Source network load intelligent enhanced storage optimization operation method and related device

Abstract

The invention discloses a source network load intelligent enhanced storage optimization operation method and a related device. Comprising the following steps: inputting topological structure information of a graph model of the source network load storage system, feature information of graph nodes in the graph model of the source network load storage system and feature information of graph edges in the graph model of the source network load storage system into a trained physical information graph neural network model, the physical information graph neural network model is trained based on a physical constraint equation set of a graph model of the source network load storage system to obtain an optimized operation strategy of the source network load storage system, the source network load storage system is controlled according to the optimized operation strategy of the source network load storage system, and the physical information graph neural network model is trained based on a physical constraint equation set of the graph model of the source network load storage system. According to the method and the related device, the physical consistency and reliability of source network load storage optimization can be improved.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of source network load storage optimization, and relates to a source network load intelligent enhanced storage optimization operation method and a related device. BACKGROUND

[0002] A source network load storage integrated system is concerned due to its ability to effectively improve energy utilization efficiency and system flexibility. At present, the optimization operation of such a system mainly relies on traditional mathematical programming methods or heuristic algorithms. However, when facing an increasingly complex source network load storage system, the traditional mathematical programming method often has problems such as complex model establishment, long solution time, and difficulty in handling non-convex characteristics, which makes it difficult to meet the demand for rapid response. Although the heuristic algorithm has a faster solution speed, it is easy to fall into local optimization, and the optimization result often lacks strict adherence to the physical operation rules of the system, which may lead to the risk of infeasibility or suboptimality of the scheduling scheme in the actual physical layer. In addition, although the existing part of the data-driven machine learning method can improve the optimization efficiency, it usually needs a large amount of labeled data, and the "black box" characteristics of the model make it difficult to explain, and more importantly, they often ignore or weaken the strict physical constraints that must be met in system operation, resulting in insufficient physical consistency and reliability of the optimization result. SUMMARY

[0003] The purpose of the present application is to overcome the shortcomings of the prior art and provide a source network load intelligent enhanced storage optimization operation method and related device, which can improve the physical consistency and reliability of source network load optimization.

[0004] To achieve the above purpose, the present application discloses a source network load intelligent enhanced storage optimization operation method, comprising: constructing a graph model of a source network load storage system; obtaining topological structure information of the graph model of the source network load storage system, feature information of graph nodes in the graph model of the source network load storage system, and feature information of graph edges in the graph model of the source network load storage system; inputting the topological structure information of the graph model of the source network load storage system, the feature information of the graph nodes in the graph model of the source network load storage system, and the feature information of the graph edges in the graph model of the source network load storage system into a trained physical information graph neural network model to obtain an optimization operation strategy of the source network load storage system, and controlling the source network load storage system according to the optimization operation strategy of the source network load storage system, wherein the physical information graph neural network model is trained based on a set of physical constraint equations of the graph model of the source network load storage system.

[0005] The further improvement of the source network load intelligent enhanced storage optimization operation system of the present application is that: Further, before the topology structure information of the graph model of the source network and load storage system, the feature information of the graph node in the graph model of the source network and load storage system and the feature information of the graph edge in the graph model of the source network and load storage system are input into the trained physical information graph neural network model, the method further comprises the following steps: constructing a training data set; constructing a loss function; constructing a physical information graph neural network model; training the physical information graph neural network model using the training data set and the loss function to obtain a trained physical information graph neural network model.

[0006] Further, the process of constructing the loss function is as follows: constructing the loss function based on the physical constraint equation set of the graph model of the source network and load storage system.

[0007] Further, the loss function is as follows:

[0008] wherein, L represents the total loss function value; Ltarget represents a task target loss term, which is used to evaluate the deviation of the optimized operation strategy output by the physical information graph neural network model from the target strategy; Ltarget represents a task target loss term, which is used to evaluate the deviation of the optimized operation strategy output by the physical information graph neural network model from the target strategy; Ltarget represents a task target loss term, which is used to evaluate the deviation of the optimized operation strategy output by the physical information graph neural network model from the target strategy; Ltarget represents a task target loss term, which is used to evaluate the deviation of the optimized operation strategy output by the physical information graph neural network model from the target strategy; Ltarget represents a task target loss term, which is used to evaluate the deviation of the optimized operation strategy output by the physical information graph neural network model from the target strategy; Ltarget represents a task target loss term, which is used to evaluate the deviation of the optimized operation strategy output by the physical information graph neural network model from the target strategy; Ltarget represents a task target loss term, which is used to evaluate the deviation of the optimized operation strategy output by the physical information graph neural network model from the target strategy; Ltarget represents a task target loss term, which is used to evaluate the deviation of the optimized operation strategy output by the physical information graph neural network model from the target strategy; Ltarget represents a task target loss term, which is used to evaluate the deviation of the optimized operation strategy output by the physical information graph neural network model from the target strategy;

[0009] Further, the process of training the physical information graph neural network model using the training data set and the loss function to obtain a trained physical information graph neural network model is as follows: training the physical information graph neural network model using the training data set and the loss function by a gradient descent optimizer or a back propagation algorithm to obtain a trained physical information graph neural network model.

[0010] The application discloses a source network and load intelligent enhanced storage optimization operation system, which comprises: a first construction module for constructing a graph model of a source network and load storage system; an acquisition module for acquiring topology structure information of the graph model of the source network and load storage system, feature information of a graph node in the graph model of the source network and load storage system and feature information of a graph edge in the graph model of the source network and load storage system; The control module is configured to input topological structure information of a graph model of the source network and storage system, feature information of a graph node in the graph model of the source network and storage system, and feature information of a graph edge in the graph model of the source network and storage system into a trained physical information graph neural network model, obtain an optimized operation strategy of the source network and storage system, and control the source network and storage system according to the optimized operation strategy of the source network and storage system, wherein the physical information graph neural network model is trained based on a set of physical constraint equations of the graph model of the source network and storage system.

[0011] The source network and storage intelligent enhancement optimization operation system further has the following improvements: Further, the source network and storage intelligent enhancement optimization operation system further comprises: The second construction module is configured to construct a training data set. The third construction module is configured to construct a loss function. The fourth construction module is configured to construct a physical information graph neural network model. The training module is configured to train the physical information graph neural network model by using the training data set and the loss function, and obtain a trained physical information graph neural network model.

[0012] Further, the process of constructing the loss function is as follows: The loss function is constructed based on the set of physical constraint equations of the graph model of the source network and storage system.

[0013] Further, the loss function is as follows:

[0014] wherein, L represents a total loss function value; Ltarget represents a task target loss term, which is used to evaluate the deviation of the optimized operation strategy output by the physical information graph neural network model from a target strategy; Ltarget represents a task target loss term, which is used to evaluate the deviation of the optimized operation strategy output by the physical information graph neural network model from a target strategy; Ltarget represents a task target loss term, which is used to evaluate the deviation of the optimized operation strategy output by the physical information graph neural network model from a target strategy; N represents the number of physical constraints in the set of physical constraint equations; wi represents a weight coefficient of the i-th physical constraint; wi represents a weight coefficient of the i-th physical constraint; wi represents a weight coefficient of the i-th physical constraint; wi represents a weight coefficient of the i-th physical constraint; wi represents a weight coefficient of the i-th physical constraint;

[0015] Further, the process of training the physical information graph neural network model by using the training data set and the loss function to obtain a trained physical information graph neural network model is as follows: The physical information graph neural network model is trained by a gradient descent optimizer or a back propagation algorithm to obtain a trained physical information graph neural network model.

[0016] The application discloses a computer device, including a memory, a processor and a computer program stored in the memory and executable on the processor, when the processor executes the computer program, the steps of the source network load intelligent enhancement storage optimization operation method are realized.

[0017] The application discloses a computer readable storage medium, the computer readable storage medium stores a computer program, when the processor executes the computer program, the steps of the source network load intelligent enhancement storage optimization operation method are realized.

[0018] The application has the following beneficial effects: The source network load intelligent enhancement storage optimization operation method and related device have the following beneficial effects: the topological structure information of the graph model of the source network load storage system, the feature information of the graph nodes in the graph model of the source network load storage system and the feature information of the graph edges in the graph model of the source network load storage system are input into the trained physical information graph neural network model to obtain the optimization operation strategy of the source network load storage system, and the source network load storage system is controlled according to the optimization operation strategy of the source network load storage system, wherein the physical information graph neural network model is trained based on the physical constraint equation set of the graph model of the source network load storage system, the physical feasibility and the global optimization ability of the optimization strategy can be significantly improved, the operation instruction accuracy and reliability and the physical consistency are ensured, and the practicability is extremely strong. BRIEF DESCRIPTION OF DRAWINGS

[0019] The drawings constituting a part of the specification of the application are used to provide further understanding of the application, the illustrative embodiments of the application and the description thereof are used to explain the application, and do not constitute improper limitation on the application. In the drawings: Figure 1 The method flowchart of the application is shown in the drawings; Figure 2 The system structure diagram of the application is shown in the drawings. DETAILED DESCRIPTION

[0020] The technical solutions in the embodiments of the application will be clearly and completely described below with reference to the drawings of the embodiments of the application, obviously, the described embodiments are part of the embodiments of the application, rather than all the embodiments of the application. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor are within the protection scope of the application.

[0021] In the description of the present application, it is to be understood that the terms "including", "comprising", "having" and "encompassing" mean that there are additions to the described features, integers, steps, operations, elements, components, and / or groups thereof that are not specifically recited. The terms "comprising" and "including" are to be construed open-ended, in that they allow for the addition of one or more features, integers, steps, operations, elements, components, and / or groups thereof.

[0022] It should also be understood that the terms used in the present specification and claims are not to be interpreted as limiting the present application. The singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.

[0023] It will be further understood that the terms "and / or", "including" and "comprising" when used in this specification, specify the presence of features, integers, steps, operations, elements, components and / or groups thereof, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.

[0024] It should be understood that, although the terms first, second, third, etc. can be used herein to describe various ranges or elements, these ranges or elements should not be limited by these terms. These terms are only used to distinguish one range or element from another. For example, a first range could be termed a second range without departing from the scope of the example embodiments. Similarly, it will be understood that, when an element or layer is referred to as being on another element or layer, it can be directly on the other element or layer or intervening elements or layers can also be present.

[0025] Depending on the context, the word "if" can be interpreted to mean "when" or "upon" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [a stated condition or event] is detected" can be interpreted to mean "upon determining" or "in response to determining" or "upon detecting [the stated condition or event]" or "in response to detecting [the stated condition or event]", depending on the context.

[0026] In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0027] Various structural schematic diagrams according to the disclosed embodiments of the present application are shown in the drawings. These diagrams are not drawn to scale, in which some details are exaggerated for the purpose of clear expression, and some details can be omitted. The shapes of various regions, layers and their relative sizes and positional relationships shown in the drawings are only exemplary, and in actuality, there can be deviations due to manufacturing tolerances or technical limitations, and regions / layers with different shapes, sizes and relative positions can be additionally designed by those skilled in the art according to actual needs.

[0028] Embodiment one With reference to Figure 1 The source-grid-load-storage intelligent enhancement optimization operation method described in the present application includes the following steps: 1) Construct a graph model of the source-grid-load-storage system; The specific process of step 1) is: 11) Determine the graph node set: take the power generation units in the source-grid-load-storage system as power generation unit nodes; take the energy storage units in the source-grid-load-storage system as energy storage unit nodes; take the load units in the source-grid-load-storage system as load unit nodes; take the key topological nodes of the power grid as graph nodes; take all the power generation unit nodes, energy storage unit nodes, load unit nodes and graph nodes as the graph nodes of the source-grid-load-storage system, and construct a graph node set in this way.

[0029] 12) Determine the graph edge set: take the physical connection relationship or electrical coupling relationship between the power generation unit nodes, energy storage unit nodes, load unit nodes and other graph nodes in the source-grid-load-storage system as the graph edges of the graph model. The direction of the edge represents the typical direction of power flow, or for bidirectional flow devices, it can be defined as an undirected edge or two directed edges.

[0030] 13) Configure the initial characteristics of the graph nodes and / or graph edges: configure initial characteristics for each graph node and each graph edge, which include numerical information for characterizing their respective physical properties, operating parameters or real-time states.

[0031] For example, for a generation unit node, the initial characteristics of the generation unit node at least include: upper and lower limits of output: the minimum and maximum output power allowed by the unit; ramp rate limit: the maximum rate of increase and decrease of output allowed per unit time.

[0032] For example, for an energy storage unit node, the initial characteristics of the energy storage unit node at least include: rated capacity: the maximum storage capacity of the energy storage system; rated charge and discharge power: the maximum charge and discharge power allowed; current state of charge: the percentage of the current capacity of the energy storage system; charge and discharge efficiency: the energy conversion efficiency during the charging and discharging process; current state of charge operating interval: the upper and lower limits of the SOC allowed for the operation of the energy storage system to ensure the service life and safety.

[0033] For a load unit node, the initial characteristics of the load unit node at least include: predicted load curve: a sequence of predicted load demand values in the future period of time; capacity and response characteristics of adjustable load: for demand-side response resources, including the amount of load that can be reduced / shifted, response delay, duration, compensation cost, etc.

[0034] For a key topology node of the power grid, the initial characteristics at least include: node type: such as PQ node, PV node, balance node; voltage / phase angle reference value, or allowed upper and lower limits of voltage amplitude.

[0035] 14) determining the set of physical constraint equations of the source grid load storage system; The specific process is: identifying the core physical laws and operating rules that the source grid load storage system must comply with; mathematically formulating the physical laws and operating rules to form a set of equality or inequality constraint equations, which constitute the set of physical constraint equations; the set of physical constraint equations at least includes power balance constraint equations for each graph node and device operating boundary constraint equations for generation unit nodes and energy storage unit nodes; and converting each constraint equation in the set of physical constraint equations into a form that can evaluate the residual or violation degree in the training process of the physical information graph neural network model.

[0036] Mathematically formulating the constraint equations: expressing the above-mentioned physical laws and operating rules as a set of equality or inequality constraint equations. The set of equations constitutes the set of physical constraint equations, which at least includes: power balance constraint equations for each graph node: for each power grid topology node n, at any time t, the total power flowing into the node is equal to the total power flowing out of the node.

[0037] 2) obtaining the topology structure information of the graph model of the source grid load storage system, the characteristic information of the graph nodes in the graph model of the source grid load storage system, and the characteristic information of the graph edges in the graph model of the source grid load storage system; 3) inputting the topological structure information of the graph model of the source grid- load-storage system, the feature information of the graph nodes in the graph model of the source grid- load-storage system, and the feature information of the graph edges in the graph model of the source grid- load-storage system into the trained physical information graph neural network model to obtain an optimized operation strategy of the source grid- load-storage system, and controlling the source grid- load-storage system according to the optimized operation strategy of the source grid- load-storage system.

[0038] The process of step 3) is as follows: 31) a training data set; Historical operation data, simulation data or predicted working condition data of the source grid- load-storage system are obtained, and a training data set is constructed therefrom, the training data set including diversified system operation scenarios and corresponding (approximate) optimal operation strategies.

[0039] 32) constructing a loss function; The loss function is as follows:

[0040] wherein, represents a total loss function value; represents a task target loss term, which is used to evaluate the optimized operation strategy output by the physical information graph neural network model relative to the target strategy ; represents the number of physical constraints contained in the set of physical constraint equations; represents the weight coefficient of the th physical constraint; represents the th physical constraint penalty term, which is calculated by the evaluation function from the variable set related to the th physical constraint output by the physical information graph neural network model, or derived based on the output thereof.

[0041] 33) training the physical information graph neural network model by using the training data set and the loss function through a gradient descent optimizer or a back propagation algorithm to obtain a trained physical information graph neural network model; 34) inputting the topological structure information of the graph model of the source grid- load-storage system, the feature information of the graph nodes in the graph model of the source grid- load-storage system, and the feature information of the graph edges in the graph model of the source grid- load-storage system into the trained physical information graph neural network model to obtain an optimized operation strategy of the source grid- load-storage system; The optimization operation strategy of the source network load storage system comprises: operation condition information of the source network load storage system in real time or in a future period of time, including load prediction, renewable energy output prediction and initial state of each unit; the operation condition information is processed and fed as input to the trained physical information graph neural network model; the physical information graph neural network model performs forward inference calculation and outputs the optimization operation strategy; the optimization operation strategy is converted into specific control setting values or scheduling plans which can be directly issued to each controllable unit in the source network load storage system.

[0042] Embodiment two Reference Figure 2 The source network load intelligent enhanced storage optimization operation system comprises: A first construction module for constructing a graph model of the source network load storage system; A obtaining module for obtaining topological structure information of the graph model of the source network load storage system, feature information of graph nodes in the graph model of the source network load storage system and feature information of graph edges in the graph model of the source network load storage system; A control module for inputting the topological structure information of the graph model of the source network load storage system, the feature information of the graph nodes in the graph model of the source network load storage system and the feature information of the graph edges in the graph model of the source network load storage system into a trained physical information graph neural network model to obtain an optimization operation strategy of the source network load storage system, and controlling the source network load storage system according to the optimization operation strategy of the source network load storage system, wherein the physical information graph neural network model is trained based on a set of physical constraint equations of the graph model of the source network load storage system.

[0043] In this embodiment, it also comprises: A second construction module for constructing a training data set; A third construction module for constructing a loss function; A fourth construction module for constructing a physical information graph neural network model; A training module for training the physical information graph neural network model by using the training data set and the loss function to obtain a trained physical information graph neural network model.

[0044] In this embodiment, the process of constructing the loss function is: The loss function is constructed based on the set of physical constraint equations of the graph model of the source network load storage system.

[0045] In this embodiment, the loss function is:

[0046] Wherein, L represents the total loss function value; denotes a task objective loss term for evaluating the optimized operation strategy output by the physical information graph neural network model relative to the target strategy . denotes the number of physical constraints in the set of physical constraint equations; denotes the weight coefficient of the th physical constraint; denotes a penalty term related to the variable set of the th physical constraint .

[0047] In this embodiment, the process of training the physical information graph neural network model using the training data set and the loss function to obtain the trained physical information graph neural network model is as follows: The physical information graph neural network model is trained by a gradient descent optimizer or a back propagation algorithm using the training data set and the loss function to obtain the trained physical information graph neural network model.

[0048] The division of the modules in the embodiments of the present application is illustrative, and is only a logical functional division. In actual implementation, another division mode can be used. In addition, the functional modules in each embodiment of the present application can be integrated in one processor, or can be physically separated, or two or more modules can be integrated in one module. The integrated module can be realized in the form of hardware or in the form of a software functional module.

[0049] Embodiment Three The computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the source network load intelligent enhancement storage optimization operation method when executing the computer program, for example, comprising: constructing a graph model of a source network load storage system; obtaining topology structure information of the graph model of the source network load storage system, feature information of graph nodes in the graph model of the source network load storage system and feature information of graph edges in the graph model of the source network load storage system; inputting the topology structure information of the graph model of the source network load storage system, the feature information of the graph nodes in the graph model of the source network load storage system and the feature information of the graph edges in the graph model of the source network load storage system into a trained physical information graph neural network model to obtain an optimization operation strategy of the source network load storage system, and controlling the source network load storage system according to the optimization operation strategy of the source network load storage system, wherein the physical information graph neural network model is trained based on a set of physical constraint equations of the graph model of the source network load storage system. The memory can include an internal memory, for example, a high-speed random memory, and can also include a non-volatile memory, for example, at least one disk memory and the like; the processor, the network interface and the memory are connected to each other through an internal bus, which can be an industry standard architecture bus, a peripheral component interconnect standard bus, an extended industry standard structure bus and the like, and the bus can be divided into an address bus, a data bus, a control bus and the like. The memory is used to store programs, specifically, the programs can include program codes, and the program codes include computer operation instructions. The memory can include an internal memory and a non-volatile memory, and provide instructions and data to the processor.

[0050] Embodiment four A computer readable storage medium stores a computer program, the computer program is executed by a processor to implement the steps of the source network load intelligent enhancement storage optimization operation method, for example, including: constructing a graph model of a source network load storage system; obtaining topology structure information of the graph model of the source network load storage system, feature information of a graph node in the graph model of the source network load storage system, and feature information of a graph edge in the graph model of the source network load storage system; inputting the topology structure information of the graph model of the source network load storage system, the feature information of the graph node in the graph model of the source network load storage system, and the feature information of the graph edge in the graph model of the source network load storage system into a trained physical information graph neural network model, to obtain an optimization operation strategy of the source network load storage system, and controlling the source network load storage system according to the optimization operation strategy of the source network load storage system. Specifically, the computer readable storage medium includes but is not limited to, for example, volatile memory and / or non-volatile memory. The volatile memory can include random access memory (RAM) and / or cache memory (cache), etc. The non-volatile memory can include read-only memory (ROM), hard disk, flash memory, optical disk, magnetic disk, etc.

[0051] Those skilled in the art will appreciate that embodiments of the application can be supplied as a method, a system, or a computer program product. Therefore, the application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage, etc.) containing computer usable program code.

[0052] The application is described with reference to flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as combinations of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing apparatus to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing apparatus produce a means for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in a flow or multiple flows and / or blocks Figure 1 The apparatus that implements the functions specified in a flow or multiple flows and / or blocks.

[0053] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the Figure 1 function specified in the flow or flows and / or blocks Figure 1 of the block or blocks.

[0054] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the Figure 1 function specified in the flow or flows and / or blocks Figure 1 of the block or blocks.

[0055] Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. It is intended that the present application be considered as including any variations, uses, or adaptations of this application following, in general, the principles of the application and including such steps and features as come within the purview of the present application. The specification and examples given are considered exemplary only and the true scope and spirit of the application is indicated by the appended claims.

[0056] It is to be understood that the application is not limited to the precise construction described and as shown in the attached drawings, and that various modifications and changes can be made by those skilled in the art without departing from the scope of the present application. The scope of the application is limited only by the claims that follow.

[0057] The above description is only preferred embodiments of the present application, not any limitation thereto, any simple modification, change and equivalent structural change made according to the technical essence of the present application to the above embodiments are still within the protection scope of the present application.

Claims

1. A method for optimizing operation of source-network-load intelligence enhancement and storage optimization, characterized in that, The method comprises the following steps: constructing a graph model of a source network and energy storage system; obtaining topological structure information of the graph model of the source network and energy storage system, feature information of graph nodes in the graph model of the source network and energy storage system, and feature information of graph edges in the graph model of the source network and energy storage system; inputting the topological structure information of the graph model of the source network and energy storage system, the feature information of the graph nodes in the graph model of the source network and energy storage system, and the feature information of the graph edges in the graph model of the source network and energy storage system into a trained physical information graph neural network model to obtain an optimized operation strategy of the source network and energy storage system, and controlling the source network and energy storage system according to the optimized operation strategy of the source network and energy storage system, wherein the physical information graph neural network model is trained based on a set of physical constraint equations of the graph model of the source network and energy storage system. 2.The source network load intelligent enhancement optimization operation method according to claim 1, characterized in that, Before the topological structure information of the graph model of the source network and energy storage system, the feature information of the graph nodes in the graph model of the source network and energy storage system, and the feature information of the graph edges in the graph model of the source network and energy storage system are input into the trained physical information graph neural network model, the method further comprises the following steps: constructing a training data set; constructing a loss function; constructing a physical information graph neural network model; training the physical information graph neural network model by using the training data set and the loss function to obtain a trained physical information graph neural network model. 3.The source network load intelligent enhancement optimization operation method according to claim 2, characterized in that, The process of constructing the loss function is as follows: constructing the loss function based on the set of physical constraint equations of the graph model of the source network and energy storage system. 4.The source network load intelligent enhancement optimization operation method according to claim 2, characterized in that, The loss function is: wherein, represents the total loss function value; represents a task target loss term for evaluating the optimized operation strategy output by the physical information graph neural network model relative to the target strategy ; represents the number of physical constraints in the set of physical constraint equations; represents the weight coefficient of the th physical constraint; represents the penalty term of the variable set related to the th physical constraint . 5.The source network load intelligent enhancement optimization operation method according to claim 2, characterized in that, The process of training the physical information graph neural network model by using the training data set and the loss function to obtain a trained physical information graph neural network model is as follows: training the physical information graph neural network model by using the training data set and the loss function through a gradient descent optimizer or a back propagation algorithm to obtain a trained physical information graph neural network model.

6. A source network load intelligent enhancement and optimal operation system, characterized in that, The method comprises the following steps: a first constructing module configured to construct a graph model of a source network and energy storage system; an obtaining module configured to obtain topological structure information of the graph model of the source network and energy storage system, feature information of graph nodes in the graph model of the source network and energy storage system, and feature information of graph edges in the graph model of the source network and energy storage system; a control module configured to input the topological structure information of the graph model of the source network and energy storage system, the feature information of the graph nodes in the graph model of the source network and energy storage system, and the feature information of the graph edges in the graph model of the source network and energy storage system into a trained physical information graph neural network model to obtain an optimized operation strategy of the source network and energy storage system, and control the source network and energy storage system according to the optimized operation strategy of the source network and energy storage system, wherein the physical information graph neural network model is trained based on a set of physical constraint equations of the graph model of the source network and energy storage system. 7.The source network load intelligent enhancement optimization operation system according to claim 6, characterized in that, The method further comprises the following steps: a second constructing module configured to construct a training data set; a third constructing module configured to construct a loss function; a fourth constructing module configured to construct a physical information graph neural network model; a training module configured to train the physical information graph neural network model by using the training data set and the loss function to obtain a trained physical information graph neural network model. 8.The source network load intelligent enhancement optimization operation system according to claim 7, characterized in that, The process of constructing the loss function is: Based on the physical constraint equation set of the graph model of the source network load storage system, the loss function is constructed. 9.The source network load intelligent enhancement optimization operation system according to claim 7, wherein, The loss function is: wherein, represents the total loss function value; represents a task target loss term for evaluating the optimized operation strategy output by the physical information graph neural network model relative to the target strategy ; represents the number of physical constraints in the set of physical constraint equations; represents the weight coefficient of the th physical constraint; represents the penalty term of the variable set related to the th physical constraint . 10.The source network load intelligent enhancement optimization operation system according to claim 7, wherein, The process of training the physical information graph neural network model using the training data set and the loss function is: The training data set and the loss function are used to train the physical information graph neural network model through a gradient descent optimizer or a back propagation algorithm, and a trained physical information graph neural network model is obtained.

11. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the steps of the source network load intelligent enhancement storage optimization operation method according to any one of claims 1-5.

12. A computer-readable storage medium, the computer-readable storage medium storing a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the source network load intelligent enhancement storage optimization operation method according to any one of claims 1-5.

Images