A power grid power flow planning method, device, storage medium and product

Abstract

The application discloses a power grid power flow planning method and device, a storage medium and a product, and relates to the technical field of power grid power flow planning. The method comprises the following steps: constructing a space-time graph of a space-time graph neural network according to the topological structure of a power grid, collecting real-time operation data and historical operation data according to the space-time graph, training the space-time graph neural network according to the historical operation data, obtaining a power flow path planning model, inputting the real-time operation data into the power flow path planning model for processing, obtaining an initial power flow path planning scheme of the power grid, optimizing the initial power flow path planning scheme, obtaining a target power flow path planning scheme of the power grid, and adjusting the power flow distribution and voltage state in the power grid according to the target power flow path planning scheme. According to the optimized scheme, the power flow distribution and voltage state of the power grid can be adjusted, potential errors of the scheme can be effectively reduced, nonlinear and time-varying factors in the operation of the power grid are considered, and the stable operation of the power grid is ensured. While the complex dynamic relationship of the power grid is handled, the accuracy of the power flow path planning is improved.

Description

TECHNICAL FIELD

[0001] The embodiment of the application relates to the technical field of power grid dispatching, and particularly relates to a power grid power flow planning method and device, a storage medium and a product. BACKGROUND

[0002] With the transformation of global energy structure and the rapid development of renewable energy, power grids are facing more and more complex operating environments and challenges. With the integration of a large number of distributed energy and renewable energy, the power flow planning problem of the power grid becomes complex. Reasonable power flow planning of the power grid can keep the voltage stable, distribute the load stably, reduce the occurrence of power grid faults, and ensure the stable operation of the power grid.

[0003] Traditional power grid power flow planning methods mainly rely on linear programming, heuristic algorithms and other methods. Although these methods can provide power flow planning schemes, they have poor adaptability to dynamic changes in power grid operation and time-space coupling effects in the power grid, resulting in low accuracy of the provided power flow planning schemes, which may affect the stable operation of the power grid. SUMMARY

[0004] The application provides a power grid power flow planning method, device, storage medium and product to improve the accuracy of power flow path planning.

[0005] In a first aspect, the embodiment of the application provides a power grid power flow planning method, comprising:

[0006] constructing a space-time graph of a space-time graph neural network according to a topological structure of the power grid;

[0007] collecting real-time operation data and historical operation data according to the space-time graph;

[0008] training the space-time graph neural network according to the historical operation data to obtain a power flow path planning model;

[0009] inputting the real-time operation data into the power flow path planning model for processing to obtain an initial power flow path planning scheme of the power grid;

[0010] optimizing the initial power flow path planning scheme to obtain a target power flow path planning scheme of the power grid;

[0011] adjusting the power flow distribution and voltage state in the power grid according to the target power flow path planning scheme.

[0012] In a second aspect, the embodiment of the application further provides a power grid power flow planning device, comprising:

[0013] a space-time graph construction module configured to construct a space-time graph of a space-time graph neural network according to a topological structure of the power grid;

[0014] The operation data collection module is configured to collect real-time operation data and historical operation data according to the space-time graph;

[0015] The neural network training module is configured to train the space-time graph neural network according to the historical operation data, to obtain a power flow path planning model;

[0016] The initial scheme acquisition module is configured to input the real-time operation data into the power flow path planning model for processing, to obtain an initial power flow path planning scheme of the power grid;

[0017] The initial scheme optimization module is configured to optimize the initial power flow path planning scheme, to obtain a target power flow path planning scheme of the power grid;

[0018] The power grid adjustment module is configured to adjust the power flow distribution and voltage state in the power grid according to the target power flow path planning scheme.

[0019] In a third aspect, an embodiment of the present application further provides a computer device, which comprises:

[0020] one or more processors;

[0021] a storage device configured to store one or more programs;

[0022] When the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the power grid power flow planning method according to the first aspect of the present application.

[0023] In a fourth aspect, an embodiment of the present application further provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to implement the power grid power flow planning method according to the first aspect of the present application.

[0024] In a fifth aspect, an embodiment of the present application further provides a computer program product, which comprises a computer program, and the computer program is executed by a processor to implement the power grid power flow planning method according to the first aspect of the present application.

[0025] In the embodiment of the present application, the space-time graph of the space-time graph neural network is constructed according to the topology structure of the power grid, the real-time operation data and the historical operation data are collected according to the space-time graph, the space-time graph neural network is trained according to the historical operation data, the power flow path planning model is obtained, the real-time operation data is input into the power flow path planning model for processing, the initial power flow path planning scheme of the power grid is obtained, the initial power flow path planning scheme is optimized, the target power flow path planning scheme of the power grid is obtained, and the power flow distribution and voltage state in the power grid are adjusted according to the target power flow path planning scheme. The space-time graph neural network is constructed through the topology structure of the power grid, the spatial and temporal dynamic relationship of the power grid is converted into a graph structure, the adaptability of the dynamic change in the power grid operation and the time-space coupling effect in the power grid is improved, and accurate basic data is provided for power flow planning of the power grid. The real-time operation data and the historical data are collected, the power flow path planning model can learn the change rule of the power grid state from the historical data, the real-time data is input into the power flow path planning model, and the initial power flow path planning scheme is generated. The optimization method is used to adjust the initial power flow path planning scheme to obtain the target power flow path planning scheme, which can effectively reduce the potential error of the scheme and consider the nonlinearity and time-varying factors in the power grid operation. The power flow distribution and voltage state of the power grid are adjusted according to the optimized scheme to ensure the stable operation and optimal performance of the power grid, improve the accuracy of the power flow path planning while processing the complex dynamic relationship of the power grid, and ensure the stable operation of the power grid. BRIEF DESCRIPTION OF DRAWINGS

[0026] Figure 1 A flowchart of a power grid power flow planning method provided for the first embodiment of the present application is shown in the figure.

[0027] Figure 2 A structural block diagram of a power grid power flow planning device provided for the second embodiment of the present application is shown in the figure.

[0028] Figure 3 A structural schematic diagram of a computer device provided for the third embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0029] In order for those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should be within the scope of protection of the present application.

[0030] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and in the above drawings are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the application described herein can encompass the order implementation other than those illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0031] Embodiment one

[0032] Referring to Figure 1 , a flowchart of a power grid power flow planning method provided by the embodiment one of the present application is shown, which can be executed by a power grid power flow planning device, which can be realized in the form of hardware and / or software, and can be configured in a computer device. As Figure 1 shown, the method comprises:

[0033] Step 101, constructing a space-time graph of a space-time graph neural network according to the topology of the power grid.

[0034] The topology of the power grid refers to the connection mode or layout of each component in the power grid, including how the substations, power stations, load points, transmission lines, etc. are connected to each other through cables, switches and other electrical equipment. The topology describes how each node and edge (i.e. each type of electrical equipment in the power grid and its connection relationship) in the power grid interacts.

[0035] The space-time graph neural network (ST-GNN) is a method combining graph neural network (GNN) and time series analysis, aiming to capture both the spatial structure information of graph data and the dynamic characteristics of time series data. In the application of power grid, graph neural network can effectively process the topological information of power grid (i.e. the connection relationship between nodes and the characteristics of edges), while time convolution layer can capture the evolution of power grid state over time. The space-time graph neural network is suitable for processing complex power grids with spatial and temporal dependence.

[0036] The space-time graph is an extension of the concept of traditional graph, which not only contains the spatial information of nodes and edges of the graph, but also considers the time dimension. The state of each node depends not only on the state of other nodes (spatial relationship), but also on the time series. The space-time graph not only focuses on the connection relationship between nodes (such as the connection of substations in the power grid), but also considers how these connection relationships change over time.

[0037] In the present embodiment, the topology of the power grid reflects the connection relationship between each substation, load point and transmission line in the power grid, and the core purpose of constructing the space-time graph is to convert this structured connection relationship into a form that can be processed by the space-time graph neural network, so as to capture the electrical interaction between nodes (such as substations and load points) by using the graph structure.

[0038] In an embodiment of the present application, step 101 can include the following steps:

[0039] Step 1011, taking the substations and load points in the power grid as nodes, and assigning the nodes with first feature vectors.

[0040] In the present embodiment, the substations and load points in the power grid are taken as nodes, and the physical properties (voltage amplitude, voltage phase angle, active input power, reactive input power, active output power and reactive output power) of these nodes are taken as first feature vectors, which can comprehensively describe the state of the nodes. These first feature vectors not only reflect the electrical state of the nodes, but also can change over time, and the behavior of these nodes can be modeled using time series data, which can better capture the dynamic characteristics of the power grid.

[0041] For example, the first feature vector is represented as:

[0042]

[0043] In the formula, X i (t) is the first feature vector, V i (t) is the voltage amplitude of the node at time t, θ i (t) is the voltage phase angle of the node, is the active input power of the node, is the reactive input power of the node, is the active output power of the node, is the reactive output power of the node.

[0044] Step 1012, calculating the first dynamic weight of the node according to at least part of the first feature vector.

[0045] In the present embodiment, the calculation of the first dynamic weight is to reflect the influence of the change of the node on the power flow of the power grid, as well as the importance and operating state of the node. In the power flow planning of the power grid, the electrical parameters (such as active power, reactive power and voltage) of the node will change over time, and the first dynamic weight can help the power flow path planning model to dynamically adjust the importance of the node according to these changes. By using the voltage amplitude and power information in the time series data, a weight value can be assigned to each node in the space-time graph of the power grid, representing the influence of the node on the power flow of the power grid at a certain time.

[0046] The first dynamic weight is expressed as:

[0047]

[0048] wherein w i (t) is the first dynamic weight, γ i is the weight coefficient of the node n i , which considers the topological position and historical operation data of the node in the power grid, is the active power input of the node n i , is the active power output of the node n i , V i (t) is the voltage amplitude of the node n i at time t, represents the ratio of the power imbalance of the node to the voltage, reflecting the load fluctuation of the node.

[0049] Step 1013: regarding the power transmission lines between nodes as edges, and assigning the second feature vector to the edges.

[0050] In this embodiment, the power transmission lines in the power grid are regarded as edges connecting nodes, and the second feature vector of the edge includes resistance, reactance, susceptance and power flow. These second feature vectors change over time, and the state and characteristics of each power transmission line are dynamically changing in the space-time graph. By taking these time-dependent parameters as the second feature vector of the edge, the running state of the power transmission line at different time periods and its influence on the power flow of the power grid can be accurately described. These parameters help simulate how power flows through different power transmission lines in the power grid and how different power transmission lines cooperate and influence each other.

[0051] The second feature vector is expressed as:

[0052] A ij (t)=[R ij ,X ij ,B ij ,S ij (t)];

[0053] S ij (t)=P ij (t)+Q ij (t);

[0054] wherein A ij (t) is the second feature vector, R ij is the resistance of the power transmission line e ij , X ij is the reactance of the power transmission line, B ij is the susceptance of the power transmission line, and S ij(t) is the power flow of the transmission line at time t, P ij (t) is the active power, Q ij (t) is the reactive power.

[0055] Step 1014, calculating the second dynamic weight of the edge according to at least part of the second feature vector.

[0056] In this embodiment, similar to the first dynamic weight of the node, the second dynamic weight of the edge reflects the transmission capacity and actual performance of the transmission line at different time points. The load capacity, transmission capacity and electrical characteristics (such as resistance and reactance) of the transmission line in the power grid will change over time. By calculating the second dynamic weight of each transmission line, the time-varying load and power transmission capacity of each transmission line can be considered when calculating the power flow. The second dynamic weight of these edges makes the power flow path planning model more flexible and real-time in response to changes in the power grid, such as the impact of load fluctuations, transmission line losses or other changes in power grid operating conditions. By highlighting transmission lines with high transmission load and low transmission efficiency through the second dynamic weight, the space-time graph neural network pays more attention to transmission lines that may become bottlenecks, optimizing power flow path planning to avoid line overload and excessive loss.

[0057] For example, the second dynamic weight is represented as:

[0058]

[0059] where w ij (t) is the second dynamic weight, δ ij is the weight coefficient of the transmission line e ij , which is set based on the importance and historical failure rate of the line, |S ij (t)| is the modulus of the power flow of the transmission line at time t, is the rated maximum power transmission capacity of the transmission line, R ij is the resistance of the transmission line e ij , X ij is the reactance of the transmission line, represents the modulus of the admittance of the transmission line, reflecting the transmission efficiency of the transmission line.

[0060] Step 1015, constructing a space-time graph according to the node, the first feature vector, the first dynamic weight, the edge, the second feature vector and the second dynamic weight.

[0061] In this embodiment, the space-time graph is a graph structure that connects the nodes and edges of the power grid according to the relationship between time and space. By adding the feature vectors of nodes and edges, as well as the dynamic weights of nodes and edges in the space-time graph, the space-time graph can effectively represent the time-varying characteristics and structure of the power grid. The space-time graph not only reflects the topological structure of the power grid, but also dynamically adapts to the operation of the power grid at different time periods.

[0062] For example, the space-time graph is represented as:

[0063] G(t) = (V, E, X i (t), A ij (t), W(t));

[0064] In the formula, G(t) is the space-time graph, V is the set of nodes, E is the set of transmission lines, X i (t) is the first feature vector, A ij (t) is the second feature vector, and W(t) is the set between the first dynamic weight and the second dynamic weight.

[0065] Step 102, collecting real-time operation data and historical operation data according to the space-time graph.

[0066] In this embodiment, the real-time operation data can reflect the actual operation state of the power grid at the current time, while the historical operation data can help the power flow path planning model to learn and summarize the rules and trends of the power flow of the power grid, ensuring the accuracy and reliability of the prediction. By collecting and analyzing both real-time operation data and historical operation data, the space-time graph neural network can fully grasp the dynamic characteristics of the power grid, so that the power flow path planning model can better adapt to real-time and future changes when predicting the power flow path, improving the adaptability and stability of the power grid, and helping power grid managers to make real-time adjustment and optimization decisions based on actual and predicted data.

[0067] Exemplarily, the real-time operation data and the historical operation data of the nodes (such as the substations and the load points) and the edges (such as the power transmission lines) in the space-time graph are collected respectively to more accurately reflect each component of the power grid and the mutual relationship thereof. The real-time operation data and the historical operation data both contain node data and edge data. The node data includes the voltage, the current, the active power and the reactive power of the substations, which reflect the power states of the substations and the load points. The edge data includes the power flow of the power transmission lines, which represents the transmission of the power between different nodes. The collection of the real-time operation data and the historical operation data can help to understand the power characteristics of each node and power transmission line and the dynamic characteristics thereof changing over time. The power output of the new energy power station is collected in real time and integrated into the real-time operation data set, and the power output of the new energy power station affects the power balance and the power flow distribution of the power grid. The conversion of the real-time and historical data into a format suitable for the space-time graph neural network is to ensure that the data can be correctly input into the neural network for training and prediction. The space-time graph neural network processes graph data, converts all related node and edge information into a data format suitable for the graph structure, so that the space-time graph neural network can efficiently perform graph convolution operation, thereby correctly learning the spatial relationship and the time dependence, improving the training effect and the prediction ability of the power flow path planning model, and enabling the power flow path planning model to plan and optimize the power flow path of the power grid in real time and accurately in practical applications.

[0068] The power output of the new energy power station can be defined as wherein:

[0069] denotes the node n i The power output of the new energy power station at time t, the power output of the new energy power station is used to capture the volatility of new energy power generation in real time, and reflects the degree of new energy access of the node at different times.

[0070] The format suitable for the space-time graph neural network of the real-time operation data can be represented as:

[0071]

[0072] A(t) = {S ij (t) | e ij ∈ E};

[0073] In the formula, X(t) represents a data set of the node, denotes the node data of the real-time operation data, the node data includes the voltage, the current, the active power and the reactive power of the substation, n i denotes the node, N represents a set of nodes, A(t) represents a data set of the edge, S ij denotes the edge data of the real-time operation data, the edge data includes the power flow of the power transmission line, eij represents a power transmission line, E represents a set of power transmission lines. The format of historical data adapted to the spatio-temporal graph neural network is consistent with the format of real-time operation data adapted to the spatio-temporal graph neural network described above.

[0074] Step 103, training the spatio-temporal graph neural network according to the historical operation data to obtain a power flow path planning model.

[0075] In this embodiment, a power flow path planning model capable of dynamically adjusting and optimizing the power flow path of the power grid is established. This process combines historical operation data with deep learning technology and uses the structure of the spatio-temporal graph neural network to accurately predict the power flow distribution and voltage state of the power grid under different conditions, thereby providing an optimized dispatching scheme for the power grid. The spatio-temporal graph neural network includes a graph convolution layer, a time convolution layer, and a fully connected layer.

[0076] The graph convolution layer is used to capture the power transmission relationship between nodes in the power grid topology, and to establish a structured graph representation of the power grid through the feature information of the nodes and the feature information of the edges.

[0077] The time convolution layer is used to extract the dynamic change characteristics of the nodes and the power transmission lines to capture the dynamic characteristics of the power grid over time and analyze the time sequence characteristics of the nodes and the edges.

[0078] The fully connected layer is used to integrate and map the analysis results of the graph convolution layer and the analysis results of the time convolution layer.

[0079] In an embodiment of the present application, step 103 can include the following steps:

[0080] Step 1031, adding power flow path planning labels to the historical operation data.

[0081] In this embodiment, before training the spatio-temporal graph neural network, power flow path planning labels are added to the historical operation data. Each historical data point is assigned a correct output (i.e., an initial power flow path planning scheme). These labels are usually determined based on the ideal operating state of the power grid under certain operating conditions (such as power flow, load balancing, etc.). By adding labels, the spatio-temporal graph neural network can calculate the error by comparing the predicted results with the actual results, and update the weights through backpropagation to ensure that the power flow path planning model gradually learns how to accurately predict the power flow path of the power grid.

[0082] Step 1032, inputting the historical operation data into the graph convolution layer and calculating the node features of the nodes in the spatio-temporal graph according to the node feature formula.

[0083] In this embodiment, the historical operation data will be input to the graph convolution layer of the spatio-temporal graph neural network for processing. The graph convolution layer is used to extract feature information from the nodes (e.g., substations and load points) in the spatio-temporal graph. The node feature formula calculates the feature vector of each node of the power grid based on the specific electrical quantities of each node of the power grid, such as voltage amplitude, current, active and reactive power, etc. These feature vectors reflect the state of the power grid and capture the role of each node in the power grid and its relationship with other nodes. The role of the graph convolution layer is to propagate and aggregate the information of the nodes through the adjacency relationship of the spatio-temporal graph structure, so that the features of each node can effectively reflect its dynamic interaction in the entire power grid.

[0084] For example, the node feature formula is represented as:

[0085]

[0086] In the formula, is the node feature of the (l+1)th layer of the graph convolution layer for node n i , σ is an activation function for introducing nonlinearity, α ij is the attention weight between node n i and node n j , reflecting the information transmission strength between the two nodes, W (l) is the trainable weight matrix of the lth layer, j is the field node, N(i) is the neighborhood set of node n i , is the node feature of the lth layer of the graph convolution layer for node n j .

[0087] In step 1033, in the time convolution layer, node time sequence features are extracted from the node features according to a time feature formula.

[0088] In this embodiment, in the time convolution layer, the historical data of each node at multiple time points are integrated to extract node time sequence features through a time convolution kernel weight matrix. The time feature formula performs convolution operation on the node features of the node at different time points, so that the spatio-temporal graph neural network can capture possible trends in the time series, such as fluctuations in power grid load, time lag of system response, etc. This helps the power flow path planning model to understand the operation rules of the power grid under different time states and improve the prediction accuracy.

[0089] For example, the time feature formula is represented as:

[0090]

[0091] In the formula, Z i is the node time sequence feature, V t is the time convolution kernel weight matrix for learning the trend of node features at different times, and Hi (t) is the node n i The node feature at time t, and is the bias term, which is used for offset adjustment of the power flow path planning model.

[0092] In step 1034, the node features and the node time sequence features are mapped in the full connection layer to obtain a mapping result.

[0093] In this embodiment, the multi-dimensional information of the node features and the node time sequence features is fused in the full connection layer through linear transformation and a nonlinear activation function to generate a comprehensive feature representation (i.e., the mapping result). The full connection layer integrates the features at different levels together through a weight matrix, so that the output of each node can comprehensively consider its current state and historical dynamics to form a comprehensive understanding of the power grid state. Finally, this mapping result will be used to predict the power flow path planning scheme. This mapping process ensures that the spatio-temporal graph neural network can learn the most suitable power flow state prediction mode.

[0094] In step 1035, a total loss value is calculated according to the mapping result and the power flow path planning label.

[0095] In this embodiment, the total loss value is calculated by comparing the predicted result (i.e., the power flow path planning scheme) output by the power flow path planning model and the actual power flow path planning label. The loss value is a measure of the performance of the power flow path planning model, representing the error between the predicted result and the true label. The total loss value is calculated in a weighted manner, so that the spatio-temporal graph neural network can pay more attention to important parts in different nodes and spatio-temporal relationships. The size of the total loss value provides an optimization direction for the spatio-temporal graph neural network, and through the backpropagation of the total loss value, the spatio-temporal graph neural network can adjust the weights and gradually optimize its prediction accuracy.

[0096] In step 1036, the spatio-temporal graph neural network is updated according to the total loss value to obtain the power flow path planning model.

[0097] In this embodiment, the parameters (weights and biases) of the spatio-temporal graph neural network are updated through the backpropagation algorithm according to the calculated total loss value. The purpose is to minimize the total loss value, so that the power flow path planning model can better fit the actual power flow path of the power grid when processing new data. Through multiple iterations and training, the spatio-temporal graph neural network continuously adjusts its internal parameters and gradually improves the accuracy of the power flow path planning, so that it can provide efficient and accurate schemes for power grid dispatching in actual applications.

[0098] For example, the total loss value is represented as:

[0099]

[0100] In the formula, For the node n of the l-th layer of the graph convolutional layer i Node characteristics, W (l) Let N(i) be the trainable weight matrix of the l-th layer, j be the neighborhood node, and N(i) be the node n. i The neighborhood set, For the node n of the l-th layer of the graph convolutional layer j The node characteristics, Z i Let L be the node temporal feature, and y be the total loss value. i For node n i Trend load tag, f(Z) i ) is node n i The sample power flow load is given by N, where N is the total number of nodes, p and q are the norms for loss calculation, β is the neighborhood smoothing parameter, and K is the total number of trainable weight matrices. For node n in layer l j The trainable weight matrix, For node n in layer l i The trainable weight matrix, where λ is the regularization parameter. This is a neighborhood smoothing term used to constrain the smoothness of features between adjacent nodes, ensuring the continuity of power transmission relationships. This is a regularization term used to prevent the model from overfitting.

[0101] Step 104: Input the real-time running data into the power flow path planning model for processing to obtain the initial power flow path planning scheme of the power grid.

[0102] In this embodiment, real-time running data is input into the trained power flow path planning model for processing. The power grid is modeled using a spatiotemporal graph neural network to accurately calculate the voltage and power flow load distribution of the power grid, thereby obtaining the initial power flow path planning scheme of the power grid.

[0103] In one embodiment of the present invention, step 104 may include the following steps:

[0104] Step 1041: Input the real-time running data into the graph convolutional layer to calculate the optimal voltage value of the node in the spatiotemporal graph.

[0105] In this embodiment, real-time operational data is input into a graph convolutional layer. The function of the graph convolutional layer is to extract features of each node (substation and load point) in the power grid through the graph structure of a spatiotemporal graph neural network. These features include voltage amplitude, current, active power, and reactive power, reflecting the operating state of each node. Through graph convolution operations, the node features are converted into optimal voltage values, which are calculation results describing the most suitable voltage state of a node at a specific point in time. Based on the current power grid topology and operational data, the optimal voltage value of each node at time t is predicted, ensuring the stability and reliability of voltage control.

[0106] An exemplary optimal voltage value is represented as:

[0107]

[0108] wherein, is the optimal voltage value of node n i The optimal voltage value at time t, f θ is an output function of the power flow path planning model, V j (t) is the optimal voltage value of node n i is the voltage value of the adjacent node, a ij is the weight reflecting the power transmission relationship between nodes, j is the adjacent node, and N(i) is the adjacent set of node n i . is the target operation data.

[0109] Step 1042, in the time convolution layer, the optimal power flow load of the power transmission line between nodes is calculated according to the optimal voltage value.

[0110] In this embodiment, after obtaining the optimal voltage value of the node, the optimal power flow load of the power transmission line is calculated according to the optimal voltage value. This process is completed through the time convolution layer, which combines the node time sequence features (i.e., the trend of voltage value change) with the physical characteristics of the power transmission line (such as resistance, reactance, admittance, etc.) to calculate the optimal power flow load between connected nodes, i.e., the power flow direction and intensity of the power transmission line at each time, to ensure that the power transmission of the power grid is within the safe and efficient range. The calculation of the optimal power flow load not only considers the voltage level, but also considers the electrical characteristics of each power transmission line in the power grid, ensuring that the power transmission of the power grid does not exceed its carrying capacity.

[0111] An exemplary optimal power flow load is represented as:

[0112]

[0113] wherein, is the optimal power flow load of the power transmission line at time t, is the optimal voltage value of node n i , is the optimal voltage value of node n j , G ij is the real part of the admittance of the power transmission line, B ij is the imaginary part of the admittance of the power transmission line, R ij is the resistance of the power transmission line, and X ij is the reactance of the power transmission line.

[0114] Step 1043, in the fully connected layer, the optimal voltage value and the optimal power flow load are mapped to obtain an initial power flow path planning scheme.

[0115] In the present embodiment, the optimal voltage values and the optimal power flow loads are input into the fully connected layer, which is mainly used to integrate the feature information from different layers and make the final decision or prediction. Through the mapping process, the optimal voltage values of the nodes and the optimal power flow loads of the transmission lines are integrated together to obtain the initial power flow path planning scheme of the power grid. This initial power flow path planning scheme will reflect the voltage distribution and power flow direction of the power grid, providing a basis for subsequent optimization.

[0116] For example, the initial power flow path planning scheme is represented as:

[0117]

[0118] wherein Ω * (t) represents the initial power flow path planning scheme at time t, represents the set of optimal voltage values of all nodes, represents the set of optimal power flow loads of all transmission lines, i represents a node, N represents a set of nodes, e ij represents a transmission line, and E represents a set of transmission lines.

[0119] Step 105, optimizing the initial power flow path planning scheme to obtain the target power flow path planning scheme of the power grid.

[0120] In the present embodiment, the initial power flow path planning scheme may not meet the actual operation requirements of the power grid, especially for the unbalanced load distribution. Optimizing the initial power flow path planning scheme is a step to ensure the stable, economic and safe operation of the power grid. The goal is to optimize the initial power flow path planning scheme to ensure more balanced power distribution in the power grid, avoid overload of some transmission lines or nodes in the power grid, and maximize overall efficiency to obtain the target power flow path planning scheme.

[0121] In one embodiment of the present application, step 105 can include the following steps:

[0122] Step 1051, calculating the load rate of the transmission lines of the power grid according to the initial power flow path planning scheme.

[0123] In this embodiment, the load rate refers to the ratio between the actual transmitted power of the transmission line and its maximum carrying capacity. Calculating the load rate is the basis for power flow path optimization, and the load rate directly affects the operation efficiency and safety of the power grid. By calculating the load rate of each transmission line in the initial power flow path planning scheme, it can be evaluated whether there is an overload risk in the power grid. If the load rate of some lines is too high, it means that these lines may face overload, and even equipment failure or shutdown. Therefore, the calculation of the load rate is the premise of judging the health status of the power grid, and can provide specific data support for the subsequent optimization steps.

[0124] For example, the load rate is represented as:

[0125]

[0126] In the formula, ρ ij (t) is the load rate of the transmission line e ij at time t. is the optimal power flow load of the transmission line e ij at time t. is the rated power transmission capacity of the transmission line e ij .

[0127] Step 1052, calculate the fairness index of the load rate.

[0128] In this embodiment, the fairness index (such as Jain's fairness index) measures the balance of load distribution in the power grid. By calculating the fairness index of the load rate, the distribution of the load of each transmission line in the power grid can be understood. If the load rate of some transmission lines is much higher than that of other lines, it means that the load distribution is uneven, which may cause some lines to run at high load, thereby affecting the reliability and stability of the power grid. The calculation of the fairness index helps to identify the part of the power grid where the load distribution is uneven, providing a direction for adjustment in the subsequent optimization. The fairness index is usually directly related to the fairness of load distribution, and is an important indicator to measure whether the power grid is in the best balanced state.

[0129] For example, the fairness index is represented as:

[0130]

[0131] In the formula, J(t) is the fairness index, ρ ij (t) is the load rate of the transmission line e ij at time t, N is the total number of transmission lines, and E is the set of transmission lines.

[0132] Step 1053, if the fairness index is greater than or equal to the preset load threshold, determine that the initial power flow path planning scheme is the target power flow path planning scheme.

[0133] In the embodiment, when the calculated fairness index is greater than or equal to the preset load threshold (i.e., the fairness index is greater than or equal to 1), it indicates that the load distribution of the power grid is already balanced enough, and the load of the transmission line is not excessively concentrated on some lines, and thus the initial power flow path planning scheme can be directly used as the target power flow path planning scheme. At this time, the power grid has met the demand for load balancing, and further optimization operation can not bring significant benefits, and thus additional complex optimization is not needed.

[0134] Step 1054, if the fairness index is less than the preset load threshold, optimization operation is performed on the initial power flow path planning scheme to optimize the initial power flow path planning scheme into the target power flow path planning scheme.

[0135] In the embodiment, if the fairness index is less than the preset load threshold, it indicates that there is an unbalanced phenomenon in the load distribution of the power grid, and some lines can be overloaded, and there is a risk of instability or excessive loss of the power grid. At this time, the initial power flow path planning scheme needs to be optimized. The purpose of the optimization operation is to adjust the power distribution of the power grid, so that the load of each transmission line is more uniform, thereby improving the efficiency of the power grid, reducing the risk of overload, and preventing transmission line failure or power loss.

[0136] For example, a target function is constructed to optimize the total power consumption and the fairness index of the power grid. Optimization of the total power consumption of the power grid can effectively reduce energy consumption, reduce the operating cost of the power grid, and improve the economy and environmental friendliness of the power grid. Optimization of the fairness index focuses on improving the balance of the load of the power grid, avoiding overload of individual transmission lines or nodes, and ensuring that each part of the power grid does not produce excessive load fluctuation or voltage instability during operation, thereby improving the reliability and safety of the power grid; by solving the minimum value of the target function, the initial power flow path planning scheme is optimized into the target power flow path planning scheme, meeting the dynamic demand of the power grid under different time and different operating conditions, thereby providing more scientific guidance for intelligent scheduling, load prediction and resource allocation of the power grid.

[0137] The target function is represented as:

[0138] U(t) = a1 P total (t) - b1 J(t);

[0139]

[0140] In the formula, U(t) is the target function, a1 and b1 are weight coefficients, P total (t) is the total power consumption of the power grid, R ij is the resistance of the transmission line, is the modulus of the optimal power flow load of the transmission line at time t, J(t) is the fairness index, p ij (t) is the load rate, and eij E is a set of transmission lines.

[0141] Solving the minimum value of the objective function is represented as:

[0142]

[0143] In the formula, Ω'(t) represents the target flow path planning scheme at time t, and by minimizing the objective function U(t), the power consumption and load balance are balanced to find the target path planning scheme.

[0144] Step 106, adjust the flow distribution and voltage state in the power grid according to the target flow path planning scheme.

[0145] In this embodiment, by adjusting the flow distribution and voltage state through the target flow path planning scheme, the load of each transmission line and substation in the power grid can be effectively distributed, avoiding overload or voltage instability, and reducing the risk of system failure. This process can balance the load of each part of the power grid, ensuring efficient transmission and use of power.

[0146] In the event of a transmission line fault or equipment anomaly in the power grid, the emergency flow path planning process is immediately started, using the online calculation capability of the flow path planning model to quickly generate an emergency flow path planning scheme based on the current power grid state, and combining the Jain's fairness index method to evaluate the load balance of the emergency scheme, avoiding line overload or system instability caused by fault propagation.

[0147] In the embodiment of the present application, the space-time graph of the space-time graph neural network is constructed according to the topological structure of the power grid, real-time operation data and historical operation data are collected according to the space-time graph, the space-time graph neural network is trained according to the historical operation data, a power flow path planning model is obtained, the real-time operation data is input into the power flow path planning model for processing, an initial power flow path planning scheme of the power grid is obtained, the initial power flow path planning scheme is optimized, a target power flow path planning scheme of the power grid is obtained, and the power flow distribution and voltage state in the power grid are adjusted according to the target power flow path planning scheme. The space-time graph neural network is constructed through the topological structure of the power grid, the spatial and temporal dynamic relationship of the power grid is converted into a graph structure, the adaptability of the dynamic changes in the power grid operation and the space-time coupling effect in the power grid is improved, and accurate basic data is provided for power flow planning of the power grid. Real-time operation data and historical data are collected, the power flow path planning model can learn the change rule of the power grid state from the historical data, real-time data is input into the power flow path planning model, and an initial power flow path planning scheme is generated. The initial power flow path planning scheme is adjusted by using an optimization method to obtain a target power flow path planning scheme, which can effectively reduce the potential error of the scheme and consider the nonlinearity and time-varying factors in the power grid operation. The power flow distribution and voltage state of the power grid are adjusted according to the optimized scheme to ensure stable operation and optimal performance of the power grid, improve the accuracy of the power flow path planning while handling the complex dynamic relationship of the power grid, and ensure stable operation of the power grid.

[0148] Embodiment two

[0149] Figure 2 A structural schematic diagram of a power grid power flow planning device provided in the second embodiment of the present application is shown in Figure 2 The device comprises:

[0150] The space-time graph construction module 201 is configured to construct a space-time graph of a space-time graph neural network according to the topological structure of the power grid.

[0151] The operation data collection module 202 is configured to collect real-time operation data and historical operation data according to the space-time graph.

[0152] The neural network training module 203 is configured to train the space-time graph neural network according to the historical operation data to obtain a power flow path planning model.

[0153] The initial scheme acquisition module 204 is configured to input the real-time operation data into the power flow path planning model for processing to obtain an initial power flow path planning scheme of the power grid.

[0154] The initial scheme optimization module 205 is configured to optimize the initial power flow path planning scheme to obtain a target power flow path planning scheme of the power grid.

[0155] a power grid regulation module 206, configured to regulate a power flow distribution and a voltage state in the power grid according to the target power flow path planning scheme.

[0156] In an embodiment of the present application, the space-time graph construction module 201 comprises:

[0157] a node screening module, configured to take a transformer substation and a load point in the power grid as a node, and assign a first feature vector to the node; the first feature vector comprises a voltage amplitude, a voltage phase angle, an active input power, a reactive input power, an active output power, and a reactive output power;

[0158] a first weight calculation module, configured to calculate a first dynamic weight of the node according to at least part of the first feature vector;

[0159] an edge screening module, configured to take a power transmission line between the nodes as an edge, and assign a second feature vector to the edge; the second feature vector comprises a resistance, a reactance, a susceptance, and a power flow;

[0160] a second weight calculation module, configured to calculate a second dynamic weight of the edge according to at least part of the second feature vector;

[0161] a space-time graph acquisition module, configured to construct a space-time graph according to the nodes, the first feature vector, the first dynamic weight, the edges, the second feature vector, and the second dynamic weight;

[0162] wherein, the first feature vector is represented as:

[0163]

[0164] wherein, X i (t) is the first feature vector, V i (t) is the voltage amplitude of the node at time t, θ i (t) is the voltage phase angle of the node, is the active input power of the node, is the reactive input power of the node, is the active output power of the node, is the reactive output power of the node.

[0165] the first dynamic weight is represented as:

[0166]

[0167] wherein, w i (t) is the first dynamic weight, γ i is a weight coefficient of the node n i . the active input power of the node n i , the active output power of the node n i , V i (t) the voltage amplitude of the node n i at time t;

[0168] the second feature vector is represented as:

[0169] A ij (t) = [R ij , X ij , B ij , S ij (t)];

[0170] S ij (t) = P ij (t) + Q ij (t);

[0171] wherein A ij (t) is the second feature vector, R ij is the resistance of the transmission line e ij , X ij is the reactance of the transmission line, B ij is the susceptance of the transmission line, S ij (t) is the power flow of the transmission line at time t, P ij (t) is the active power, and Q ij (t) is the reactive power;

[0172] the second dynamic weight is represented as:

[0173]

[0174] wherein w ij (t) is the second dynamic weight, δ ij is the weight coefficient of the transmission line e ij , |S ij (t)| is the modulus of the power flow of the transmission line at time t, is the rated maximum power transmission capability of the transmission line, R ij is the resistance of the transmission line e ij , and X ij is the reactance of the transmission line;

[0175] the space-time graph is represented as:

[0176] G(t) = (V, E, X i (t), Aij (t), W(t));

[0177] In the formula, G(t) is the space-time graph, V is the set of nodes, E is the set of transmission lines, X i (t) is the first feature vector, A ij (t) is the second feature vector, and W(t) is the set between the first dynamic weight and the second dynamic weight.

[0178] In an embodiment of the present application, the operation data collection module 202 comprises:

[0179] A data collection module is configured to collect real-time operation data and historical operation data of the nodes and edges in the space-time graph, wherein the real-time operation data and the historical operation data both include voltage, current, active power and reactive power of the substation, and power flow of the transmission line.

[0180] A power station collection module is configured to collect power output of a new energy power station and write the power output into the real-time operation data.

[0181] A format conversion module is configured to convert the real-time operation data and the historical operation data into a format suitable for a space-time graph neural network.

[0182] In an embodiment of the present application, the space-time graph neural network comprises a graph convolution layer, a time convolution layer and a full connection layer, and the neural network training module 203 comprises:

[0183] A label adding module is configured to add a power flow path planning label to the historical operation data.

[0184] A node feature calculation module is configured to input the historical operation data into the graph convolution layer and calculate node features of the nodes in the space-time graph according to a node feature formula.

[0185] A node time sequence feature extraction module is configured to extract node time sequence features from the node features in the time convolution layer according to a time feature formula.

[0186] A mapping result acquisition module is configured to map the node features and the node time sequence features in the full connection layer to obtain a mapping result.

[0187] A total loss value calculation module is configured to calculate a total loss value according to the mapping result and the power flow path planning label.

[0188] A model training module is configured to update the space-time graph neural network according to the total loss value to obtain a power flow path planning model.

[0189] Wherein, the node feature formula is represented as:

[0190]

[0191] In the formula, is the node feature of the node n i of the (l+1)th layer of the graph convolution layer, and sigma is an activation function, alpha ij is the attention weight between the node n i and the node n j , W (l) is a trainable weight matrix of the lth layer, j is a domain node, N(i) is a neighborhood set of the node n i , is the node feature of the node n j of the lth layer of the graph convolution layer;

[0192] The time feature formula is represented as:

[0193]

[0194] In the formula, Z i is the node time sequence feature, V t is a time convolution kernel weight matrix, H i (t) is the node feature of the node n i at time t, and epsilon is a bias term;

[0195] The total loss value is represented as:

[0196]

[0197] In the formula, is the node feature of the node n i of the lth layer of the graph convolution layer, W (l) is a trainable weight matrix of the lth layer, j is a domain node, N(i) is a neighborhood set of the node n i , is the node feature of the node n j of the lth layer of the graph convolution layer, Z i is the node time sequence feature, L is the total loss value, y i is the power load label of the node n i , f(Z i ) is the sample power load of the node n i , N is the total number of nodes, p and q are both norms of loss calculation, beta is a neighborhood smoothing parameter, and K is the total number of the trainable weight matrices, is the trainable weight matrix of the node n j of the lth layer, the node n i of the lth layer, λ is a regularization parameter.

[0198] In an embodiment of the present application, the initial scheme acquisition module 204 comprises:

[0199] a voltage value calculation module, configured to input the real-time operation data into the graph convolution layer to calculate optimal voltage values of the nodes in the space-time graph;

[0200] a power flow load calculation module, configured to calculate optimal power flow loads of transmission lines between the nodes according to the optimal voltage values in the time convolution layer;

[0201] an initial scheme mapping module, configured to map the optimal voltage values and the optimal power flow loads in the fully connected layer to obtain an initial power flow path planning scheme;

[0202] wherein the optimal voltage value is expressed as:

[0203]

[0204] wherein, is the optimal voltage value of the node n i at time t, f θ is an output function of the power flow path planning model, V j (t) is a voltage value of a neighbor node of the node n i , α ij is a weight, j is a neighbor node, and N(i) is a neighbor set of the node n i , is the target operation data;

[0205] the optimal power flow load is expressed as:

[0206]

[0207] wherein, is an optimal power flow load of the transmission line at time t, is the optimal voltage value of the node n i , is the optimal voltage value of the node n j , G ij is a real part of admittance of the transmission line, B ij is an imaginary part of admittance of the transmission line, R ij is a resistance of the transmission line, and X ij is a reactance of the transmission line;

[0208] the initial power flow path planning scheme is expressed as:

[0209]

[0210] Ω * (t) represents the initial power flow path planning scheme at time t, represents a set of the optimal voltage values of all the nodes, represents a set of the optimal power flow loads of all the transmission lines, i represents the node, N represents a set of the nodes, e ij represents the transmission line, and E represents a set of the transmission lines.

[0211] In an embodiment of the present application, the initial scheme optimization 205 comprises:

[0212] a load rate calculation module configured to calculate load rates of transmission lines of the power grid according to the initial power flow path planning scheme;

[0213] a fairness index calculation module configured to calculate a fairness index of the load rates;

[0214] a target scheme determination module configured to determine the initial power flow path planning scheme as a target power flow path planning scheme if the fairness index is greater than or equal to a preset load threshold;

[0215] a target scheme acquisition module configured to perform an optimization operation on the initial power flow path planning scheme to optimize the initial power flow path planning scheme into a target power flow path planning scheme if the fairness index is less than the preset load threshold;

[0216] wherein the load rate is represented as:

[0217]

[0218] wherein ρ ij (t) is the transmission line e ij the load rate at time t, is the transmission line e ij the optimal power flow load at time t, is the transmission line e ij the rated power transmission capacity of the transmission line e

[0219] the fairness index is represented as:

[0220]

[0221] wherein J(t) is the fairness index, ρ ij (t) is the transmission line e ijThe load rate at time t, N is the total number of the transmission lines, and E is the set of the transmission lines.

[0222] In one embodiment of the present application, the target scheme acquisition module comprises:

[0223] A target function construction module is configured to construct a target function with the optimization of the total power consumption of the power grid and the fairness index as the target.

[0224] A target function calculation module is configured to optimize the initial power flow path planning scheme into a target power flow path planning scheme by solving the minimum value of the target function.

[0225] The target function is expressed as:

[0226] U(t) = a1 P total (t) - b1 J(t);

[0227]

[0228] In the formula, U(t) is the target function, a1 and b1 are weight coefficients, P total (t) is the total power consumption of the power grid, R ij is the resistance of the transmission line, is the modulus of the optimal power flow load of the transmission line at time t, J(t) is the fairness index, p ij (t) is the load rate, e ij is a transmission line, and E is the set of the transmission lines.

[0229] The power grid power flow planning device provided in the embodiments of the present application can execute the power grid power flow planning method provided in any of the embodiments of the present application, and has the corresponding function modules and beneficial effects of executing the power grid power flow planning method.

[0230] Embodiment three

[0231] Referring to Figure 3 , a structural schematic diagram of a computer device provided in an embodiment of the present application is shown. The computer device is intended to represent various forms of digital computers, such as a laptop computer, a desktop computer, a workstation, a personal digital assistant, a blade server, a mainframe computer, and other suitable computers. The computer device can also represent various forms of mobile devices, such as a personal digital processing, a cellular phone, a smart phone, a wearable device (such as a helmet, glasses, a watch, etc.), and other similar computing devices. The components shown in the figure, their connections and relationships, and their functions are merely examples, and are not intended to limit the implementation of the present application described and / or claimed herein.

[0232] As Figure 3As shown, the computer device 10 includes at least one processor 11, and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., communicatively connected to the at least one processor 11, where the memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer programs stored in the read-only memory (ROM) 12 or loaded into the random access memory (RAM) 13 from the storage unit 18. In the RAM 13, various programs and data required for the operation of the computer 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.

[0233] Various components in the computer 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 magnetic 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 computer device 10 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0234] The processor 11 can be various general and / or special-purpose 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 special-purpose 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 performs various methods and processes described above, such as the power flow planning method.

[0235] In some embodiments, the power flow planning method can be implemented as a computer program tangibly embodied in a computer readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the computer device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded onto the RAM 13 and executed by the processor 11, one or more steps of the power flow planning method described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to perform the power flow planning method by any other appropriate means, such as by means of firmware.

[0236] The various embodiments of the systems and techniques described above can be implemented in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a load programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0237] Computer programs used to implement the processes of the application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer program

[0238] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store computer programs for use by or in connection with an instruction execution system, apparatus, or device. Computer-readable storage media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium will include one or more lines of a program of instructions in a transitory signal, a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0239] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer 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 a trackball) by which the user can provide input to the computer device. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0240] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can 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), blockchain network, and the Internet.

[0241] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. A server can be a cloud server, also known as cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business scalability in traditional physical host and VPS service.

[0242] Embodiment Four

[0243] The embodiment of the present application further provides a computer program product, which comprises a computer program, and the computer program is executed by a processor to implement the power flow planning method provided by any of the embodiments of the present application.

[0244] The computer program code can also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce the computer implemented process such that the

[0245] It should be understood that the various forms of flow shown in the figures are illustrative examples of implementing the steps of the application. Several steps have been described as being performed by a single device. It will be understood that these steps can be performed by a single device or multiple devices, and that the steps can be performed in an order different from that shown in the figures. For example, the steps described in the figures can be performed in parallel or in a different order, as long as the desired results of the application are achieved. The application is not limited in this regard.

[0246] The specific embodiments have been shown and described for the purposes of illustrating the physiological principles of the application and its practical application. It is therefore to be understood that various modifications and changes can be made by those skilled in the art without departing from the spirit and scope of the application. The scope of the application is not to be limited by specific illustrative embodiments. The application is to cover any and all modifications and the same is therefore intended to be within the scope of the application.

Claims

1. A power grid flow planning method, characterized in that, include: The spatiotemporal graph of the spatiotemporal graph neural network is constructed based on the topology of the power grid; Real-time and historical operating data are collected based on the aforementioned spatiotemporal diagram; The spatiotemporal graph neural network is trained based on the historical operating data to obtain the power flow path planning model; The real-time operating data is input into the power flow path planning model for processing to obtain the initial power flow path planning scheme of the power grid; The initial power flow path planning scheme is optimized to obtain the target power flow path planning scheme of the power grid; Adjust the power flow distribution and voltage state in the power grid according to the target power flow path planning scheme; The spatiotemporal graph neural network includes graph convolutional layers, temporal convolutional layers, and fully connected layers; training the spatiotemporal graph neural network based on the historical operation data to obtain the power flow path planning model includes: Add a power flow path planning tag to the historical operation data; The historical running data is input into the graph convolutional layer, and the node features of the nodes in the spatiotemporal graph are calculated according to the node feature formula. In the temporal convolutional layer, temporal features of nodes are extracted from the node features according to the temporal feature formula; The node features and the node temporal features are mapped in the fully connected layer to obtain the mapping result; The total loss value is calculated based on the mapping results and the power flow path planning labels; The spatiotemporal graph neural network is updated based on the total loss value to obtain the power flow path planning model.

2. The method according to claim 1, characterized in that, The spatiotemporal graph of the spatiotemporal graph neural network constructed based on the topology of the power grid includes: Substations and load points in the power grid are taken as nodes, and a first feature vector is assigned to each node; the first feature vector includes voltage amplitude, voltage phase angle, active input power, reactive input power, active output power and reactive output power; Calculate the first dynamic weight of the node based on at least a portion of the first feature vector; The transmission lines between the nodes are taken as edges, and a second feature vector is assigned to the edges; the second feature vector includes resistance, reactance, susceptance, and power flow. The second dynamic weight of the edge is calculated based on at least a portion of the second feature vector; A spatiotemporal graph is constructed based on the nodes, the first feature vector, the first dynamic weight, the edges, the second feature vector, and the second dynamic weight. The first feature vector is represented as: ； In the formula, For the first feature vector, The voltage amplitude of the node at time t. The voltage phase angle of the node. The active power input to the node is [the active power input to the node]. The reactive power input of the node. The active power output of the node. The reactive power output of the node; The first dynamic weight is represented as: ； In the formula, This is the first dynamic weight. For the node The weighting coefficients, For the node The active input power, For the node The active power output, For the node The voltage amplitude at time t; The second feature vector is represented as: In the formula, This is the second feature vector. For the transmission line The aforementioned resistance, The reactance of the transmission line. The susceptance of the transmission line. The power flow of the transmission line at time t. Active power Reactive power; The second dynamic weight is expressed as: ； In the formula, This is the second dynamic weight. For the transmission line The weighting coefficients, Let be the magnitude of the power flow of the transmission line at time t. This refers to the rated maximum power transmission capacity of the transmission line. For the transmission line The aforementioned resistance, The reactance of the transmission line; The spatiotemporal diagram is represented as follows: ； In the formula, For the aforementioned spacetime diagram, The set of nodes, The collection of the aforementioned transmission lines. For the first feature vector, This is the second feature vector. It is the set between the first dynamic weight and the second dynamic weight.

3. The method according to claim 2, characterized in that, The collection of real-time and historical operational data based on the spatiotemporal diagram includes: Real-time and historical operating data are collected for the nodes and edges in the spatiotemporal graph, respectively; the real-time and historical operating data include the voltage, current, active power and reactive power of the substation, and the power flow of the transmission line. The power output of the new energy power plant is collected and written into the real-time operation data; The real-time running data and the historical running data are converted into a format that is compatible with the spatiotemporal graph neural network.

4. The method according to claim 1, characterized in that, The node feature formula is expressed as follows: ； In the formula, For the (l+1)th layer node of the graph convolutional layer Node characteristics, For activation function, For the node and the node Attention weights between them Let be the trainable weight matrix of the l-th layer, and j be the neighborhood node. For the node The neighborhood set, For the node of the l-th layer of the graph convolutional layer The node features; The time characteristic formula is expressed as follows: ； In the formula, The node's temporal characteristics, The time convolution kernel weight matrix is... For the node The node characteristics at time t For bias terms; The total loss value is expressed as: ； In the formula, For the node of the l-th layer of the graph convolutional layer The node features, Let be the trainable weight matrix of the l-th layer, and j be the neighborhood node. For the node The neighborhood set, For the node of the l-th layer of the graph convolutional layer The node features, Let L be the temporal feature of the node, and L be the total loss value. For the node Trendy load tags, For the node The sample power flow load is given, where N is the total number of nodes, and p and q are the norms for loss calculation. Here, K is the neighborhood smoothing parameter, and K is the total number of trainable weight matrices. The node of the lth layer The trainable weight matrix, The node of the lth layer The trainable weight matrix, This is the regularization parameter.

5. The method according to claim 4, characterized in that, The step of inputting the real-time operating data into the power flow path planning model for processing to obtain the initial power flow path planning scheme of the power grid includes: The real-time running data is input into the graph convolutional layer to calculate the optimal voltage value of the node in the spatiotemporal graph; In the temporal convolutional layer, the optimal power flow load of the transmission line between the nodes is calculated based on the optimal voltage value; In the fully connected layer, the optimal voltage value and the optimal power flow load are mapped to obtain an initial power flow path planning scheme; The optimal voltage value is expressed as: ； In the formula, For the node The optimal voltage value at time t, This is the output function of the power flow path planning model. For the node Voltage values ​​of neighboring nodes, Let j be the weight, and j be the domain node. For the node The neighborhood set, For the target running data; The optimal power flow load is expressed as: ； In the formula, Let be the optimal power flow load for the transmission line at time t. For the node The optimal voltage value, For the node The optimal voltage value, Let be the real part of the admittance of the transmission line. Let be the imaginary part of the admittance of the transmission line. The resistance of the transmission line is given. The reactance of the transmission line; The initial power flow path planning scheme is expressed as follows: ； In the formula, This represents the initial power flow path planning scheme at time t. This represents the set of optimal voltage values ​​for all the nodes. Let i represent the set of optimal power flow loads for all the aforementioned transmission lines, i represent the node, and N represent the set of the nodes. The term "transmission line" refers to the transmission line, and "E" represents the set of transmission lines.

6. The method according to any one of claims 1-5, characterized in that, The step of optimizing the initial power flow path planning scheme to obtain the target power flow path planning scheme for the power grid includes: Calculate the load rate of the power grid's transmission lines based on the initial power flow path planning scheme; Calculate the fairness index of the load rate; If the fairness index is greater than or equal to the preset load threshold, then the initial power flow path planning scheme is determined to be the target power flow path planning scheme. If the fairness index is less than the preset load threshold, then the initial power flow path planning scheme is optimized to optimize the initial power flow path planning scheme into the target power flow path planning scheme. The load rate is expressed as: ； In the formula, For the transmission line The load rate at time t, For the transmission line The optimal power flow load model at time t. For the transmission line Rated power transmission capacity; The fairness index is expressed as: ； In the formula, J(t) is the fairness index. For the transmission line The load rate at time t, where N is the total number of transmission lines. This refers to the collection of power transmission lines.

7. The method according to claim 6, characterized in that, If the fairness index is less than a preset load threshold, then an optimization operation is performed on the initial power flow path planning scheme to optimize the initial power flow path planning scheme into the target power flow path planning scheme, including: An objective function is constructed with the goal of optimizing the total power consumption of the power grid and the fairness index. The initial power flow path planning scheme is optimized into the target power flow path planning scheme by solving for the minimum value of the objective function. The objective function is expressed as: ； ； In the formula, U(t) is the objective function. and All are weighting coefficients. The total power consumption of the power grid is [value missing]. The resistance of the transmission line is given. Let J(t) be the modulus of the optimal power flow load for the transmission line at time t, and J(t) be the fairness index. The load rate, Let E be the set of power transmission lines.

8. A computer device, characterized in that, The computer device includes: One or more processors; Storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the power flow planning method as described in any one of claims 1-7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the power flow planning method as described in any one of claims 1-7.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the power flow planning method as described in any one of claims 1-7.

Images