly, and the automation and intelligence level of the system can be improved.

[0078] S240. Generate an equipment detection report based on the three-phase unbalanced operating condition information and the graph neural network model.

[0079] In this embodiment, the abnormality detection features in the nodes can be extracted according to the three-phase imbalance industrial control information, and the abnormality detection features can be input into the graph neural network model to identify the abnormality scores corresponding to the nodes and edges, and the abnormality detection coefficients can be determined according to the abnormality scores to determine the cause analysis of the abnormal nodes and the three-phase imbalance, and the corresponding equipment detection report can be generated according to the abnormal nodes and the cause analysis of the three-phase imbalance.

[0080] In this embodiment, optionally, an equipment inspection report is generated based on the three-phase unbalanced operating condition information and the graph neural network model, including: extracting abnormality detection features in the three-phase unbalanced operating condition information; inputting the abnormality detection features into the graph neural network model to obtain an abnormality score for each node; determining an abnormality detection coefficient based on the abnormality score of each node; and forming an equipment inspection report based on the abnormality detection coefficient and the three-phase unbalanced operating condition information.

[0081] Among them, the anomaly detection feature can be a feature obtained by performing anomaly detection extraction on the features of the nodes and edges. The anomaly detection features of this embodiment may include voltage deviation, current fluctuation, and power anomaly. The anomaly score can be the anomaly score of the nodes and edges obtained by inputting the anomaly detection feature into the graph neural network model. The anomaly detection coefficient can be an anomaly detection system determined by integrating the anomaly scores of the nodes and edges.

[0082] In this embodiment, graph structure data of the power system can be extracted from the graph database. The graph structure data can include node and edge features, and the node and edge features are processed to extract anomaly detection features, and the anomaly detection features are input into the graph neural network model to identify normal and abnormal power system behavior patterns. In addition, in this embodiment, historical data of anomaly detection features can also be input into the graph neural network model to train the graph neural network model so that it can identify normal and abnormal power system behavior patterns.

[0083] In this embodiment, the real-time data of the anomaly detection feature can be input into the trained graph neural network model, and the graph neural network model outputs the anomaly score of each node and edge, and synthesizes the output results of the anomaly score to obtain the anomaly detection coefficient, and analyzes the association between abnormal behavior and three-phase imbalance. The fundamental embodiment can generate a device detection report based on the results of anomaly detection and positioning. Among them, the device detection report includes information about abnormal nodes (such as location, type, and anomaly score, etc.), analysis of the causes of three-phase imbalance, and recommended repair measures.

[0084] Furthermore, the calculation formula for the abnormality score in this embodiment may be:

[0085]

[0086] in, is the abnormal score of the graph neural network model for the output of node i, x j is the feature vector of node j, is the set of neighbor nodes of node i, W v is the weight matrix of feature changes, W h is the weight matrix of the graph convolution layer, b h is the bias vector of the graph convolutional layer, σ is the activation function, ReLU corrected linear unit activation function is used, AGGREGATE is the aggregation function, which represents the summation operation. The higher it is, the more the node's behavior deviates from the normal pattern, making it more likely to be in an abnormal state.

[0087] The calculation formula of the anomaly detection coefficient in this embodiment can be:

[0088]

[0089] Among them, Y is the anomaly detection coefficient, which is used to comprehensively consider the anomaly scores of all nodes in the entire power system; N is the total number of nodes in the graph, and w i is the weight of point i, which can reflect the importance of the node in the power grid; is the abnormal score of the graph neural network model for the output of node i, is the abnormal score of the graph neural network model for the output of node j, is the set of neighbor nodes of point i, k is the number of neighbor nodes, which is used to normalize the difference in abnormal scores of neighbor nodes; λ is the adjustment term, which is used to balance the impact of voltage and power factor abnormal scores on the final coefficient; δ i is the adjustment factor associated with node i, determined based on historical anomaly records; PF i is the power factor of node i, and ω is the regulation index, which is used to control the contribution of power factor anomaly to the anomaly detection coefficient.

[0090] Through such a setting in this embodiment, the graph neural network can be used to quickly detect and locate abnormal behaviors in the power system, identify the causes of three-phase imbalance, and generate a detection report, thereby improving the system's troubleshooting capabilities, reducing troubleshooting time, and providing strong support for quickly restoring three-phase balance.

[0091] S250, determining a phase-changing switch control strategy according to the equipment detection report, and controlling the phase-changing switch based on the phase-changing switch control strategy to adjust the three-phase load balance.

[0092] In this embodiment, optionally, a phase-changing switch control strategy is determined according to a device detection report, including: determining a node to be adjusted, an imbalance assessment factor, and an influencing factor based on the device detection report; sorting the nodes to be adjusted according to the nodes to be adjusted, the imbalance assessment factor, and the influencing factor to obtain a sorting result, and setting a three-phase balance target for the nodes to be adjusted; determining a corresponding phase-changing switch control strategy according to the sorting result and the three-phase balance target.

[0093] Among them, the node to be adjusted can be understood as a node that needs to be adjusted. The imbalance assessment factor can be an assessment factor determined based on the imbalance of the node. The impact factor can be understood as a factor determined based on the urgency of the node. The sorting result can be the result of prioritizing the nodes according to the imbalance factor and the impact factor. The three-phase balance target can be the goal of adjusting the node to achieve three-phase balance. Exemplarily, the three-phase balance target can include the balance standard of current, voltage or power factor.

[0094] In this embodiment, abnormal node identification, imbalance assessment and impact range analysis of each node or edge can be obtained from the graph neural network model; wherein, abnormal node identification indicates which nodes (such as loads or generators) have three-phase imbalance problems, imbalance assessment indicates the quantitative index of the three-phase imbalance of each abnormal node, and impact range analysis indicates the area or node set that may be affected by the imbalance problem; then, based on the output content of the graph neural network model, the nodes that need to be adjusted are prioritized according to the imbalance and urgency, and a specific three-phase balance target is set for each node to be adjusted; then, based on the priority sorting results and the three-phase balance target, the control strategy of the phase-changing switch is preliminarily planned, and the switch control instruction is generated and sent to the execution module for execution.

[0095] Furthermore, in this embodiment, the process of controlling the actual action of the phase-changing switch in the execution module includes: receiving control instructions from the control strategy generation module, the control instructions including the opening and closing state, operation sequence and timing of the phase-changing switch; the execution module converts the received control instructions into switch operation instructions recognizable by the phase-changing switch actuator, specifies the phase-changing switch to be opened or closed, and the sequence and timing of the operation; transmits the instructions to the phase-changing switch actuator of the phase-changing switch through the communication network, and the execution module continuously monitors the feedback information from the phase-changing switch actuator to confirm whether the instructions have been executed correctly, and the feedback information includes key information such as whether the operation is successfully executed, the execution time, and the execution result; the execution module compares and analyzes the received feedback information with the expected effect to evaluate the adjustment effect of the three-phase load balance; if the comparison and analysis finds that there is a deviation between the actual execution result and the expected effect, the execution module feeds back the deviation information of the comparison and analysis to the control strategy generation module, and the control strategy generation module adjusts the control strategy according to the feedback information to optimize subsequent control operations.

[0096] Through such a setting in this embodiment, through the control strategy generation module, a specific phase-changing switch control strategy can be generated according to the output results of the graph neural network model to adjust the three-phase load balance, and the abstract decision results can be converted into executable control instructions to guide the phase-changing switch to perform actual operations; through the execution module, the control instructions generated by the control strategy generation module are converted into specific operation commands to control the actual actions of the phase-changing switch, which are sent to the phase-changing switch actuator in real time, and the feedback information after the execution of the phase-changing switch is received, and compared and analyzed with the expected effect, and the control strategy is adjusted as needed to achieve closed-loop control, continuously optimize the control strategy, and improve the stability and reliability of the system.

[0097] In this embodiment, the three-phase unbalanced working condition phase-changing switch control and management system based on the graph neural network can accurately identify the three-phase unbalance problem of each node in the power grid by utilizing the graph structure data processing capability of the graph neural network, deeply analyze the connection relationship and electrical parameters between nodes, quickly locate the source of imbalance, and evaluate its imbalance degree. Once the imbalance problem is detected, the control instruction can be immediately generated. Through the rapid action of the phase-changing switch, the impact of the imbalance on the power grid is effectively reduced, and the fault handling capability and operation stability of the power grid are significantly improved. And by using the graph neural network, the three-phase imbalance problem can be quickly identified and responded to. The graph neural network model analyzes the data collected from the power system sensors in real time, identifies abnormal nodes and unbalanced areas, and compared with the traditional monitoring and control system, it reduces the dependence on manual intervention and improves the level of automation, so that the system can take measures before the imbalance problem worsens, thereby reducing the equipment loss and power quality degradation caused by the imbalance.

[0098] The technical solution of the embodiment of the present invention obtains the status data and device connection relationship of each power device in the power system; determines the graph structure data according to the status data and the device connection relationship; inputs the graph structure data into the graph neural network model to obtain the three-phase unbalanced working condition information; generates the equipment detection report based on the three-phase unbalanced working condition information and the graph neural network model; determines the phase-changing switch control strategy according to the equipment detection report, and controls the phase-changing switch based on the phase-changing switch control strategy to adjust the three-phase load balance. This technical solution, by utilizing the graph structure data processing capability of the graph neural network, accurately identifies the three-phase imbalance problem of each node in the power grid, effectively reduces the impact of imbalance on the power grid through the rapid action of the phase-changing switch, and significantly improves the fault handling capability and operation stability of the power grid.

[0099] Embodiment 3

[0100] Figure 3 is a schematic diagram of the structure of a phase-changing switch control device based on a graph neural network according to Embodiment 3 of the present invention. Figure 3 As shown, the device comprises:

[0101] The data acquisition module 310 is used to acquire the status data and device connection relationship of each power device in the power system;

[0102] A graph structure data determination module 320, for determining graph structure data according to the state data and the device connection relationship;

[0103] The operating condition information determination module 330 is used to determine the three-phase unbalanced operating condition information and the equipment detection report based on the graph structure data and the graph neural network model;

[0104] The phase-changing switch control module 340 is used to determine the phase-changing switch control strategy according to the equipment detection report, and control the phase-changing switch based on the phase-changing switch control strategy to adjust the three-phase load balance.

[0105] Optionally, the data acquisition module 310 is specifically used to respectively acquire the original status data of each power device in the power system; perform preprocessing operations on the original status data to obtain preprocessed status data; and integrate the preprocessed status data of each power device to obtain the status data of the power device.

[0106] Optionally, the device connection relationship includes the location of each power device and the connection relationship between the devices; the graph structure data includes nodes and edges;

[0107] The graph structure data determination module 320 is specifically used to determine each power device as a node, define the connection relationship between the devices as an edge; assign corresponding attribute data to the nodes and edges based on the state data; and construct graph structure data based on the nodes, edges and attribute information.

[0108] Optionally, the operating condition information determination module 330 includes:

[0109] A three-phase unbalanced working condition information obtaining unit, used for inputting graph structure data into a graph neural network model to obtain three-phase unbalanced working condition information;

[0110] The equipment detection report generation unit is used to generate an equipment detection report based on the three-phase unbalanced operating condition information and the graph neural network model.

[0111] Optionally, a three-phase unbalanced operating condition information acquisition unit is specifically used to input graph structure data into a graph neural network model to extract node features and edge features; determine the feature vector of each node and the feature vector of each edge based on the node features and edge features; perform aggregation processing based on the neighbor node feature vectors of each node to obtain a target node feature vector; perform aggregation processing based on the neighbor edge feature vectors of each edge to obtain a target edge feature vector; determine an unbalance index based on the target node feature vector and the target edge feature vector, and identify the three-phase unbalanced operating condition information of the node based on the unbalance index.

[0112] Optionally, an equipment detection report generation unit is specifically used to extract abnormality detection features in the three-phase unbalanced operating condition information; input the abnormality detection features into the graph neural network model to obtain an abnormality score for each node; determine an abnormality detection coefficient based on the abnormality score of each node; and form an equipment detection report based on the abnormality detection coefficient and the three-phase unbalanced operating condition information.

[0113] Optionally, the phase-changing switch control module 340 is specifically used to determine the nodes to be adjusted, the imbalance assessment factors and the influencing factors based on the equipment detection report; sort the nodes to be adjusted according to the nodes to be adjusted, the imbalance assessment factors and the influencing factors to obtain the sorting results, and set the three-phase balance targets for the nodes to be adjusted; determine the corresponding phase-changing switch control strategy according to the sorting results and the three-phase balance targets.

[0114] A phase-changing switch control device based on a graph neural network provided in an embodiment of the present invention can execute a phase-changing switch control method based on a graph neural network provided in any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

[0115] Embodiment 4

[0116] Figure 41 is a schematic diagram of the structure of an electronic device provided according to Embodiment 4 of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0117] like Figure 4 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0118] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0119] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a commutation switch control method based on a graph neural network.

[0120] In some embodiments, the phase-changing switch control method based on the graph neural network can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the phase-changing switch control method based on the graph neural network described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to execute the phase-changing switch control method based on the graph neural network in any other appropriate manner (for example, by means of firmware).

[0121] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0122] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0123] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0124] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0125] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0126] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0127] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0128] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A phase-changing switch control method based on graph neural network, characterized in that: include: Obtain status data and equipment connection relationships of each power device in the power system; Determine graph structure data according to the state data and the device connection relationship; Determine three-phase unbalanced operating condition information and equipment detection report based on the graph structure data and the graph neural network model; A phase-changing switch control strategy is determined according to the device detection report, and the phase-changing switch is controlled based on the phase-changing switch control strategy to adjust the three-phase load balance.

2. The method according to claim 1, characterized in that Obtain status data of each power device in the power system, including: Respectively obtain the original status data of each power device in the power system; Performing a preprocessing operation on the original state data to obtain preprocessed state data; The pre-processed status data of each power device are integrated to obtain the status data of the power device.

3. The method according to claim 1, characterized in that The device connection relationship includes the location of each power device and the connection relationship between the devices; the graph structure data includes nodes and edges; Determining graph structure data according to the state data and the device connection relationship includes: Determine each power device as a node, and define the connection relationship between the devices as an edge; assigning corresponding attribute data to the nodes and edges based on the state data; Graph structure data is constructed based on the nodes, edges and attribute information.

4. The method according to claim 1, characterized in that: Determine three-phase unbalanced operating condition information and equipment detection report based on the graph structure data and the graph neural network model, including: Inputting the graph structure data into a graph neural network model to obtain three-phase unbalanced operating condition information; Generate an equipment detection report based on the three-phase unbalanced operating condition information and the graph neural network model.

5. The method according to claim 4, characterized in that The graph structure data is input into the graph neural network model to obtain three-phase unbalanced operating condition information, including: Inputting the graph structure data into a graph neural network model to extract node features and edge features; Determine a feature vector of each node and a feature vector of each edge based on the node features and the edge features; Aggregate the feature vectors of neighboring nodes of each node to obtain the feature vector of the target node; Aggregate the neighbor edge feature vectors of each edge to obtain the target edge feature vector; An unbalance index is determined according to the target node feature vector and the target edge feature vector, and three-phase unbalanced operating condition information of the node is identified based on the unbalance index.

6. The method according to claim 4, characterized in that Generating a device detection report based on the three-phase unbalanced operating condition information and the graph neural network model includes: Extracting abnormal detection features from the three-phase unbalanced operating condition information; Inputting the anomaly detection feature into the graph neural network model to obtain an anomaly score for each node; determining an anomaly detection coefficient based on the anomaly score of each node; An equipment detection report is formed according to the abnormal detection coefficient and the three-phase unbalanced operating condition information.

7. The method according to claim 1, characterized in that Determining a commutation switch control strategy according to the device detection report includes: Determine the node to be adjusted, the imbalance assessment factor and the influencing factor based on the equipment detection report; The nodes to be adjusted are sorted according to the nodes to be adjusted, the imbalance evaluation factors and the influencing factors to obtain a sorting result, and a three-phase balance target is set for the nodes to be adjusted; A corresponding phase-changing switch control strategy is determined according to the sorting result and the three-phase balance target.

8. A phase-changing switch control device based on graph neural network, characterized in that: include: A data acquisition module is used to obtain the status data and device connection relationship of each power device in the power system; A graph structure data determination module, used to determine graph structure data according to the state data and the device connection relationship; A working condition information determination module, used to determine three-phase unbalanced working condition information and equipment detection report based on the graph structure data and the graph neural network model; The phase-changing switch control module is used to determine the phase-changing switch control strategy according to the equipment detection report, and control the phase-changing switch based on the phase-changing switch control strategy to adjust the three-phase load balance.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the phase-changing switch control method based on graph neural network described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the phase-changing switch control method based on a graph neural network as described in any one of claims 1 to 7 when executed.

Images