Energy scheduling method, device, storage medium and program product

Abstract

The present application discloses an energy scheduling method, device, storage medium and program product. Among them, the method constructs an energy topology map according to the connection status of each energy router in the target energy network, and constructs an adjacency matrix based on the energy topology map, and constructs a feature matrix according to the current state information of each energy router at the current moment; the adjacency matrix and the feature matrix are input into the pre-trained target graph neural network model to determine the predicted state information of each energy router at the next moment; wherein the predicted state information only includes the predicted carbon emissions of each energy router; if the predicted carbon emissions exceed the preset carbon quota, at least one external energy is obtained from the external power grid; based on the energy topology map, the external energy is assigned a path to determine the energy scheduling strategy of the target energy network at the next moment. This technical solution, through the graph neural network, realizes the dynamic prediction of the state of each energy router in the energy network, and timely adjusts the scheduling strategy of the external energy to improve energy utilization.

Description

Technical Field

[0001] The present application relates to the technical field of energy system optimization control, and in particular to an energy scheduling method, device, storage medium and program product. Background Art

[0002] As the world pays more attention to environmental protection and sustainable energy development, the scale of renewable energy utilization continues to expand. Since renewable energy is intermittent, volatile and decentralized, energy routers, as the core equipment for energy and information exchange in energy networks, can realize the conversion and storage of different energy sources to meet user energy needs and reduce energy transmission losses.

[0003] However, since the campus energy network will face various changes in the external environment during operation, such as changes in transmission voltage, electricity prices, and the number of users, the existing energy router scheduling scheme needs to be adjusted at all times as the status information changes. This not only consumes a lot of transmission costs, but also cannot guarantee the real-time and accuracy of the scheduling strategy.

[0004] Therefore, how to provide a technical solution that can perform energy scheduling in a timely and accurate manner is a technical problem that needs to be urgently solved by technical personnel in this field. Summary of the invention

[0005] The present application provides an energy scheduling method, device, medium and product, which uses a graph neural network to achieve dynamic prediction of the status of each energy router in the energy network, and timely adjust the scheduling strategy of external energy to improve energy utilization.

[0006] According to a first aspect of the present application, there is provided an energy scheduling method, the method comprising:

[0007] According to the connection status of each energy router in the target energy network, an energy topology map is constructed, and an adjacency matrix is ​​constructed based on the energy topology map, and a feature matrix is ​​constructed according to the current state information of each energy router at the current moment;

[0008] Inputting the adjacency matrix and the feature matrix into a pre-trained target graph neural network model to determine the predicted state information of each energy router at the next moment; wherein the predicted state information at least includes the predicted carbon emissions of each energy router;

[0009] If the carbon emissions exceed the preset carbon quota, obtaining at least one external energy source from an external power grid; wherein the external energy source is green energy;

[0010] Based on the energy topology map, the external energy is assigned a path, and the energy scheduling strategy of the target energy network at the next moment is determined.

[0011] According to the second aspect of the present application, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the energy scheduling method described in the first aspect of the present application.

[0012] According to a third aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the energy scheduling method described in the first aspect of the present application when executed.

[0013] According to a fourth aspect of the present application, a computer program product is provided, wherein the computer program product comprises a computer program, and when the computer program is executed by a processor, the energy scheduling method described in the first aspect of the present application is implemented.

[0014] The technical solution provided by the present application is to construct an energy topology map according to the connection status of each energy router in the target energy network, and to construct an adjacency matrix based on the energy topology map, and to construct a feature matrix based on the current state information of each energy router at the current moment; the adjacency matrix and the feature matrix are input into the pre-trained target graph neural network model to determine the predicted state information of each energy router at the next moment; wherein the predicted state information only includes the predicted carbon emissions of each energy router; if the carbon emissions exceed the preset carbon quota, at least one external energy source is obtained from the external power grid; based on the energy topology map, the external energy source is assigned a path to determine the energy scheduling strategy of the target energy network at the next moment. This technical solution, through the graph neural network, realizes the dynamic prediction of the state of each energy router in the energy network, and timely adjusts the scheduling strategy of the external energy source to improve energy utilization.

[0015] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0017] Figure 1A flowchart of an energy scheduling method provided in Example 1 of the present application.

[0018] Figure 2 A schematic diagram of the structure of an energy network provided in Example 1 of the present application.

[0019] Figure 3 A flow chart of an energy scheduling method provided in Example 2 of the present application.

[0020] Figure 4 It is a structural diagram of a device for implementing an energy scheduling method in an embodiment of the present application. DETAILED DESCRIPTION

[0021] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0022] It should be noted that the terms "current", "next", "target", "initial", "prediction", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0023] Embodiment 1

[0024] Figure 1 This is a flow chart of an energy scheduling method provided in the first embodiment of the present application. This embodiment is applicable to the case where external energy is scheduled between energy routers. The method can be executed by an energy scheduling device. The energy scheduling device can be implemented in the form of hardware and / or software. The energy scheduling device can be configured in a device with data processing capabilities. Figure 1 As shown, the method includes the following steps.

[0025] S110, constructing an energy topology map according to the connection status of each energy router in the target energy network, constructing an adjacency matrix based on the energy topology map, and constructing a feature matrix according to the current state information of each energy router at the current moment.

[0026] Among them, the target energy network can be the energy supply and distribution network of a designated area, which usually includes the conversion, transmission and distribution equipment of energy such as electricity, heat, and gas.

[0027] Energy routers can be smart devices in energy networks, used to convert, transmit and distribute energy within a specified node range in the energy network. For example, in a factory campus energy network, energy routers can dispatch energy for a single factory.

[0028] The energy topology diagram can be a graphical structure of the connection relationship between each energy router in the energy network, which is used to show the transmission path of energy in the network and the relationship between devices. In the energy topology diagram, the node represents the energy router, and the edge represents that power can be transmitted between two energy routers.

[0029] Specifically, the nodes in the energy topology map and the edges between the nodes can be determined by determining whether there are physical lines or relevant technical conditions for power transmission between the energy routers in the target energy network. For example, assuming that there are 5 energy routers in the target energy network, marked as A, B, C, D and E, if there is a line between A and B that can realize power transmission, use an edge to connect the two nodes A and B in the energy topology map. Similarly, determine the connection status between other nodes, and finally obtain the energy topology map of the target energy network.

[0030] The adjacency matrix can be used to represent the matrix of the adjacent relationship between nodes in the energy topology graph. For an energy topology graph with n energy routers, its adjacency matrix is ​​an n*n matrix, where the matrix element (i, j) can indicate whether there is an edge between node i and node j. If there is an edge connection, the element value is usually 1, and if there is no edge connection, the element value is 0. It should be noted that in a directed graph, the matrix element (i, j) indicates whether there is an edge from node i to node j, and the case from node j to node i needs to be considered separately; in an undirected graph, the adjacency matrix can be a symmetric matrix.

[0031] Specifically, each node in the energy topology graph may be traversed one by one to determine the connection between each node, thereby determining the adjacency matrix.

[0032] For each energy router, the current status information of each energy router at the current moment can be obtained through various sensors installed on the energy router and related operation and production records.

[0033] Sensors such as electricity metering sensors, carbon emission monitoring equipment, etc.

[0034] The current state information may include the load power, power of the power generation equipment, voltage of the microgrid, etc. in the microgrid connected to the energy router, and may also include the energy transmission efficiency, maximum load capacity, maximum power generation capacity, etc. of the line connected to the energy router. Optionally, the current state information includes at least one of the carbon emissions, power consumption, adjacent node transmission cost, and transmission line length of each energy router at the current moment.

[0035] The feature matrix can be a collection of the current state information of each energy router. For example, if an energy network has n energy routers and each energy router has m current state information, then the feature matrix can be an n*m matrix. In this feature matrix, the element X ij It can represent the jth current state information of the i-th energy router.

[0036] The present application represents the energy topology map and current status information in the form of a matrix, thereby facilitating the subsequent processing of information data in the target energy network.

[0037] S120. Input the adjacency matrix and the feature matrix into a pre-trained target graph neural network model to determine the predicted state information of each energy router at the next moment.

[0038] The predicted state information at least includes the predicted carbon emissions of each of the energy routers.

[0039] The target graph neural network model can be a model obtained after training and learning the status information and connection information of each energy router in the target energy network, and can predict the status information of each energy router in the target energy network at future times.

[0040] The target graph neural network model can be composed of multiple graph convolutional layers and activation functions, and the feature vector of the node is updated iteratively to achieve node analysis and prediction. Common graph neural network models include graph convolutional neural networks, graph attention networks, etc.

[0041] Specifically, the adjacency matrix and the feature matrix can be input into a pre-trained target graph neural network model to output the predicted carbon emissions of each energy router at the next moment.

[0042] Optionally, the training process of the target graph neural network model includes: obtaining a historical data set of each energy router in the target energy network; the historical data includes a historical adjacency matrix and a historical feature matrix; inputting the historical data set into the initial graph neural network model for training, adjusting the parameters of the initial graph neural network model, and obtaining the target graph neural network model.

[0043] Specifically, the historical data set can be divided into a training set and a validation set. The initial graph neural network model is trained with the training set, and the trained model is evaluated with the validation set. The above steps are repeated until the preset requirements of the model are met to obtain the target graph neural network model.

[0044] S130: If the predicted carbon emissions exceed the preset carbon quota, obtaining at least one external energy source from an external power grid.

[0045] Wherein, the external energy is green energy.

[0046] The preset carbon quota can be a greenhouse gas emission cap set in advance for each company to limit the amount of carbon that each company can emit.

[0047] The carbon quota of the enterprise that each energy router is responsible for is also different. Therefore, in this application, the predicted carbon emissions of each energy router and the corresponding preset carbon quota can be compared respectively. If there is an energy router whose predicted carbon emissions exceed the preset carbon quota, the energy of the enterprise responsible for the energy router needs to be re-planned and dispatched to meet the requirements of the preset carbon quota.

[0048] If the predicted carbon emissions exceed the preset carbon quota, it means that the energy router is responsible for the enterprise's current energy configuration and operation mode no longer meet the carbon emission standards, which may be due to the high carbon emissions of the energy it connects to or the energy utilization efficiency. Therefore, this application introduces green energy from the external power grid to replace or supplement the current energy used, thereby reducing the overall carbon emissions.

[0049] like Figure 2 The figure shows a schematic diagram of the structure of an energy network provided in an embodiment of the present application. The energy network is composed of an external power grid, a control center and an internal energy network, wherein the internal energy network is composed of a number of energy routers, and the external power grid includes photovoltaic energy, wind power energy, hydropower energy and other green energy.

[0050] Specifically, the control center analyzes and predicts the status information of each energy router in the internal energy network at the current moment, and when the predicted carbon emissions of the energy router at the next moment exceed the carbon quota, it purchases a certain amount of external energy, such as at least one of photovoltaic, wind power, and hydropower, from the external power grid.

[0051] Optionally, before obtaining at least one external energy source from the external power grid, the method also includes: if the predicted carbon emissions exceed the preset carbon quota, determining the excess carbon emissions based on the predicted carbon emissions and the preset carbon quota; and determining the amount of electricity to be supplied of at least one external energy source based on the excess carbon emissions.

[0052] Specifically, the predicted carbon emissions can be subtracted from the preset carbon quota to determine the excess carbon emissions. For example, if the preset carbon quota of an energy router is 100 kg of carbon dioxide per day, and the predicted carbon emissions are 120 kg of carbon dioxide, the excess carbon emissions are 20 kg of carbon dioxide.

[0053] Different types of energy have different carbon emission coefficients, that is, the amount of carbon emissions produced per unit of energy is different. For example, the amount of carbon dioxide produced per kilowatt-hour by hydropower is almost negligible, the carbon emission coefficient of wind power is usually around 0-0.01 kg of carbon dioxide / kilowatt-hour, and the carbon emission coefficient of solar photovoltaic power generation is also very low, about 0.02-0.05 kg of carbon dioxide / kilowatt-hour. If the carbon emission coefficients of various external energy sources are known, the amount of electricity to be supplied by the external energy source can be calculated based on the excess carbon emissions to offset the excess carbon emissions.

[0054] It should be noted that when using external energy, energy routers also need to consider energy conversion efficiency. For example, converting the AC power of the external power grid into the DC power required by internal devices may result in energy loss.

[0055] Optionally, the amount of electricity to be supplied of at least one external energy source is determined based on the excess carbon emissions, including: determining the total amount of electricity to be supplied based on the excess carbon emissions; determining the amount of electricity to be supplied of at least one external energy source based on the electricity price and transportation cost of each external energy source and the total amount of electricity to be supplied.

[0056] For the convenience of calculation, the preset carbon emission coefficient can be used as a reference standard, and the total amount of electricity to be supplied can be calculated based on the excess carbon emissions and the preset carbon emission coefficient. Furthermore, an electricity equation is established based on the electricity price, transportation cost and total amount of electricity to be supplied of each green energy source, and constraints are set according to actual needs, such as the total cost does not exceed the preset amount, or the amount of electricity to be supplied of a certain green energy source does not exceed the preset amount, etc. Finally, the amount of electricity to be supplied of at least one external energy source is calculated based on the electricity equation and constraints, so that relevant staff can purchase a variety of green energy sources in combination according to the calculated results to reduce the cost of purchasing electricity.

[0057] S140: Based on the energy topology map, perform path allocation for the external energy and determine an energy scheduling strategy for the target energy network at the next moment.

[0058] Since the energy router nodes in the energy topology are intertwined, for a designated energy router to be supplemented with external energy, there may be multiple nodes and multiple reachable paths between its external energy access point and the node where the designated energy router is located. In order to improve energy utilization, this application allocates paths to external energy to determine the energy scheduling strategy for the next moment.

[0059] The energy scheduling strategy may be the name and order of each energy router node passed from the external energy input node.

[0060] Specifically, a path with a small number of nodes can be selected as the optimal path for external energy input, or a path with the lowest transmission cost can be selected as the optimal path for external energy input.

[0061] It should be noted that when allocating paths, the transmission capacity of the power lines must be considered to avoid overloading the lines and ensure the safety of energy transmission.

[0062] The embodiment of the present invention provides an energy scheduling method, which constructs an energy topology map according to the connection status of each energy router in the target energy network, constructs an adjacency matrix based on the energy topology map, and constructs a feature matrix according to the current state information of each energy router at the current moment; the adjacency matrix and the feature matrix are input into the pre-trained target graph neural network model to determine the predicted state information of each energy router at the next moment; wherein the predicted state information only includes the predicted carbon emissions of each energy router; if the carbon emissions exceed the preset carbon quota, at least one external energy source is obtained from the external power grid; based on the energy topology map, the external energy source is assigned a path to determine the energy scheduling strategy of the target energy network at the next moment. This technical solution, through the graph neural network, realizes the dynamic prediction of the state of each energy router in the energy network, and timely adjusts the scheduling strategy of the external energy source to improve energy utilization.

[0063] Embodiment 2

[0064] Figure 3 This is a flow chart of an energy scheduling method provided in Example 2 of this application. This embodiment is optimized based on the above embodiment, specifically, the energy scheduling process is refined. Figure 3 As shown, the method of this embodiment specifically includes the following steps.

[0065] S210, constructing an energy topology map according to the connection status of each energy router in the target energy network, constructing an adjacency matrix based on the energy topology map, and constructing a feature matrix according to the current state information of each energy router at the current moment.

[0066] S220. Input the adjacency matrix and the feature matrix into a pre-trained target graph neural network model to determine the predicted state information of each energy router at the next moment.

[0067] The predicted state information at least includes the predicted carbon emissions of each of the energy routers.

[0068] S230: If the carbon emissions exceed the preset carbon quota, obtaining at least one external energy source from an external power grid.

[0069] Wherein, the external energy is green energy.

[0070] S240. Based on a graph search algorithm, according to the transmission cost from the input node of the external energy in the energy topology graph to the energy router, the external energy is assigned a path, and the energy scheduling strategy of the target energy network at the next moment is determined.

[0071] Among them, the graph search algorithm can be a type of algorithm used to find a specific path or traverse a graph in graph structured data. Common ones include depth-first search algorithm, breadth-first search algorithm, Dijkstra algorithm, A algorithm, etc.

[0072] The transmission cost may be the result of a combination of factors, for example, the resistance loss of the line, such as line length, material, current size, etc.; the operation and maintenance cost of the transmission equipment, etc.; for thermal energy transmission, it may also involve heat loss in the heat exchange process, pipeline insulation and maintenance costs, etc.

[0073] Specifically, we can first determine the input nodes of each external energy source and the nodes where the energy routers are located to determine the starting and ending points of the path. Taking the Dijkstra algorithm as an example, starting from the external energy input node, the algorithm will examine each edge connected to the node and the corresponding node in turn, and record the transmission cost from the starting node to these adjacent nodes; then continuously update the shortest path cost to each node, and mark the nodes with the shortest path determined as visited, continue to explore the unvisited neighbor nodes of these visited nodes, and repeat this process until the shortest transmission cost path to all energy routers is found.

[0074] Optionally, the graph search algorithm is a greedy algorithm; accordingly, based on the graph search algorithm, the external energy is assigned a path according to the transmission cost from the input node of the external energy in the energy topology graph to the energy router, and the energy scheduling strategy of the target energy network at the next moment is determined, including: taking the input node of the external energy as the starting node, determining the transmission cost between the starting node and its adjacent nodes, and taking the adjacent node with the lowest transmission cost as the starting node of the next round; repeating the above steps until the energy router is taken as the starting node of the next round, and determining the energy scheduling strategy of the target energy network at the next moment according to the starting nodes in each round.

[0075] Among them, the greedy algorithm is an algorithm that takes the best decision in the current state in each step of selection, and reaches an approximate optimal solution through a series of local optimal choices. In the external energy path allocation problem, the goal of the greedy algorithm is to make the current selected path have the lowest cost or the highest benefit in each step of selection, and gradually build a complete energy allocation path.

[0076] Specifically, the external energy input node is first used as the starting node, marked as visited, and an empty path list is created to store the final energy distribution path. Starting from the starting node, all unvisited nodes adjacent to the starting node are checked. For each adjacent node, the transmission cost from the starting node to the node is calculated. The adjacent node with the lowest transmission cost is selected as the next node to be visited, added to the path list, and marked as visited. Repeat the above process of selecting the next node. For the node newly added to the path list, all its unvisited adjacent nodes are checked again, the transmission cost from the current node to these adjacent nodes is calculated, and the node with the lowest cost is selected to be added to the path list. This process continues until all target energy router nodes that need to allocate energy are visited or no new accessible nodes can be found. After the above iterative process, the node sequence stored in the path list constitutes an energy distribution path from the external energy supply node to each target energy router node. External energy is distributed along this path.

[0077] The advantage of the above technical solution is that the implementation process of the greedy algorithm is relatively simple and the computational complexity is low. Especially when the energy network is large in scale, the energy distribution path plan can be quickly determined.

[0078] The energy scheduling method provided in the embodiment of the present application is to construct an energy topology map according to the connection status of each energy router in the target energy network, and to construct an adjacency matrix based on the energy topology map, and to construct a feature matrix according to the current state information of each energy router at the current moment; the adjacency matrix and the feature matrix are input into the pre-trained target graph neural network model to determine the predicted state information of each energy router at the next moment; wherein the predicted state information only includes the predicted carbon emissions of each energy router; if the carbon emissions exceed the preset carbon quota, at least one external energy source is obtained from the external power grid; based on the graph search algorithm, the external energy source is assigned a path according to the transmission cost from the input node of the external energy source in the energy topology map to the energy router, and the energy scheduling strategy of the target energy network at the next moment is determined. This technical solution allocates external energy paths through a graph search algorithm to optimize the energy transmission cost, and can achieve the carbon emission target at a low cost and improve the energy allocation efficiency.

[0079] Embodiment 3

[0080] Figure 4 A schematic diagram of a device 10 that can be used to implement an embodiment of the present application is shown. The device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or required herein.

[0081] like Figure 4 As shown, the device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the device 10 can also be stored. The processor 11, ROM 12 and RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0082] A number of components in the device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0083] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the energy scheduling method.

[0084] In some embodiments, the energy scheduling method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the energy scheduling method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the energy scheduling method in any other appropriate manner (e.g., by means of firmware).

[0085] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0086] The computer programs for implementing the methods of the present application may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer programs are executed by the processor, the functions / operations specified in the flow charts and / or block diagrams are implemented. The computer programs may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0087] In the context of the present application, a computer readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device or equipment. A computer readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer readable storage medium may be a machine readable signal medium. A more specific example of a machine readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0088] To provide interaction with a user, the systems and techniques described herein can be implemented on a device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0089] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0090] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0091] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this application can be executed in parallel, sequentially or in different orders, as long as the expected results of the technical solution of this application can be achieved, and this document is not limited here.

[0092] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. An energy scheduling method, characterized in that: The method comprises: According to the connection status of each energy router in the target energy network, an energy topology map is constructed, and an adjacency matrix is ​​constructed based on the energy topology map, and a feature matrix is ​​constructed according to the current state information of each energy router at the current moment; Inputting the adjacency matrix and the feature matrix into a pre-trained target graph neural network model to determine the predicted state information of each energy router at the next moment; wherein the predicted state information at least includes the predicted carbon emissions of each energy router; If the predicted carbon emissions exceed the preset carbon quota, obtaining at least one external energy source from an external power grid; wherein the external energy source is green energy; Based on the energy topology map, the external energy is assigned a path, and the energy scheduling strategy of the target energy network at the next moment is determined.

2. The method according to claim 1, characterized in that The current state information includes at least one of the carbon emissions, electricity consumption, adjacent node transmission cost and transmission line length of each energy router at the current moment.

3. The method according to claim 1, characterized in that Before obtaining at least one external energy source from the external power grid, the method further comprises: If the predicted carbon emissions exceed the preset carbon quota, the excess carbon emissions are determined based on the predicted carbon emissions and the preset carbon quota; The amount of electricity to be supplied by at least one external energy source is determined according to the excess carbon emissions.

4. The method according to claim 3, characterized in that Determining the amount of electricity to be supplied by at least one external energy source according to the excess carbon emissions, including: Determine the total amount of electricity to be supplied based on the excess carbon emissions; The amount of electricity to be supplied by at least one external energy source is determined according to the electricity price and transportation cost of each external energy source and the total amount of electricity to be supplied.

5. The method according to claim 1, characterized in that: Based on the energy topology map, the external energy is assigned a path, and an energy scheduling strategy of the target energy network at the next moment is determined, including: Based on the graph search algorithm, the external energy is assigned a path according to the transmission cost from the input node of the external energy in the energy topology graph to the energy router, and the energy scheduling strategy of the target energy network at the next moment is determined.

6. The method according to claim 5, characterized in that The graph search algorithm is a greedy algorithm; Accordingly, based on the graph search algorithm, according to the transmission cost from the input node of the external energy in the energy topology graph to the energy router, the external energy is assigned a path, and the energy scheduling strategy of the target energy network at the next moment is determined, including: Taking the input node of the external energy as the starting node, determining the transmission cost between the starting node and its adjacent nodes, and taking the adjacent node with the lowest transmission cost as the starting node of the next round; The above steps are repeated until the energy router is used as the starting node of the next round, and the energy scheduling strategy of the target energy network at the next moment is determined according to the starting node in each round.

7. The method according to claim 1, characterized in that The training process of the target graph neural network model includes: Acquire a historical data set of each energy router in the target energy network; the historical data includes a historical adjacency matrix and a historical feature matrix; The historical data set is input into the initial graph neural network model for training, and the parameters of the initial graph neural network model are adjusted to obtain the target graph neural network model.

8. An electronic device, characterized in that: The device comprises: At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the energy scheduling method described in any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the energy scheduling method according to any one of claims 1 to 7 when executed.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the computer program implements the energy scheduling method according to any one of claims 1 to 7.

Images