Low-voltage distribution network node voltage prediction method based on full-factor learning graph neural network

Abstract

The application provides a low-voltage distribution network node voltage prediction method based on a full-factor learning graph neural network, belongs to the technical field of smart grids, and comprises the following steps: S1: based on the absence of a low-voltage distribution network topological structure, edges of a graph neural network are updated through iteration, and a graph neural network model of the low-voltage distribution network is established; S2: based on edge features and node features of the graph neural network model, iterative learning of the graph neural network model is carried out; and S3: based on the learned graph neural network model, direct prediction of the low-voltage distribution network node voltage is realized. The application can take into account topological structure features and metering data features, realize direct prediction of the low-voltage distribution network node voltage, has lower model complexity, deeply excavates potential relationships between data, is higher in efficiency of prediction model establishment, and improves the accuracy of the prediction model.

Description

Technical Field

[0001] The present invention belongs to the field of smart grid technology, and specifically relates to a method for predicting node voltages in a low-voltage distribution network based on a full-factor learning graph neural network. Background Art

[0002] Low-voltage distribution networks, as the terminal network of the power system, are characterized by a large number of diverse terminal devices, low intelligence levels, inconsistent standards, and irregular network wiring. These issues pose significant challenges to their operation and maintenance. Power supply reliability and power quality often fail to meet user requirements, with voltage over-limit being a common problem. Therefore, accurately predicting node voltages in low-voltage distribution networks can effectively prevent potential electrical hazards.

[0003] Distribution network node voltage prediction methods based on power flow calculations primarily calculate node voltages based on the impedance matrix and Kirchhoff's law. However, traditional power flow calculation methods can encounter convergence issues in certain situations. Specifically, the iterative algorithm may fail to converge to a stable solution, and certain operating conditions of the power system may cause the power flow equation to become ill-conditioned, significantly affecting the accuracy and stability of the calculations.

[0004] Conventional node voltage prediction methods are mostly developed for medium- and high-voltage distribution networks, and only some methods that ignore the distribution network topology can be applied to low-voltage distribution networks. However, research has shown that node voltage prediction methods that use topology information outperform those that do not. Therefore, these node voltage prediction methods for low-voltage distribution networks fail to consider the topological characteristics of the low-voltage distribution network and fail to fully explore the potential relationships between data, resulting in low model accuracy. Summary of the Invention

[0005] In order to solve the above problems existing in the prior art, a low-voltage distribution network node voltage prediction method based on a full-factor learning graph neural network is provided.

[0006] The technical solution adopted by the present invention to solve its technical problem is:

[0007] This technical solution proposes a low-voltage distribution network node voltage prediction method based on a full-factor learning graph neural network, which includes the following steps:

[0008] S1: Based on the missing topological structure of the low-voltage distribution network, a graph neural network model of the low-voltage distribution network is established by iteratively updating the edges of the graph neural network;

[0009] S2: Iteratively learn the graph neural network model based on its edge and node features;

[0010] S3: Based on the learned graph neural network model, direct prediction of low-voltage distribution network node voltage is achieved.

[0011] Preferably, in S1, the graph neural network model includes edge features, node features and global features.

[0012] Preferably, the low-voltage distribution network topology is regarded as a complete graph, and the edge characteristics include the conductance and admittance of the corresponding line. The weight of the edge with actual connection is the admittance value of the line segment, and the weight of the edge without connection is 0.

[0013] Preferably, the node characteristics include three electrical quantities of the circuit node, which are active power, reactive power and voltage, and are set as per-unit values ​​when input.

[0014] Preferably, the global features include: the node voltage of the transformer is used as a global variable, and the vertex is represented as:

[0015] v i ={P i ,Q i ,U i} (1);

[0016] Where, P i , Q i 、U i Represent the active power, reactive power and voltage of node i respectively, and the characteristic attribute is a three-dimensional vector;

[0017] The edges are represented as:

[0018] e k ={G k ,B k} (2);

[0019] Where G k 、B k They represent the conductance and susceptance of edge k respectively, and the characteristic attribute is a two-dimensional vector.

[0020] Preferably, it is characterized in that the graph neural network model with global variables is expressed as:

[0021] G(u0,V,E)(3);

[0022] Where u0 is the global variable representing the transformer voltage, V={v i} is a vertex set consisting of user nodes and intermediate nodes, E={e k ,r k ,s k} is the set of edges represented by triples;

[0023] Among them, e kis the feature of edge k, r k is the index of the receiving node, s k The index of the sending node.

[0024] Preferably, the iterative learning process of the graph neural network model includes:

[0025] Edge feature learning: defining edge feature update function The formula is:

[0026]

[0027] Where, e' k is the updated feature of edge k, is the feature of the receiving node of edge k, is the characteristic of the sending node.

[0028] Preferably, It is implemented by a three-layer fully connected network, whose input is a 9-dimensional feature vector, expressed as:

[0029]

[0030] The output is a 2D feature vector representing the conductance and susceptance of the edge [G' k ,B' k ];

[0031] Node feature learning: defining edge aggregation function ρ e→v , the formula is:

[0032]

[0033] Where, The edge features are aggregated into the adjacency matrix and transformed into a weighted adjacency matrix. It consists of two layers of fully connected networks, and the input is the edge feature [G k ,B k ], the output is 1-dimensional features.

[0034] Preferably, define a node update function The formula is:

[0035]

[0036] The node update function is implemented using a 3-layer graph convolutional neural network;

[0037] Vertex feature matrix H at time l+1 (l+1) Calculated by formula (8), the formula is expressed as:

[0038] H (l+1) =GCN(H (l) ) (8);

[0039] Where H (l) is the vertex feature matrix at the lth moment. GCH is implemented by three layers of graph convolution layers. The calculation method of each layer is expressed as follows:

[0040]

[0041] Where i = 1, 2, 3, and are the inputs of the i-th layer and the (i-1)-th layer respectively, W is the weight matrix, when i=1, When i=3,

[0042] is the adjacency matrix with self-loops added, for The degree matrix of .

[0043] Preferably, a regularization term about global variables is added to the first layer of GCN, and the formula is expressed as:

[0044]

[0045] Where, is the learning weight of the global variable u0, is the weighted adjacency matrix with self-loops added.

[0046] Compared with the prior art, the present invention has the following advantages:

[0047] 1. In the absence of a low-voltage distribution network topology, this application can achieve autonomous evolution of the potential topology by iteratively updating the edges of the graph neural network, so that the connection relationship between nodes is close to that of the real low-voltage distribution network, thereby taking into account both the topological structure characteristics and the metering data characteristics, and realizing direct prediction of the node voltage of the low-voltage distribution network.

[0048] 2. This application can clearly reflect the information flow and inter-node relationships between low-voltage distribution network nodes, and can fully utilize the neighborhood information between nodes, thereby improving the accuracy of the prediction model and deeply mining the potential relationships between data, thereby improving the performance of data analysis. Compared with the flow calculation model, the model complexity is lower and the efficiency of predictive model establishment is higher. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the following description of the embodiments with reference to the accompanying drawings, in which:

[0050] Figure 1 It is the overall flow chart of the present invention;

[0051] Figure 2 It is the graph neural network model structure of low-voltage distribution network. DETAILED DESCRIPTION

[0052] The following describes embodiments of the present invention in detail. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended only to explain the present invention and are not to be construed as limiting the present invention.

[0053] like Figure 1-Figure 2 As shown, this embodiment proposes a low-voltage distribution network node voltage prediction method based on a full-factor learning graph neural network, including the following steps:

[0054] S1: Based on the missing topological structure of the low-voltage distribution network, a graph neural network model of the low-voltage distribution network is established by iteratively updating the edges of the graph neural network;

[0055] S2: Iteratively learn the graph neural network model based on its edge and node features;

[0056] S3: Based on the learned graph neural network model, direct prediction of low-voltage distribution network node voltage is achieved.

[0057] In the absence of a low-voltage distribution network topology, the autonomous evolution of the potential topology can be achieved by iteratively updating the edges of the graph neural network. The connection relationship between nodes can be inferred and autonomously evolved through measurement data, making the connection relationship between nodes close to the real low-voltage distribution network, thereby taking into account both the topological structure characteristics and the metering data characteristics, and realizing direct prediction of the node voltage of the low-voltage distribution network.

[0058] In S1, the graph neural network model includes edge features, node features and global features.

[0059] The topology of a low-voltage distribution network is considered a complete graph. Edge features include the conductance and susceptance of the corresponding lines. Edges with actual connections have a weight equal to the admittance of that line segment, while edges without connections have a weight of 0. The direction of power transmission is primarily determined by the potential difference between the two ends of the circuit. When modeling low-voltage distribution networks using graph neural networks, an undirected graph is constructed to accurately reflect this physical phenomenon.

[0060] The node characteristics include three electrical quantities of the circuit node, namely active power, reactive power and voltage. Since the voltage is unknown in the initial state, it is set to the per-unit value when input.

[0061] Global features include: the node voltage of the transformer is used as a global variable, and the graph neural network model of the low-voltage distribution network can be described as follows Figure 2 As shown, Figure 2 This is the graph neural network model structure of the low-voltage distribution network, where the solid line represents an actual connection relationship between two adjacent nodes, and the dotted line represents the absence of an actual connection relationship.

[0062] Figure 2 In , vertices are represented as:

[0063] v i ={P i ,Q i ,U i} (1);

[0064] Where, P i , Q i 、U i Represent the active power, reactive power and voltage of node i respectively, and the characteristic attribute is a three-dimensional vector;

[0065] The edges are represented as:

[0066] e k ={G k ,B k} (2);

[0067] Where G k 、B k They represent the conductance and susceptance of edge k respectively, and the characteristic attribute is a two-dimensional vector.

[0068] The graph neural network model with global variables is represented as:

[0069] G(u0,V,E) (3);

[0070] Where u0 is the global variable representing the transformer voltage, V={v i} is a vertex set consisting of user nodes and intermediate nodes, E={e k ,r k ,s k} is the set of edges represented by triples;

[0071] Among them, e k is the feature of edge k, r k is the index of the receiving node, s k The index of the sending node.

[0072] The iterative learning process of the graph neural network model includes:

[0073] Edge feature learning: defining edge feature update function The formula is:

[0074]

[0075] Where, e'k is the updated feature of edge k, is the feature of the receiving node of edge k, is the characteristic of the sending node;

[0076] It is implemented by a three-layer fully connected network, whose input is a 9-dimensional feature vector, expressed as:

[0077]

[0078] The output is a 2D feature vector representing the conductance and susceptance of the edge [G' k ,B' k ];

[0079] Node feature learning: defining edge aggregation function ρ e→v , the formula is:

[0080]

[0081] Where, The edge features are aggregated into the adjacency matrix and transformed into a weighted adjacency matrix. It consists of two layers of fully connected networks, and the input is the edge feature [G k ,B k ], the output is 1-dimensional features.

[0082] Define node update function The formula is:

[0083]

[0084] The node update function is implemented using a 3-layer graph convolutional neural network;

[0085] Vertex feature matrix H at time l+1 (l+1) Calculated by formula (8), the formula is expressed as:

[0086] H (l+1) =GCN(H (l) ) (8);

[0087] Where H (l) is the vertex feature matrix at the lth moment. GCH is implemented by three layers of graph convolution layers. The calculation method of each layer is expressed as follows:

[0088]

[0089] Where i = 1, 2, 3, and are the inputs of the i-th layer and the (i-1)-th layer respectively, W is the weight matrix, when i=1, When i=3,

[0090] is the adjacency matrix with self-loops added, for The degree matrix of .

[0091] In order to compensate for the inability of formula (9) to process global features, a regularization term about global variables is added to the first layer of GCN, which is expressed as:

[0092]

[0093] Where, is the learning weight of the global variable u0, is the weighted adjacency matrix with self-loops added.

[0094] The learning process of the graph neural network model for low-voltage distribution network node grid prediction is as follows:

[0095] Input:G(u,V,E)

[0096] Output:G(u',V',E')

[0097] 1:fore k ∈E

[0098] 2: / *Calculate updated edge attributes* /

[0099] 3:end for

[0100] 4:forv i ∈Vdo

[0101] 5: / *Aggregate edge attributes of each node* /

[0102] 6: / *Calculate updated node attributes* /

[0103] 7:end for.

[0104] This application can clearly reflect the information flow and inter-node relationships between low-voltage distribution network nodes, and can fully utilize the neighborhood information between nodes, improve the accuracy of the prediction model, deeply explore the potential relationships between data, and thus improve the performance of data analysis. Compared with the power flow calculation model, the model complexity is lower and the efficiency of predictive model establishment is higher.

[0105] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to the embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the claims and their equivalents.

Claims

1. A low-voltage distribution network node voltage prediction method based on full-factor learning graph neural network is characterized by: The following steps are involved: S1: Based on the missing topological structure of the low-voltage distribution network, a graph neural network model of the low-voltage distribution network is established by iteratively updating the edges of the graph neural network; S2: Iteratively learn the graph neural network model based on its edge and node features; S3: Based on the learned graph neural network model, direct prediction of low-voltage distribution network node voltage is achieved; Global features include: transformer node voltages are used as global variables, and vertices are represented as: （1）； Where, 、 、 Represents nodes respectively i The active power, reactive power and voltage of , the characteristic attribute is a three-dimensional vector; The edges are represented as: （2）； Where, 、 Represents edges k The conductivity and susceptance of , the characteristic attribute is a two-dimensional vector; The graph neural network model with global variables is represented as: （3）； Where, is a global variable representing the transformer voltage, is a vertex set consisting of user nodes and intermediate nodes, is the set of edges represented by triples; in, For the edge k Features, is the index of the receiving node, is the index of the sending node; The iterative learning process of the graph neural network model includes: Edge feature learning: defining edge feature update function , the formula is: （4）； Where, For the edge k Updated features, For the edge k Characteristics of the receiving node, is the characteristic of the sending node; It is implemented by a three-layer fully connected network, whose input is a 9-dimensional feature vector, expressed as: （5）； The output is a 2D feature vector representing the conductance and susceptance of the edge ; Node feature learning: defining edge aggregation functions , the formula is: （6）； Where, For the edge k After aggregation, the edge features are aggregated into the adjacency matrix, which is converted into a weighted adjacency matrix. It consists of two layers of fully connected networks, and the input is the edge features. , the output is 1-dimensional features; Define node update function , the formula is: （7）； The node update function is implemented using a 3-layer graph convolutional neural network; l Vertex feature matrix at time +1 Calculated by formula (8), the formula is expressed as: （8）； Where, For the l The vertex feature matrix at time t, GCH It is implemented by three layers of graph convolutional layers. The calculation method of each layer is expressed as follows: （9）； Where, i =1,2,3, and Respectively i Layer and ( i -1) layer input, W is the weight matrix, when i =1, ,when i =3, ; is the adjacency matrix with self-loops added, for degree matrix of ; exist GCN The first layer adds a regular term about global variables, and the formula is expressed as: （10）； Where, For global variables The learning weights, is the weighted adjacency matrix with self-loops added.

2. The method for predicting low-voltage distribution network node voltage based on full-factor learning graph neural network according to claim 1 is characterized in that: In S1, the graph neural network model includes edge features, node features and global features.

3. The method for predicting low-voltage distribution network node voltage based on full-factor learning graph neural network according to claim 2 is characterized in that: The topological structure of the low-voltage distribution network is regarded as a complete graph. The edge characteristics include the conductance and admittance of the corresponding line. The weight of the edge with actual connection is the admittance value of the line segment, and the weight of the edge without connection is 0.

4. The method for predicting low-voltage distribution network node voltage based on full-factor learning graph neural network according to claim 2 is characterized in that: Node characteristics include three electrical quantities of the circuit node, namely active power, reactive power and voltage, which are set as per-unit values ​​when input.

Images