Power load prediction method and device based on graph convolutional neural network and time series fusion

Abstract

The embodiment of the application provides a power load prediction method and device based on graph convolutional neural network and time series fusion, which comprises the following steps: acquiring 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; acquiring the node features of each node in the power system topological model, and updating the node features of each node in the power system topological model based on a graph convolutional neural network to obtain the updated node features of each node; acquiring the historical time series features of each node in the power system topological model, and obtaining the fusion feature data of each node by fusing the historical time series features of each node with the updated node features; and 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.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to a power load prediction method and device based on graph convolutional neural network and time series fusion. BACKGROUND

[0002] In the modern power system, there are many methods for current power load prediction. Traditional prediction methods such as regression analysis, time series method, and grey model have certain effects and stability when dealing with simple and linear load changes. However, these methods often fail to accurately capture the complex nonlinear characteristics and uncertainty factors of power load. Intelligent prediction methods such as artificial neural networks, support vector machines, and fuzzy logic have certain advantages in dealing with complex relationships, but also have some limitations, such as neural networks being prone to local optimal solutions, leading to inaccurate prediction results. In addition, existing technologies only rely on historical load data and historical device power data, but do not comprehensively depict the overall operation system of the factory, and the correlation between them is missing, which affects the prediction accuracy. SUMMARY

[0003] Therefore, the embodiments of the present application provide a power load prediction method based on graph convolutional neural network and time series fusion. One or more embodiments of the present application also relate to a power load prediction device based on graph convolutional neural network and time series fusion, a computing device, a computer-readable storage medium, and a computer program to solve the technical defects in the prior art.

[0004] According to a first aspect of the embodiments of the present application, a power load prediction method based on graph convolutional neural network and time series fusion is provided, comprising:

[0005] Obtaining the topological relationship between devices in the power system, and constructing a power system topological model according to the topological relationship between devices in the power system;

[0006] Obtaining the node features of each node in the power system topological model, and updating the node features of each node in the power system topological model based on a graph convolutional neural network to obtain updated node features of each node;

[0007] Obtaining the historical time series features of each node in the power system topological model, and obtaining fusion feature data of each node by fusing the historical time series features of each node with the updated node features;

[0008] Obtaining the power load prediction result of each node by inputting the fusion feature data of each node into a trained deep neural network prediction model.

[0009] Preferably, the constructing a power system topology model according to the topological relationship between devices in the power system comprises:

[0010] According to 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, and the current flow, power consumption or other metrics between devices are modeled as edge weights;

[0011] According to all the nodes, edges and edge weights in the power system, a power system topology model is constructed.

[0012] Preferably, the edge weights comprise:

[0013]

[0014] wherein: denotes the edge weight between node and node ; denotes the average consumption power of node ; denotes the average consumption power of node ; denotes the power consumption of node ; denotes the power consumption of node ; denotes the actual cooperation importance of node and node in the production process, which is set by experience or actual situation; and are weight coefficients, and .

[0015] Preferably, the updating the node features of each node in the power system topology model based on the graph convolutional neural network comprises:

[0016]

[0017] wherein: is the updated node feature of each node output by the layer in the graph convolutional neural network; is the number of layers of the graph convolutional neural network; is the node feature of each node input into the graph convolutional neural network; is the normalized adjacency matrix of each node; A is the adjacency matrix of each node; D is the degree matrix of each node; is the updated node feature of each node output by the layer in the graph convolutional neural network;a weight matrix of a layer, is an activation function.

[0018] Preferably, the historical time series feature of each node is a historical load time series feature or a historical weather data time series feature.

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

[0020]

[0021] wherein: is the power load prediction result of each node; Z is the fusion feature data of each node; is a weight matrix of an output layer of the deep neural network prediction model; is a bias term.

[0022] Preferably, the method further comprises:

[0023] obtaining a topological relationship between devices in a plurality of power systems and a real result of power load of each device, and constructing a power system topological model according to the topological relationship between devices in each power system;

[0024] obtaining node features of each node in the power system topological model, and updating the node features of each node in the power system topological model based on a graph convolutional neural network to obtain updated node features of each node;

[0025] obtaining historical time series features of each node in the power system topological model, and obtaining fusion feature data of each node by fusing the historical time series features of each node with the updated node features;

[0026] training a deep neural network prediction model based on the fusion feature data of each node and the real result of power load of each device to obtain the trained deep neural network prediction model.

[0027] According to a second aspect of the embodiments of the present application, a power load prediction device based on a graph convolutional neural network and time series fusion is provided, comprising:

[0028] an obtaining module configured to obtain a 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;

[0029] an updating module configured to obtain a node feature of each node in the power system topology model, and update the node feature of each node in the power system topology model based on a graph convolutional neural network to obtain an updated node feature of each node;

[0030] a fusion processing module configured to obtain a historical time series feature of each node in the power system topology model, and obtain a fusion feature data of each node by fusing the historical time series feature of each node with the updated node feature;

[0031] a prediction module configured to input the fusion feature data of each node into a trained deep neural network prediction model to obtain a power load prediction result of each node.

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

[0033] a memory and a processor;

[0034] the memory is configured to store computer executable instructions, and the processor is configured to execute the computer executable instructions to implement the steps of any one of the power load prediction methods based on graph convolutional neural network and time series fusion.

[0035] According to a fourth aspect of the embodiments of the present application, a computer readable storage medium is provided, which stores computer executable instructions, and the instructions are executed by a processor to implement the steps of any one of the power load prediction methods based on graph convolutional neural network and time series fusion.

[0036] According to a fifth aspect of the embodiments of the present application, a computer program is provided, and when the computer program is executed in a computer, the computer is caused to perform the steps of the power load prediction method based on graph convolutional neural network and time series fusion.

[0037] The power load prediction scheme based on the graph convolutional neural network and time sequence fusion provided in the embodiment of the application comprises the following steps: acquiring a topological relationship between devices in a power system, and constructing a power system topological model according to the topological relationship between the devices in the power system; acquiring node features of each node in the power system topological model, and updating the node features of each node in the power system topological model based on a graph convolutional neural network to obtain updated node features of each node; acquiring historical time sequence features of each node in the power system topological model, and performing fusion processing on the historical time sequence features of each node and the updated node features to obtain fusion feature data of each node; and inputting the fusion feature data of each node into a trained deep neural network prediction model to obtain a power load prediction result of each node. The power load prediction scheme based on the graph convolutional neural network and time sequence fusion provided in the embodiment of the application aims to improve the accuracy and robustness of load prediction by fully mining the topological relationship between devices and the historical load change rule. The method can effectively adapt to complex and changeable power demand scenarios, improve the precision and stability of load prediction, thereby providing scientific and reliable technical support for energy storage enterprises in power dispatching, energy storage management and operation decision-making, and promoting the efficient operation and resource optimization configuration of the power system. BRIEF DESCRIPTION OF DRAWINGS

[0038] Figure 1 is a flowchart of a power load prediction method based on a graph convolutional neural network and time sequence fusion provided in an embodiment of the application;

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

[0040] Figure 3 is a schematic diagram of a power load prediction device based on a graph convolutional neural network and time sequence fusion provided in an embodiment of the application;

[0041] Figure 4 is a structural block diagram of a computing device provided in an embodiment of the application. DETAILED DESCRIPTION

[0042] In the following description, many specific details are set forth in order to provide a thorough understanding of the application. However, the application can be practiced without the specific details, and it is understood that the application can be practiced in a variety of ways beyond those described herein, which will be apparent to those skilled in the art, without departing from the spirit and scope of the application.

[0043] The terminology used in this disclosure of one or more embodiments is for the purpose of describing particular embodiments only and is not intended to be limiting of one or more embodiments. As used in this disclosure and the appended claims, the singular forms "a," "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that the term "and / or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.

[0044] It will be understood that, although the terms first, second, etc. can be used herein to describe various information, these terms are not intended to denote a temporal sequence. Rather, these terms are used only as distinguish one from another. For example, without departing from the scope of one or more embodiments, first can be termed second, and similarly, second can be termed first. The word "if' as used herein means "when" or "upon" or "in response to the determination" depending on the context.

[0045] In the present application, a power load prediction method based on graph convolutional neural network and time series fusion is provided, and the present application simultaneously relates to a power load prediction device based on graph convolutional neural network and time series fusion, a computing device, a computer readable storage medium, and a computer program, which are described in detail one by one in the following embodiments.

[0046] Figure 1 A flowchart of a power load prediction method based on graph convolutional neural network and time series fusion according to one embodiment of the present application is shown, which specifically includes the following steps.

[0047] Step S101: 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;

[0048] In an optional implementation, the step of constructing a power system topological model according to the topological relationship 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, and modeling the current flow, power consumption or other metrics between devices as an edge weight according to the topological relationship between devices in the power system; and constructing a power system topological model according to all the nodes, edges and edge weights in the power system.

[0049] Further, the edge weight includes:

[0050]

[0051] wherein: Represents a node and nodes Edge weights between them; Represents a node The average power consumption; Represents a node The average power consumption; Represents a node Electricity consumption; Represents a node Electricity consumption; Represents a node and 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 update the node features of each node in the power system topology model based on the graph convolutional neural network to obtain the updated node features of each node;

[0053] In one optional implementation, the step of updating the node features of each node in the power system topology model based on a graph convolutional neural network to obtain the updated node features of each node includes:

[0054]

[0055] in: It is the first in a graph convolutional neural network The updated node features of each node output by the layer; It represents the number of layers in a graph convolutional neural network; It represents the node features of each node in the input of a graph convolutional neural network; A is the normalized adjacency matrix of each node; D is the degree matrix of each node. It is the first in a graph convolutional neural network The weight matrix of the layer, It is an activation function.

[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 updated 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: obtaining the power load prediction result of each node by inputting the fusion feature data of each node into the trained deep neural network prediction model.

[0059] In an optional implementation, the obtaining the power load prediction result of each node by inputting the fusion feature data of each node into the trained deep neural network prediction model comprises:

[0060]

[0061] 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.

[0062] In an optional implementation, the method further comprises: obtaining the topological relationship between devices in a plurality of power systems and the real result of the power load of each device, and constructing a power system topological model according to the topological relationship between devices in each power system; obtaining the node feature of each node in the power system topological model, and updating the node feature of each node in the power system topological model based on a graph convolutional neural network to obtain the updated node feature of each node; obtaining the historical time series feature of each node in the power system topological model, and obtaining the fusion feature data of each node by fusing the historical time series feature of each node and the updated node feature; training a deep neural network prediction model based on the fusion feature data of each node and the real result of the power load of each device to obtain the trained deep neural network prediction model.

[0063] The power load prediction scheme based on the graph convolutional neural network and time series fusion provided by the embodiments of the present application aims to improve the accuracy and robustness of load prediction by fully mining the topological relationship between devices and the historical load change rule. The method can effectively adapt to complex and variable power demand scenarios, improve the accuracy and stability of load prediction, thereby providing scientific and reliable technical support for energy storage enterprises in power dispatching, energy storage management and operation decision-making, and promoting the efficient operation and resource optimization of the power system.

[0064] The technical solutions of the present application will be further described below

[0065] The definition of nodes and edges, each device (such as a machine, a sensor, etc.) will be a node The edge The edge and devices between the devices. The weight of an edge can be based on the current flow, power consumption or other related metrics between the devices.

[0066] Example: In a production system, containing energy storage devices , production devices , and other non-power consuming devices (such as trucks, forklifts, etc. auxiliary equipment). The connection weight between these devices can be determined according to the comprehensive proportion of their power consumption and consumption power, and combined with their actual importance in the production process to make empirical adjustments.

[0067] Specifically, the edge weight between device and device can be represented as:

[0068]

[0069] where: denotes the edge weight between node and node ; denotes the average power consumption of node ; denotes the average power consumption of node ; denotes the power consumption of node ; denotes the power consumption of node ; denotes the actual cooperation importance of node and node in the production process, which is set by experience or actual situation; and are weight coefficients, and .

[0070] Finally, the can be normalized or further adjusted to better reflect the actual production needs and the relationship between devices.

[0071] The graph can be represented as , where is the node set, is the edge set. Each node has a feature vector , which can be represented as: [load, current, voltage, device state,...].

[0072] The basic idea of graph convolutional neural network is to update the features of nodes through the neighbor information of nodes. Given a graph , the layers of GCN can be represented by the following formula: where: is the node feature matrix of the th layer. is the normalized adjacency matrix, is the adjacency matrix, is the degree matrix. is the weight matrix of the th layer, is the activation function (such as ReLU).

[0073] where the adjacency matrix is a matrix (of size , the number of nodes), which describes which nodes in the graph are connected. indicates that node and node have an edge connected; indicates that node and node have no connection.

[0074] The degree matrix is also a diagonal matrix. Each element on the diagonal is the degree of node (i.e., how many edges the node has). For example, if the th node is connected to 3 nodes, then .

[0075] By stacking multiple GCN layers, deeper features can be extracted: Here, is the number of layers of GCN, which is 2 in this case, is the input feature matrix.

[0076] The time series data (such as historical load data) is represented as a matrix , where each row corresponds to the features of a time step (e.g.: past 24 hours of load, weather data, etc.).

[0077] Combine the node features extracted by the graph convolution network with the time series features: where the symbol represents the concatenation operation of the feature matrix.

[0078] The prediction layer will input the combined features into a fully connected layer for load prediction: where: is the predicted load value. is the weight matrix of the output layer. is a bias term.

[0079] The model is trained using mean square error (MSE) as the loss function: where is the number of samples, is the true load value.

[0080] The deep neural network prediction model training method used in the present application is based on the back propagation algorithm and gradient descent optimization technique. By iteratively adjusting the network parameters, the fitting and prediction ability of the model for input data is improved, as shown in Figure 2 The specific steps include:

[0081] Step S201: Data preprocessing: normalize and standardize the input graph structure data and time series load data to ensure data distribution stability and improve training efficiency.

[0082] Step S202: Forward propagation: input the preprocessed data into the deep neural network prediction model, and perform linear transformation and nonlinear activation function on each layer of neurons to calculate the output prediction value.

[0083] Step S203: Error calculation: use the defined loss function (such as mean square error MSE) to calculate the difference between the predicted output and the true load value, and quantify the prediction error of the model.

[0084] Step S204: Back propagation: based on the error value, use the chain rule to calculate the gradient of each layer parameter, and pass the error information layer by layer to guide the parameter update direction.

[0085] Step S205: Parameter update: use optimization algorithms (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.

[0086] Step S206: Training iteration: repeat the forward propagation, error calculation, back propagation and parameter update steps until the preset stopping condition (such as reaching the maximum training rounds or error convergence threshold) is met.

[0087] Step S207: Model verification and tuning: use an independent validation set to evaluate the performance of the trained model, adjust hyperparameters (such as learning rate, batch size, network layer number, etc.) to optimize the model effect, and effectively prevent overfitting phenomenon.

[0088] The present application combines the graph convolution network and the load prediction algorithm of time series data, which can fully utilize the relationship between devices and historical load patterns, improve the accuracy and robustness of load prediction. The model designed in this way can adapt to complex power demand scenarios and provide better decision support for energy storage enterprises.

[0089] The application also provides an electric load prediction device based on graph convolutional neural network and time series fusion, Figure 3 A structural schematic diagram of an electric load prediction device based on graph convolutional neural network and time series fusion is shown, which is provided by an embodiment of the application. As shown in the figure, Figure 3 The device comprises:

[0090] The acquisition module is configured to acquire the topological relationship between devices in the power system, and construct a power system topological model according to the topological relationship between devices in the power system;

[0091] The update module is configured to acquire the node features of each node in the power system topological model, and update the node features of each node in the power system topological model based on a graph convolutional neural network to obtain the updated node features of each node;

[0092] The fusion processing module is configured to acquire the historical time series features of each node in the power system topological model, and fuse the historical time series features of each node with the updated node features to obtain the fusion feature data of each node;

[0093] The prediction module is configured to input the fusion feature data of each node into a trained deep neural network prediction model to obtain the electric load prediction result of each node.

[0094] The above is a schematic scheme of an electric load prediction device based on graph convolutional neural network and time series fusion. It should be noted that the technical scheme of the electric load prediction device based on graph convolutional neural network and time series fusion is the same as the technical scheme of the electric load prediction method based on graph convolutional neural network and time series fusion described above. The details of the technical scheme of the electric load prediction device based on graph convolutional neural network and time series fusion which are not described in detail can be referred to the description of the technical scheme of the electric load prediction method based on graph convolutional neural network and time series fusion.

[0095] Figure 4 A structural block diagram of a computing device 400 is shown, which is provided by an embodiment of the application. 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 with the memory 410 through a bus 430, and a database 450 is used to save data.

[0096] The computing device 400 also includes an access device 440 that enables the computing device 400 to communicate via one or more networks 460. Examples of such networks include public switched telephone networks (PSTNs), local area networks (LANs), wide area networks (WANs), personal area networks (PAN), or combinations of such networks, such as the Internet. The access device 440 can include one or more of any type of network interface (for example, network interface cards (NICs)) such as IEEE 802.11 wireless local area network (WLAN) wireless interfaces, Worldwide Interoperability Microwave Access (Wi-MAX) interfaces, Ethernet interfaces, Universal Serial Bus (USB) interfaces, cellular network interfaces, Bluetooth interfaces, near-field communication (NFC) interfaces, and the like, either wired or wireless.

[0097] In an embodiment of the present application, the above-mentioned components of the computing device 400, as well as other components not shown in FIG. 4, can be connected to each other by a bus, for example. Figure 4 It should be understood that the computing device structure diagram shown is for the purpose of example only, and is not a limitation on the scope of the present application. Other components can be added or replaced as needed by those skilled in the art. Figure 4 It should be understood that the computing device structure diagram shown is for the purpose of example only, and is not a limitation on the scope of the present application. Other components can be added or replaced as needed by those skilled in the art.

[0098] The computing device 400 can be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (for example, a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, and the like), a mobile phone (for example, a smartphone), a wearable computing device (for example, a smart watch, smart glasses, and the like), or other types of mobile devices, or a stationary computing device such as a desktop computer or PC. The computing device 400 can also be a mobile or stationary server.

[0099] The processor 420 is configured to execute computer-executable instructions, which, when executed by the processor, implement the steps of the power load prediction method based on graph convolutional neural network and time series fusion described above.

[0100] The above is a schematic scheme of a computing device according to an embodiment of the present application. It should be noted that the technical scheme of the computing device belongs to the same concept as the technical scheme of the power load prediction method based on graph convolutional neural network and time series fusion described above, and the details of the technical scheme of the computing device that are not described in detail can be referred to the description of the technical scheme of the power load prediction method based on graph convolutional neural network and time series fusion described above.

[0101] An embodiment of the present application also provides 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 graph convolutional neural network and time series fusion described above.

[0102] The above is a schematic scheme of the computer readable storage medium of the embodiment. It should be noted that the technical scheme of the storage medium and the technical scheme of the power load prediction method based on graph convolutional neural network and time series fusion described above belong to the same concept, and the details of the technical scheme of the storage medium which are not described in detail can be seen from the description of the technical scheme of the power load prediction method based on graph convolutional neural network and time series fusion.

[0103] An embodiment of the present application also provides a computer program, wherein the computer program causes a computer to execute the steps of the power load prediction method based on graph convolutional neural network and time series fusion when the computer program is executed in the computer.

[0104] The above is a schematic scheme of the computer program of the embodiment. It should be noted that the technical scheme of the computer program and the technical scheme of the power load prediction method based on graph convolutional neural network and time series fusion described above belong to the same concept, and the details of the technical scheme of the computer program which are not described in detail can be seen from the description of the technical scheme of the power load prediction method based on graph convolutional neural network and time series fusion.

[0105] The specific embodiments of the present application are described above. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in a different order and still achieve desirable results. In addition, the processes depicted in the figures do not necessarily require the particular order shown or sequential order to achieve desirable results. In certain implementations, multitasking and parallel processing can be advantageous.

[0106] The computer readable medium can include any entity or device capable of carrying the computer program code, a recording medium, a USB flash disk, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunications signal, and a software distribution medium, etc. It should be noted that the contents included in the computer readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practices in the jurisdiction, for example, in some jurisdictions, according to legislation and patent practices, the computer readable medium does not include electrical carrier signals and telecommunications signals.

[0107] It should be noted that, for the foregoing method embodiments, the sequences of the described actions are merely illustrative, and the application embodiments are not limited to the sequences of the described actions. In some embodiments, the sequences of the described actions can be changed or performed at the same time. In addition, the application embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the application embodiments.

[0108] In the above embodiments, the description of each embodiment is focused on different aspects, and the parts not described in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0109] The preferred embodiments of the application disclosed above are only used to help explain the application. The alternative embodiments do not describe all the details and limit the application to the specific embodiments described. Obviously, according to the content of the application embodiments, many modifications and changes can be made. The application selects and describes these embodiments in order to better explain the principles and practical applications of the application embodiments, so that those skilled in the art can well understand and use the application. The application is limited by the claims and their entire scope and equivalents.

Claims

1. A power load prediction method based on graph convolutional neural network and time series fusion, 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, and modeling the current flow, power consumption or other metrics between devices as an edge weight; constructing a power system topological model according to all the nodes, edges and edge weights in the power system; wherein the edge weight comprises: ； wherein: denotes the edge weight between nodes and nodes ; denotes the average consumed power of nodes ; denotes the average consumed power of nodes ; denotes the power consumption of nodes ; denotes the power consumption of nodes ; denotes the actual importance of cooperation between nodes and nodes in the production process, which is set by experience or actual situation; and are weight coefficients, and ; obtaining the node features of each node in the power system topological model, and updating the node features of each node in the power system topological model based on a graph convolutional neural network to obtain the updated node features of each node, which comprises: ； wherein: is the updated node feature of each node output by the layer of the graph convolutional neural network; is the number of layers of the graph convolutional neural network; is the node feature of each node input to the graph convolutional neural network; is the normalized adjacency matrix of each node; A is the adjacency matrix of each node; D is the degree matrix of each node; is the weight matrix of the layer of the graph convolutional neural network, is an activation function; obtaining the historical time series features of each node in the power system topological model, and obtaining the fusion feature data of each node by fusing the historical time series features of each node with the updated node features; obtaining the power load prediction result of each node by inputting the fusion feature data of each node into a trained deep neural network prediction model.

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

3. The method of claim 1, wherein, The power load prediction result of each node obtained by inputting the fusion feature data of each node into the trained deep neural network prediction model 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.

4. The method of claim 1, wherein, The method further comprises the following steps: 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 updating the node features of each node in the power system topological model based on a graph convolutional neural network to obtain the updated node features of each node; obtaining the historical time series features of each node in the power system topological model, and obtaining the fusion feature data of each node by fusing the historical time series features of each node with the updated node features; 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.

5. A power load forecasting device based on graph convolutional neural network and time series fusion, the device is used to realize the method of any one of claims 1-4, 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 updating module configured to obtain the node features of each node in the power system topological model, and update the node features of each node in the power system topological model based on a graph convolutional neural network to obtain the updated 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 updated 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.

6. 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 graph convolutional neural network and time series fusion according to any one of claims 1 to 4.

7. 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 graph convolutional neural network and time series fusion according to any one of claims 1 to 4.

Images