Power load prediction method and device based on structural perception aggregation function

Abstract

The embodiment of the application provides a kind of power load prediction method and device based on structure perception aggregation function, its method includes: obtaining the node feature of each node in the power system topology model and the node feature of its neighbor node, and based on structure perception aggregation function, the node feature of each node in the power system topology model and the node feature of its neighbor node are aggregated, to obtain the node feature after aggregation of each node;Obtain the historical time series feature of each node in the power system topology model, and by fusing the historical time series feature of each node with the aggregated node feature, obtain the fusion feature data of each node;By inputting the fusion feature data of each node into the trained deep neural network prediction model, the power load prediction result of each node is obtained.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a method and apparatus for predicting power load based on structure-aware aggregation functions. Background Technology

[0002] In modern power systems, numerous methods exist for power load forecasting. Traditional methods, such as regression analysis, time series analysis, and grey models, offer some effectiveness and stability when handling simple, linear load changes. However, these methods often struggle to accurately capture the complex nonlinear characteristics and uncertainties of power loads. Intelligent forecasting methods, such as artificial neural networks, support vector machines, and fuzzy logic, while advantageous in handling complex relationships, also have limitations. For instance, neural networks are prone to getting trapped in local optima, leading to inaccurate predictions. Furthermore, current technologies rely solely on historical load and equipment power data, lacking a comprehensive depiction of the overall plant operation system and missing correlations between different components, thus affecting forecast accuracy. Summary of the Invention

[0003] In view of this, embodiments of this application provide a power load forecasting method based on structure-aware aggregation functions. One or more embodiments of this application also relate to a power load forecasting device based on structure-aware aggregation functions, a computing device, a computer-readable storage medium, and a computer program, to address the technical deficiencies existing in the prior art.

[0004] According to a first aspect of the embodiments of this application, a power load forecasting method based on a structure-aware aggregation function is provided, comprising:

[0005] Obtain the topological relationships between devices in the power system, and construct a power system topology model based on the topological relationships between devices in the power system;

[0006] The node features of each node and the node features of its neighboring nodes in the power system topology model are obtained, and the node features of each node and the node features of its neighboring nodes in the power system topology model are aggregated based on the structure-aware aggregation function to obtain the aggregated node features of each node.

[0007] The historical time series features of each node in the power system topology model are obtained, and the historical time series features of each node are fused with the aggregated node features to obtain the fused feature data of each node.

[0008] By inputting the fused feature data of each node into a trained deep neural network prediction model, the power load prediction result of each node is obtained.

[0009] Preferably, constructing a power system topology model based on the topological relationships between devices in the power system includes:

[0010] Based on the topological relationship between devices in the power system, each device node in the power system is modeled as a node, the current flow relationship or load dependency relationship between devices is modeled as an edge, the current flow, power consumption or other metrics between devices are modeled as edge weights, and the device node that has a current flow relationship or load dependency relationship with the device node is modeled as a neighbor node.

[0011] A power system topology model is constructed based on all nodes, edges, edge weights, and neighboring nodes in the power system.

[0012] Preferably, the edge weights include:

[0013]

[0014] in: Represents a node and neighboring nodes Edge weights between them; Represents a node The average power consumption; Representing neighboring nodes The average power consumption; Represents a node Electricity consumption; Representing neighboring nodes Electricity consumption; Represents a node and neighboring nodes The practical importance of collaboration in the production process, as determined by experience or actual circumstances. and It is a weighting coefficient, and .

[0015] Preferably, the aggregation of node features of each node in the power system topology model based on the structure-aware aggregation function with the node features of its neighboring nodes, to obtain the aggregated node features of each node, includes:

[0016]

[0017] in: It is the MLP network model. +1 layer output node Aggregated node features; It is a node In the Node features in a layered model; It is a node and neighboring nodes Edge weights between them; These are learnable parameters; Neighboring nodes In the Node features in the layer model; N(i) is the node The set of neighboring nodes; MLP is a multilayer perceptron function; The value of is 0, 1, 2, ..., L-1; L is the number of layers in the MLP network model.

[0018] Preferably, the historical time series characteristics of each node are historical load time series characteristics or historical weather data time series characteristics.

[0019] Preferably, the step of obtaining the power load prediction result for each node by inputting the fused feature data of each node into a trained deep neural network prediction model includes:

[0020]

[0021] in: Z represents the power load forecast result for each node; Z represents the fused feature data for each node. It is the weight matrix of the output layer of a deep neural network prediction model; It is a bias term.

[0022] Preferably, it further includes:

[0023] Obtain the topological relationships between devices in multiple power systems and the actual power load results of each device, and construct a power system topology model based on the topological relationships between devices in each power system;

[0024] The node features of each node and the node features of its neighboring nodes in the power system topology model are obtained, and the node features of each node and the node features of its neighboring nodes in the power system topology model are aggregated based on the structure-aware aggregation function to obtain the aggregated node features of each node.

[0025] The historical time series features of each node in the power system topology model are obtained, and the historical time series features of each node are fused with the aggregated node features to obtain the fused feature data of each node.

[0026] The deep neural network prediction model is trained based on the fused feature data of each node and the actual power load results of each device to obtain the trained deep neural network prediction model.

[0027] According to a second aspect of the embodiments of this application, a power load forecasting device based on a structure-aware aggregation function is provided, comprising:

[0028] The acquisition module is configured to acquire the topological relationships between devices in the power system and construct a power system topology model based on the topological relationships between devices in the power system.

[0029] The aggregation module is configured to obtain the node features of each node in the power system topology model and the node features of its neighboring nodes, and to aggregate the node features of each node in the power system topology model and the node features of its neighboring nodes based on the structure-aware aggregation function to obtain the aggregated node features of each node.

[0030] The fusion processing module is configured to acquire the historical time series features of each node in the power system topology model, and to obtain the fused feature data of each node by fusing the historical time series features of each node with the aggregated node features.

[0031] The prediction module is configured to obtain the power load prediction result of each node by inputting the fused feature data of each node into a trained deep neural network prediction model.

[0032] According to a third aspect of the embodiments of this application, a computing device is provided, comprising:

[0033] Memory and processor;

[0034] The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement any of the steps of the power load forecasting method based on the structure-aware aggregation function.

[0035] According to a fourth aspect of the embodiments of this application, a computer-readable storage medium is provided that stores computer-executable instructions, which, when executed by a processor, implement the steps of any one of the power load forecasting methods based on structure-aware aggregation functions.

[0036] According to a fifth aspect of the present application, a computer program is provided, wherein when the computer program is executed in a computer, the computer is instructed to perform the steps of the above-described power load forecasting method based on structure-aware aggregation functions.

[0037] The power load forecasting scheme based on structure-aware aggregation functions provided in this application involves: acquiring the topological relationships between devices in a power system and constructing a power system topology model based on these relationships; acquiring the node features of each node in the power system topology model and the node features of its neighboring nodes, and aggregating these node features with the node features of its neighboring nodes using a structure-aware aggregation function to obtain the aggregated node features of each node; acquiring the historical time series features of each node in the power system topology model, and fusing these historical time series features with the aggregated node features to obtain fused feature data for each node; and inputting the fused feature data of each node into a trained deep neural network prediction model to obtain the power load forecasting result for each node. This application's embodiments abstract each device (such as a machine, sensor, etc.) as a node in a graph, and the current flow relationships or load dependencies between devices as weighted edges. It fully utilizes the power flow and load correlation information between devices and introduces a simple and efficient aggregation function that captures the graph's isomorphism. Furthermore, by introducing an important mechanism to distinguish different node structures, it enhances the model's ability to identify structural differences between nodes, thereby improving the accuracy and robustness of load forecasting. This method is applicable to complex power network environments and effectively supports load management and optimization decisions for energy storage companies. Attached Figure Description

[0038] Figure 1 This is a flowchart of a power load forecasting method based on a structure-aware aggregation function provided in one embodiment of this application;

[0039] Figure 2 This is a flowchart of a deep neural network prediction model training method provided in one embodiment of this application;

[0040] Figure 3 This is a schematic diagram of a power load forecasting device based on a structure-aware aggregation function provided in one embodiment of this application;

[0041] Figure 4 This is a structural block diagram of a computing device provided in one embodiment of this application. Detailed Implementation

[0042] Many specific details are set forth in the following description to provide a full understanding of this application. However, this application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of this application; therefore, this application is not limited to the specific embodiments disclosed below.

[0043] The terminology used in one or more embodiments of this application is for the purpose of describing particular embodiments only and is not intended to limit the scope of one or more embodiments of this application. The singular forms “a,” “the,” and “the” used in one or more embodiments of this application and in the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” used in one or more embodiments of this application refers to and includes any or all possible combinations of one or more associated listed items.

[0044] It should be understood that although the terms first, second, etc., may be used to describe various information in one or more embodiments of this application, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, first may also be referred to as second without departing from the scope of one or more embodiments of this application, and similarly, second may also be referred to as first. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to a determination."

[0045] This application provides a power load forecasting method based on structure-aware aggregation functions. It also relates to a power load forecasting device based on structure-aware aggregation functions, a computing device, a computer-readable storage medium, and a computer program, which will be described in detail in the following embodiments.

[0046] Figure 1 A flowchart of a power load forecasting method based on a structure-aware aggregation function according to an embodiment of this application is shown, which specifically includes the following steps.

[0047] Step S101: Obtain the topological relationships between devices in the power system, and construct a power system topology model based on the topological relationships between devices in the power system;

[0048] In one optional implementation, constructing a power system topology model based on the topological relationships between devices in the power system includes: modeling each device node in the power system as a node, modeling the current flow relationship or load dependency relationship between devices as an edge, modeling the current flow, power consumption or other metrics between devices as edge weights, and modeling device nodes that have a current flow relationship or load dependency relationship with the device nodes as neighbor nodes; and constructing a power system topology model based on all the nodes, edges, edge weights and neighbor nodes in the power system.

[0049] Furthermore, the edge weights include:

[0050]

[0051] in: Represents a node and neighboring nodes Edge weights between them; Represents a node The average power consumption; Representing neighboring nodes The average power consumption; Represents a node Electricity consumption; Representing neighboring nodes Electricity consumption; Represents a node and neighboring nodes The practical importance of collaboration in the production process, as determined by experience or actual circumstances. and It is a weighting coefficient, and .

[0052] Step S102: Obtain the node features of each node in the power system topology model and the node features of its neighboring nodes, and aggregate the node features of each node in the power system topology model and the node features of its neighboring nodes based on the structure-aware aggregation function to obtain the aggregated node features of each node.

[0053] In one optional implementation, the node features of each node in the power system topology model are aggregated with the node features of its neighboring nodes based on the structure-aware aggregation function to obtain the aggregated node features of each node, including:

[0054]

[0055] in: It is the MLP network model. +1 layer output node Aggregated node features; It is a node In the Node features in a layered model; It is a node and neighboring nodes Edge weights between them; These are learnable parameters; Neighboring nodes In the Node features in the layer model; N(i) is the node The set of neighboring nodes; MLP is a multilayer perceptron function; The value of is 0, 1, 2, ..., L-1; L is the number of layers in the MLP network model.

[0056] Step S103: Obtain the historical time series features of each node in the power system topology model, and obtain the fused feature data of each node by fusing the historical time series features of each node with the aggregated node features;

[0057] In one alternative implementation, the historical time series characteristics of each node are historical load time series characteristics or historical weather data time series characteristics.

[0058] Step S104: By inputting the fused feature data of each node into the trained deep neural network prediction model, the power load prediction result of each node is obtained.

[0059] In one optional implementation, obtaining the power load prediction result for each node by inputting the fused feature data of each node into a trained deep neural network prediction model includes:

[0060]

[0061] in: Z represents the power load forecast result for each node; Z represents the fused feature data for each node. It is the weight matrix of the output layer of a deep neural network prediction model; It is a bias term.

[0062] In an optional implementation, the method further includes: acquiring the topological relationships between devices in multiple power systems and the actual power load results of each device, and constructing a power system topology model based on the topological relationships between devices in each power system; acquiring the node features of each node in the power system topology model and the node features of its neighboring nodes, and aggregating the node features of each node in the power system topology model with the node features of its neighboring nodes based on a structure-aware aggregation function to obtain the aggregated node features of each node; acquiring the historical time series features of each node in the power system topology model, and fusing the historical time series features of each node with the aggregated node features to obtain fused feature data of each node; and training a deep neural network prediction model based on the fused feature data of each node and the actual power load results of each device to obtain the trained deep neural network prediction model.

[0063] The power load forecasting scheme based on structure-aware aggregation functions provided in this application aims to fully utilize the power flow and load correlation information between devices by abstracting each device (such as machines, sensors, etc.) as nodes in a graph and the current flow relationships or load dependencies between devices as weighted edges. A simple and efficient aggregation function is introduced to capture the isomorphism of the graph, and an important mechanism for distinguishing different node structures is introduced to enhance the model's ability to identify structural differences between nodes, thereby improving the accuracy and robustness of load forecasting. This method is applicable to complex power network environments and effectively supports load management and optimization decisions for energy storage companies.

[0064] The technical solution of the present invention will be further described below.

[0065] The definition of nodes and edges: each device (such as a machine, sensor, etc.) will be treated as a node. Indicates. Side Indicates device and neighboring equipment The current flow relationship or load dependency between the devices. The weight of the edges can be based on the current flow, power consumption, or other relevant metrics between the devices.

[0066] Example: In a production system, energy storage devices are included. Production equipment In addition, other non-electrical equipment (such as trucks, forklifts, and other auxiliary equipment). The connection weights between these devices can be determined based on the combined ratio of their electricity consumption and power consumption, and adjusted empirically in conjunction with their actual importance in the production process.

[0067] Specifically, the edge weight between node (device) i and its neighboring node (neighboring device) j. It can be represented as:

[0068]

[0069] in: Represents a node and neighboring nodes Edge weights between them; Represents a node The average power consumption; Representing neighboring nodes The average power consumption; Represents a node Electricity consumption; Representing neighboring nodes Electricity consumption; Represents a node and neighboring nodes The practical importance of collaboration in the production process, as determined by experience or actual circumstances. and It is a weighting coefficient, and .

[0070] Ultimately, it is possible to... Normalization or further adjustments should be made to better reflect the relationship between actual production needs and equipment.

[0071] The diagram can be represented as ,in It is a set of nodes. It is a set of edges. Each node has a feature vector. , can be represented as: [Load, current, voltage, equipment status, ...]

[0072] The isomorphism of the graph is captured through a simple aggregation function. An important mechanism is introduced during feature aggregation, which enables it to better distinguish the structure of different nodes.

[0073] The feature aggregation of the GIN layer can be represented as:

[0074]

[0075] in: It is a node In the Layer feature representation; The ranges are 0, 1, 2, ..., L-1; L is the number of layers in the MLP network model.

[0076] It is the MLP network model. +1 layer output node Aggregated node features;

[0077] The edge weights serve as weighting coefficients for neighbor features. Features from neighboring nodes are weighted according to the edge weights to reflect the actual intensity of power flow and the importance of equipment collaboration, thereby making the node feature representation richer and more consistent with actual physical relationships.

[0078] It is a node The set of neighboring nodes;

[0079] These are learnable parameters used to control the impact of the current node's features on the aggregation result.

[0080] MLP is a multilayer perceptron used for further processing of aggregated features.

[0081] Furthermore, in the formula In the middle, node The lower-level features are composed of the features of its upper-level features and neighboring nodes. The features are aggregated from the previous layer. Therefore, the update of node features directly depends on the features of neighboring nodes, reflecting the dependencies between nodes in the graph structure.

[0082] edge weight Impact: Defines edges and their weights These weights reflect important information such as power flow between devices and load dependence, as shown in the formula. Features from neighboring nodes are weighted according to edge weights to reflect the actual intensity of power flow and the importance of equipment cooperation, thus making the node feature representation richer and more consistent with actual physical relationships.

[0083] Feature aggregation: In the feature aggregation of the above model, the features of the current node are combined with the features of its neighbors, allowing the model to better capture the local structural information of the node.

[0084] The set of neighboring nodes N(i) is defined based on the set of edges in the graph structure G=(V,E). Specifically:

[0085] Furthermore, for the current node Its neighbor set N(i) is the set of all nodes that are related to node i. via edge A set of directly connected nodes. In a power network scenario, nodes represent devices, and edges represent current flow relationships or load dependencies between devices. Therefore, neighboring nodes are those that are connected to the devices in terms of power flow or dependency. There are directly connected device nodes. This neighbor relationship can be quickly indexed using an adjacency matrix or adjacency list in the graph. For example, if the element Aij in the i-th row and j-th column of adjacency matrix A is not equal to 0, then the node... It is a node The neighbors.

[0086] Furthermore, the features of neighboring nodes are represented as follows: It is calculated by the model in the previous layer, that is, the neighboring nodes in the l-th layer model. The feature vectors. In the first layer (l=0), These are the raw input features, such as node load, current, voltage, and device status. In subsequent layers, It is a feature representation that has been accumulated and transformed by the previous layers, and incorporates more structural and neighbor information.

[0087] Furthermore, in the feature aggregation phase, the current node With all its neighboring nodes The features are combined to capture local structure and relational information. Based on the feature aggregation formula, the current node... When updating features, all its neighboring nodes are considered. The characteristics of this are described in the formula, which involves considering all neighbor nodes within the neighbor set N(i). Aggregation is achieved by summing features, i.e.: This means the current node The feature not only depends on its own current layer features, but also integrates the features of all its directly connected neighbor nodes. The characteristics of the nodes reflect the information of the nodes in the local structure.

[0088] Finally, by joining The features of a node are not completely replaced during the aggregation process, thus preserving the node's feature information.

[0089] Time series data processing: Time series data (such as historical load data) can be represented as a matrix. Each row corresponds to a feature of a time step (e.g., load of the past 24 hours, weather data, etc.).

[0090] Feature fusion: Combining the node features aggregated by the above model with time series features: in It is the node feature of the last layer, that is, when When it is L-1. Where, the symbol... This represents the concatenation operation of the feature matrices.

[0091] Specifically, node features are aggregated through multiple layers (such as GIN layers) to obtain node representations that are updated layer by layer. This refers to the final features after feature aggregation, often called "aggregated node features" or "updated node features." Therefore, what is fused here is the final "aggregated node features" output from all aggregation layers, rather than the initially extracted original node features.

[0092] The initial node features are the original inputs (e.g., load, current, voltage, etc.), represented as Through multiple GIN layers, hierarchical feature updates are generated, up to the Lth layer. This feature integrates neighbor node information and local structural information. The L-th layer feature representations of all nodes are used to form a matrix. Then, with the time series feature matrix The data is then spliced ​​and merged for subsequent load forecasting.

[0093] The prediction layer takes the combined features and inputs them into a fully connected layer for load prediction. in: This is the predicted load value. It is the weight matrix of the output layer. It is a bias term.

[0094] Model training is performed using mean squared error (MSE) as the loss function: in It is the sample size. This is the actual load value.

[0095] The deep neural network prediction model training method used in this invention is based on the backpropagation algorithm and gradient descent optimization technique. By iteratively adjusting network parameters, it improves the model's ability to fit and predict input data. Figure 2 As shown, the specific steps include:

[0096] Step S201: Data preprocessing: Normalize and standardize the node feature data and time series load data aggregated by the input model to ensure the stability of data distribution and improve training efficiency.

[0097] Step S202: Forward propagation: Input the preprocessed data into the deep neural network prediction model, and calculate the output prediction value after linear transformation and nonlinear activation function of each layer of neurons.

[0098] Step S203: Error Calculation: Calculate the difference between the predicted output and the actual load value using a defined loss function (such as mean squared error MSE) to quantify the prediction error of the model.

[0099] Step S204: Backpropagation: Based on the error value, the gradient of each layer's parameters is calculated using the chain rule, and the error information is propagated forward layer by layer to guide the parameter update direction.

[0100] Step S205: Parameter update: Use an optimization algorithm (such as Adam optimizer or stochastic gradient descent SGD) to adjust the network weights and biases according to the calculated gradient, and gradually reduce the prediction error.

[0101] Step S206: Training Iteration: Repeat the forward propagation, error calculation, back propagation and parameter update steps until the preset stopping conditions are met (such as reaching the maximum number of training rounds or the error convergence threshold).

[0102] Step S207: Model Validation and Tuning: Use an independent validation set to evaluate the performance of the trained model, and adjust hyperparameters (such as learning rate, batch size, number of network layers, etc.) to optimize the model performance and effectively prevent overfitting.

[0103] This application combines graph convolutional networks and time-series data-based load forecasting algorithms to fully leverage relationships between devices and historical load patterns, thereby improving the accuracy and robustness of load forecasting. This model design can adapt to complex electricity demand scenarios, providing better decision support for energy storage companies.

[0104] This application also provides an embodiment of a power load forecasting device based on structure-aware aggregation functions. Figure 3 A schematic diagram of a power load forecasting device based on a structure-aware aggregation function, according to an embodiment of this application, is shown. Figure 3 As shown, the device includes: an acquisition module configured to acquire the topological relationships between devices in a power system and construct a power system topology model based on the topological relationships between devices in the power system; an aggregation module configured to acquire the node features of each node in the power system topology model and the node features of its neighboring nodes, and aggregate the node features of each node in the power system topology model and the node features of its neighboring nodes based on a structure-aware aggregation function to obtain the aggregated node features of each node; a fusion processing module configured to acquire the historical time series features of each node in the power system topology model, and fuse the historical time series features of each node with the aggregated node features to obtain fused feature data of each node; and a prediction module configured to input the fused feature data of each node into a trained deep neural network prediction model to obtain the power load prediction result of each node.

[0105] The above is a schematic scheme of a power load forecasting device based on a structure-aware aggregation function according to this embodiment. It should be noted that the technical solution of this power load forecasting device based on a structure-aware aggregation function belongs to the same concept as the technical solution of the power load forecasting method based on a structure-aware aggregation function described above. Details not described in detail in the technical solution of the power load forecasting device based on a structure-aware aggregation function can be found in the description of the technical solution of the power load forecasting method based on a structure-aware aggregation function described above.

[0106] Figure 4 A structural block diagram of a computing device 400 according to an embodiment of this application is shown. The components of the computing device 400 include, but are not limited to, a memory 410 and a processor 420. The processor 420 is connected to the memory 410 via a bus 430, and a database 450 is used to store data.

[0107] The computing device 400 also includes an access device 440, which enables the computing device 400 to communicate via one or more networks 460. Examples of these networks include a Public Switched Telephone Network (PSTN), a Local Area Network (LAN), a Wide Area Network (WAN), a Personal Area Network (PAN), or a combination of communication networks such as the Internet. The access device 440 may include one or more of any type of wired or wireless network interface (e.g., a Network Interface Card (NIC)), such as an IEEE 802.11 Wireless Local Area Network (WLAN) interface, a Wi-MAX interface, an Ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a Bluetooth interface, a Near Field Communication (NFC) interface, and so on.

[0108] In one embodiment of this application, the aforementioned components of the computing device 400 and Figure 4 Other components, not shown, can also be connected to each other, for example, via a bus. It should be understood that... Figure 4 The block diagram of the computing device shown is for illustrative purposes only and is not intended to limit the scope of this application. Those skilled in the art can add or replace other components as needed.

[0109] The computing device 400 can be any type of stationary or mobile computing device, including mobile computers or mobile computing devices (e.g., tablet computers, personal digital assistants, laptop computers, notebook computers, netbooks, etc.), mobile phones (e.g., smartphones), wearable computing devices (e.g., smartwatches, smart glasses, etc.) or other types of mobile devices, or stationary computing devices such as desktop computers or PCs. The computing device 400 can also be a mobile or stationary server.

[0110] The processor 420 is configured to execute the following computer-executable instructions, which, when executed by the processor, implement the steps of the above-described power load forecasting method based on structure-aware aggregation functions.

[0111] The above is a schematic representation of a computing device according to this embodiment. It should be noted that the technical solution of this computing device belongs to the same concept as the technical solution of the power load forecasting method based on structure-aware aggregation functions described above. Details not described in detail in the technical solution of the computing device can be found in the description of the technical solution of the power load forecasting method based on structure-aware aggregation functions described above.

[0112] An embodiment of this application also provides a computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of the above-described power load forecasting method based on structure-aware aggregation functions.

[0113] The above is an illustrative scheme of a computer-readable storage medium according to this embodiment. It should be noted that the technical solution of this storage medium belongs to the same concept as the technical solution of the power load forecasting method based on structure-aware aggregation functions described above. Details not described in detail in the technical solution of the storage medium can be found in the description of the technical solution of the power load forecasting method based on structure-aware aggregation functions described above.

[0114] An embodiment of this application also provides a computer program, wherein when the computer program is executed in a computer, the computer is instructed to perform the steps of the above-described power load forecasting method based on structure-aware aggregation functions.

[0115] The above is an illustrative scheme of a computer program according to this embodiment. It should be noted that the technical solution of this computer program belongs to the same concept as the above-described power load forecasting method based on structure-aware aggregation functions. For details not described in detail in the technical solution of the computer program, please refer to the description of the above-described power load forecasting method based on structure-aware aggregation functions.

[0116] The foregoing has described specific embodiments of this application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired results. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0117] The computer instructions include computer program code, which may be in the form of source code, object code, executable file, or certain intermediate forms. The computer-readable medium may include any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium may be appropriately added to or subtracted according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media may not include electrical carrier signals and telecommunication signals.

[0118] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that the embodiments of this application are not limited to the described order of actions, because according to the embodiments of this application, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also understand that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the embodiments of this application.

[0119] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0120] The preferred embodiments disclosed above are merely illustrative of this application. The optional embodiments do not exhaustively describe all details, nor do they limit the invention to the specific implementations described. Clearly, many modifications and variations can be made based on the embodiments of this application. These embodiments are selected and specifically described in this application to better explain the principles and practical applications of the embodiments of this application, thereby enabling those skilled in the art to better understand and utilize this application. This application is limited only by the claims and their full scope and equivalents.

Claims

1. A method for power load forecasting based on structure-aware aggregation function, characterized in that, The method comprises the following steps: obtaining the topological relationship between devices in a power system, and constructing a power system topological model according to the topological relationship between devices in the power system, which comprises: modeling each device node in the power system as a node according to the topological relationship between devices in the power system, modeling the current flow relationship or load dependence relationship between devices as an edge, modeling the current flow or power consumption between devices as an edge weight, and modeling the device node having a current flow relationship or load dependence relationship with the device node as a neighbor node; and constructing a power system topological model according to all the nodes, edges, edge weights and neighbor nodes in the power system; obtaining the node features of each node in the power system topological model and the node features of the neighbor nodes thereof, and aggregating the node features of each node in the power system topological model and the node features of the neighbor nodes thereof based on a structure-aware aggregation function to obtain the aggregated node features of each node, which comprises: ； wherein: is the node feature of the i-th node in the MLP network model at the l-th layer; is the output of the i-th node in the MLP network model at the l-th layer; is the aggregated node feature; is the node feature of the i-th node in the MLP network model at the l-th layer; is the node feature of the i-th node in the MLP network model at the l-th layer; is the node feature of the i-th node in the MLP network model at the l-th layer; is the edge weight between the i-th node and the j-th neighbor node; is the edge weight between the i-th node and the j-th neighbor node; is the edge weight between the i-th node and the j-th neighbor node; is the learnable parameter; is the node feature of the i-th node in the MLP network model at the l-th layer; is the node feature of the i-th node in the MLP network model at the l-th layer; is the node feature of the i-th node in the MLP network model at the l-th layer; is the set of neighbor nodes of the i-th node; MLP is a multi-layer perception function; is an integer value of 0, 1, 2, …, L-1; L is the number of layers of the MLP network model. obtaining the historical time sequence features of each node in the power system topological model, and fusing the historical time sequence features of each node with the aggregated node features to obtain the fusion feature data of each node; inputting the fusion feature data of each node into a trained deep neural network prediction model to obtain the power load prediction result of each node, which comprises: ； wherein: is the power load prediction result of each node; Z is the fusion feature data of each node; is the weight matrix of the output layer of the deep neural network prediction model; is the bias term.

2. The method of claim 1, wherein, the historical time sequence features of each node are historical load time sequence features or historical weather data time sequence features.

3. The method of claim 1, wherein, The method further comprises: obtaining the topological relationship between devices in a plurality of power systems and the power load true results of each device, and constructing a power system topological model according to the topological relationship between devices in each power system; obtaining the node features of each node in the power system topological model and the node features of the neighbor nodes thereof, and aggregating the node features of each node in the power system topological model and the node features of the neighbor nodes thereof based on a structure-aware aggregation function to obtain the aggregated node features of each node; obtaining the historical time sequence features of each node in the power system topological model, and fusing the historical time sequence features of each node with the aggregated node features to obtain the fusion feature data of each node; training a deep neural network prediction model based on the fusion feature data of each node and the power load true results of each device to obtain the trained deep neural network prediction model.

4. A structural perception aggregation function based power load forecasting apparatus for implementing the method of any one of claims 1-3, characterized in that, The method comprises the following steps: an obtaining module configured to obtain the topological relationship between devices in a power system, and construct a power system topological model according to the topological relationship between devices in the power system; an aggregation module configured to obtain the node features of each node in the power system topological model and the node features of the neighbor nodes thereof, and aggregate the node features of each node in the power system topological model and the node features of the neighbor nodes thereof based on a structure-aware aggregation function to obtain the aggregated node features of each node; a fusion processing module configured to obtain historical time series features of each node in the power system topology model, and obtain fusion feature data of each node by fusing the historical time series features of each node with the aggregated node features; a prediction module configured to obtain power load prediction results of each node by inputting the fusion feature data of each node into a trained deep neural network prediction model. 5.A computing device, comprising: a memory and a processor; the memory is configured to store computer executable instructions, and the processor is configured to execute the computer executable instructions, which, when executed by the processor, implement the steps of the power load prediction method based on the structure-aware aggregation function according to any one of claims 1 to 3. 6.A computer readable storage medium storing computer executable instructions, which, when executed by a processor, implement the steps of the power load prediction method based on the structure-aware aggregation function according to any one of claims 1 to 3.

Images