Energy storage system configuration scheduling scheme generation method and device, medium and terminal

Abstract

This application discloses a method, device, medium, and terminal for generating energy storage system configuration and scheduling schemes, relating to the field of power distribution system planning and operation optimization technology. Its main purpose is to improve the current situation where only fixed energy storage is used, leading to an inability to respond to rapidly changing and regionally significant power shortages or congestion in the power grid; and to address the over-investment problem caused by excessive energy storage configuration to adapt to various extreme scenarios. The method includes: constructing a fuzzy set of load uncertainty probabilities based on historical load forecast data and real data sets; constructing an energy storage system configuration and scheduling scheme optimization model based on a two-stage decision architecture, using the minimization of the total cost function as the objective function; establishing a collaborative operation mechanism between fixed and mobile energy storage in the energy storage system configuration and scheduling scheme optimization model; and iteratively solving the model based on a column and constraint generation algorithm to obtain the configuration and scheduling schemes for fixed and mobile energy storage.

Description

Technical Field

[0001] This application relates to the field of power distribution system planning and operation optimization technology, and in particular to a method, device, medium and terminal for generating energy storage system configuration and scheduling schemes. Background Technology

[0002] As the proportion of renewable energy sources such as wind and solar power in the power system continues to increase, the intermittency and volatility of their output significantly enhance the uncertainty of power grid supply and demand. Energy storage systems, especially battery energy storage, have become a key means to smooth out fluctuations, peak shaving and valley filling, and improve grid resilience due to their flexible power regulation and energy time-shifting capabilities. How to accurately configure energy storage systems and optimize their scheduling has become an important issue for achieving efficient utilization of energy storage resources and improving the economy and security of the distribution network.

[0003] Currently, most existing methods focus on independent optimization of stationary energy storage. However, since the geographical location of stationary energy storage cannot be changed after installation, capacity and charging / discharging strategies can only be optimized at its fixed location, making it unable to respond to rapidly changing and regionally significant power shortages or congestion issues in the power grid. At the same time, in order to adapt to various extreme scenarios, there is often a tendency to configure sufficient energy storage capacity at each critical node, leading to over-investment. Summary of the Invention

[0004] In view of this, this application provides a method, device, medium, and terminal for generating energy storage system configuration and scheduling schemes. The main purpose is to improve the existing methods that only optimize fixed energy storage independently. Since the optimization of capacity and charging and discharging strategies can only be performed at a fixed location, it is unable to respond to the power shortage or congestion problems that are dynamic and regionally significant in the power grid. In addition, it addresses the problem of over-investment caused by configuring sufficient energy storage capacity at each key node in order to adapt to various extreme scenarios.

[0005] According to one aspect of this application, a method for generating an energy storage system configuration and scheduling scheme is provided, comprising: Obtain the historical load forecast data set and the historical load actual data set of the target power grid, and construct a load uncertainty probability fuzzy set based on the Wasserstein distance according to the historical load forecast data set and the historical load actual data set; Based on a two-stage decision-making architecture, an optimization model for energy storage system configuration and scheduling is constructed with minimizing the total cost function as the objective function. The first stage is the energy storage system configuration decision-making stage, which is used to optimize the scheduling decision of the energy storage system under the worst probability distribution contained in the load uncertainty probability fuzzy set. The second stage is the energy storage system scheduling decision-making stage, which is used to optimize the scheduling decision of the energy storage system under the worst probability distribution contained in the load uncertainty probability fuzzy set. The total cost includes the configuration cost of the energy storage system configuration decision-making stage and the scheduling cost of the energy storage system scheduling decision-making stage. In the energy storage system configuration and scheduling scheme optimization model, a collaborative operation mechanism between fixed energy storage system and mobile energy storage system is constructed. The collaborative operation mechanism is used to realize energy complementarity and scheduling coordination between fixed energy storage system and mobile energy storage system in the spatiotemporal dimension, including dynamic capacity allocation model and location status model of mobile energy storage system and operation model of fixed energy storage system. Based on the column and constraint generation algorithm, the optimization model of the energy storage system configuration and scheduling scheme is iteratively solved to obtain the configuration scheme of the fixed energy storage system and the mobile energy storage system, as well as the scheduling scheme of the fixed energy storage system and the mobile energy storage system.

[0006] Preferably, the step of constructing a fuzzy set of load uncertainty probabilities based on the Wasserstein distance, according to the historical load forecast data set and the historical load real data set, includes: Based on the historical load forecast data set and the historical load actual data set, the historical load error data set of the target power grid is calculated, and the corresponding normalized random error set is calculated based on the historical load error data set. A historical empirical probability distribution is constructed based on the normalized random error set; The radius of the probabilistic fuzzy set is determined based on a preset confidence level. A load uncertainty probabilistic fuzzy set is constructed with the historical empirical probability distribution as the center of the sphere and the radius of the probabilistic fuzzy set as the radius of the sphere. The radius of the probabilistic fuzzy set is used to measure the difference between the historical empirical probability distribution and any probability distribution. The load uncertainty probabilistic fuzzy set contains all probability distributions whose Wasserstein distance from the historical empirical probability distribution is within the radius of the probabilistic fuzzy set.

[0007] Preferably, the optimization model for the energy storage system configuration and scheduling scheme is as follows: , in, This represents the configuration cost of configuration scheme X for both stationary and mobile energy storage systems. This indicates the random error in configuration scheme X and load. The scheduling cost below represents This represents the probability fuzzy set of load uncertainty. Take the worst probability distribution , This represents the feasible constraint domain for energy storage configuration schemes.

[0008] Preferably, the dynamic capacity allocation model of the mobile energy storage system is as follows: , in, This represents the remaining energy of the k-th mobile energy storage system at time t+1. This represents the transportation energy loss coefficient of the k-th mobile energy storage system. Let represent the remaining energy of the k-th mobile energy storage system during time period t. This represents the discharge power of the k-th mobile energy storage system during time period t at node i. This represents the discharge efficiency of the k-th mobile energy storage system. This represents the charging efficiency of the k-th mobile energy storage system. This represents the charging power of the k-th mobile energy storage system during time period t at node i. This represents the set of mobile energy storage system numbers. This represents the set of scheduling periods.

[0009] Preferably, the location state model of the mobile energy storage system is as follows: , , in, This indicates the node where the k-th mobile energy storage system is located during time period t+1. This represents the correlation between mobility delay and power grid topology, characterizing the spatiotemporal evolution of location parameters. This represents the node where the k-th mobile energy storage system is located during time period t. This represents the travel time of the k-th mobile energy storage system. This represents the average moving speed of the k-th mobile energy storage system. This represents the actual distance traveled based on the power grid topology.

[0010] Preferably, the operating model of the stationary energy storage system is as follows: , , in, This represents the remaining energy of the f-th stationary energy storage system at node i during time period t+1. This represents the remaining energy of the f-th stationary energy storage system at node i during time period t. This represents the discharge power of the f-th stationary energy storage system at node i during time period t. This represents the discharge efficiency of the f-th stationary energy storage system. Let f represent the charging efficiency of the f-th stationary energy storage system. Let represent the charging power of the f-th stationary energy storage system at node i during time period t. This represents the power of the f-th stationary energy storage system at node i. This represents the minimum power value of the f-th stationary energy storage system. This represents the maximum power value of the f-th stationary energy storage system. This represents the set of nodes in the power grid that are pre-designated to have energy storage systems installed.

[0011] Preferably, the energy storage system configuration and scheduling scheme optimization model further includes power grid operation safety constraints, wherein the power grid operation safety constraints include line power flow constraints, node power balance constraints, and node voltage safety constraints.

[0012] According to another aspect of this application, a generator for an energy storage system configuration and scheduling scheme is provided, comprising: The load uncertainty probability fuzzy set construction module is used to obtain the historical load prediction data set and the historical load actual data set of the target power grid, and construct the load uncertainty probability fuzzy set based on the Wasserstein distance according to the historical load prediction data set and the historical load actual data set. The energy storage system configuration and scheduling scheme optimization model construction module is used to construct an energy storage system configuration and scheduling scheme optimization model based on a two-stage decision architecture, with minimizing the total cost function as the objective function. The first stage is the energy storage system configuration decision stage, which is used to optimize the scheduling decision of the energy storage system under the worst probability distribution contained in the load uncertainty probability fuzzy set. The second stage is the energy storage system scheduling decision stage, which is used to determine the scheduling decision of the energy storage system under the worst probability distribution contained in the load uncertainty probability fuzzy set. The total cost includes the configuration cost of the energy storage system configuration decision stage and the scheduling cost of the energy storage system scheduling decision stage. The collaborative operation mechanism construction module is used to construct a collaborative operation mechanism between fixed energy storage systems and mobile energy storage systems in the energy storage system configuration and scheduling scheme optimization model. The collaborative operation mechanism is used to realize energy complementarity and scheduling coordination between fixed energy storage systems and mobile energy storage systems in the spatiotemporal dimension, including the dynamic capacity allocation model and location status model of mobile energy storage systems and the operation model of fixed energy storage systems. The energy storage system configuration and scheduling scheme optimization model solution module is used to iteratively solve the energy storage system configuration and scheduling scheme optimization model based on the column and constraint generation algorithm, so as to obtain the configuration scheme of fixed energy storage system and mobile energy storage system, as well as the scheduling scheme of fixed energy storage system and mobile energy storage system.

[0013] Preferably, the load uncertainty probability fuzzy set construction module is used for: Based on the historical load forecast data set and the historical load actual data set, the historical load error data set of the target power grid is calculated, and the corresponding normalized random error set is calculated based on the historical load error data set. A historical empirical probability distribution is constructed based on the normalized random error set; The radius of the probabilistic fuzzy set is determined based on a preset confidence level. A load uncertainty probabilistic fuzzy set is constructed with the historical empirical probability distribution as the center of the sphere and the radius of the probabilistic fuzzy set as the radius of the sphere. The radius of the probabilistic fuzzy set is used to measure the difference between the historical empirical probability distribution and any probability distribution. The load uncertainty probabilistic fuzzy set contains all probability distributions whose Wasserstein distance from the historical empirical probability distribution is within the radius of the probabilistic fuzzy set.

[0014] Preferably, the optimization model for the energy storage system configuration and scheduling scheme is as follows: , in, This represents the configuration cost of configuration scheme X for both stationary and mobile energy storage systems. This indicates the random error in configuration scheme X and load. The scheduling cost below represents This represents the probability fuzzy set of load uncertainty. Take the worst probability distribution , This represents the feasible constraint domain (configuration space) of the energy storage configuration scheme.

[0015] Preferably, the dynamic capacity allocation model of the mobile energy storage system is as follows: , in, This represents the remaining energy of the k-th mobile energy storage system at time t+1. This represents the transportation energy loss coefficient of the k-th mobile energy storage system. Let represent the remaining energy of the k-th mobile energy storage system during time period t. This represents the discharge power of the k-th mobile energy storage system during time period t at node i. This represents the discharge efficiency of the k-th mobile energy storage system. This represents the charging efficiency of the k-th mobile energy storage system. This represents the charging power of the k-th mobile energy storage system during time period t at node i. This represents the set of mobile energy storage system numbers. This represents the set of scheduling periods.

[0016] Preferably, the location state model of the mobile energy storage system is as follows: , , in, This indicates the node where the k-th mobile energy storage system is located during time period t+1. This represents the correlation between mobility delay and power grid topology, characterizing the spatiotemporal evolution of location parameters. This represents the node where the k-th mobile energy storage system is located during time period t. This represents the travel time of the k-th mobile energy storage system. This represents the average moving speed of the k-th mobile energy storage system. This represents the actual distance traveled based on the power grid topology.

[0017] Preferably, the operating model of the stationary energy storage system is as follows: , , in, This represents the remaining energy of the f-th stationary energy storage system at node i during time period t+1. This represents the remaining energy of the f-th stationary energy storage system at node i during time period t. This represents the discharge power of the f-th stationary energy storage system at node i during time period t. This represents the discharge efficiency of the f-th stationary energy storage system. Let f represent the charging efficiency of the f-th stationary energy storage system. Let represent the charging power of the f-th stationary energy storage system at node i during time period t. This represents the power of the f-th stationary energy storage system at node i. This represents the minimum power value of the f-th stationary energy storage system. This represents the maximum power value of the f-th stationary energy storage system. This represents the set of nodes in the power grid that are pre-designated to have energy storage systems installed.

[0018] Preferably, the energy storage system configuration and scheduling scheme optimization model further includes power grid operation safety constraints, wherein the power grid operation safety constraints include line power flow constraints, node power balance constraints, and node voltage safety constraints.

[0019] According to another aspect of this application, a storage medium is provided, wherein at least one executable instruction is stored therein, the executable instruction causing a processor to perform an operation corresponding to the above-described method for generating an energy storage system configuration scheduling scheme.

[0020] According to another aspect of this application, a terminal is provided, comprising: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other through the communication bus; The memory is used to store at least one executable instruction, which causes the processor to perform the operation corresponding to the above-described method for generating the energy storage system configuration and scheduling scheme.

[0021] By employing the above technical solutions, the technical solutions provided in the embodiments of this application have at least the following advantages: This application provides a method, apparatus, medium, and terminal for generating energy storage system configuration and scheduling schemes. First, it acquires a set of historical load forecast data and a set of historical load actual data for the target power grid. Based on these data, a load uncertainty probability fuzzy set is constructed using Wasserstein distance. Second, based on a two-stage decision architecture, an optimization model for the energy storage system configuration and scheduling scheme is constructed with minimizing the total cost function as the objective function. The first stage is the energy storage system configuration decision stage, used to optimize the scheduling decision of the energy storage system under the worst-case probability distribution contained in the load uncertainty probability fuzzy set. The second stage is the energy storage system scheduling decision stage, used to determine the worst-case probability distribution contained in the load uncertainty probability fuzzy set. The energy storage system scheduling decision includes a total cost comprising the configuration cost during the energy storage system configuration decision stage and the scheduling cost during the energy storage system scheduling decision stage. Further, in the energy storage system configuration and scheduling scheme optimization model, a collaborative operation mechanism between fixed and mobile energy storage systems is constructed. This collaborative operation mechanism is used to achieve energy complementarity and scheduling coordination between the fixed and mobile energy storage systems in the spatiotemporal dimensions, including a dynamic capacity allocation model and a location status model for the mobile energy storage system, and an operation model for the fixed energy storage system. Finally, based on a column and constraint generation algorithm, the energy storage system configuration and scheduling scheme optimization model is iteratively solved to obtain the configuration schemes and scheduling schemes for both fixed and mobile energy storage systems. Compared with existing technologies, the embodiments of this application first adopt a two-stage decision-making architecture to jointly optimize energy storage configuration and operation scheduling. The scheduling cost under the worst probability distribution is introduced into the objective function, enabling the configuration scheme to proactively defend against various adverse scenarios that may occur in the future. This balances investment economy with the safety and flexibility of the operation phase. Furthermore, by using a fuzzy set of load uncertainty probabilities, the possible range of load fluctuations is described in a data-driven manner, allowing the model to avoid over-conservatism while considering uncertainty. This reduces the problem of over-investment caused by conservative configuration while ensuring the robustness of the model. Second, a collaborative operation mechanism between fixed energy storage systems and mobile energy storage systems is constructed. Through the dynamic capacity allocation model and location status model of the mobile energy storage system, constraints such as transportation loss, movement delay, and location migration are imposed on it. This allows the mobile energy storage to dynamically adjust its access location according to the real-time demand of the power grid, forming a spatiotemporal complementarity with the fixed energy storage system. This effectively solves the problem that traditional fixed energy storage cannot respond to the rapidly changing and regionally significant power shortages or congestion in the power grid due to its fixed geographical location. The flexible scheduling of the mobile energy storage system enables cross-regional energy support, significantly improving the power grid's ability to respond to local emergencies.

[0022] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0023] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the scope of this application. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 A flowchart illustrating a method for generating an energy storage system configuration and scheduling scheme according to an embodiment of this application is shown. Figure 2 This paper illustrates a flowchart of the probabilistic fuzzy set construction process for load uncertainty provided in an embodiment of this application. Figure 3 This paper shows a block diagram of a device for generating an energy storage system configuration and scheduling scheme according to an embodiment of this application; Figure 4 A schematic diagram of the structure of a terminal provided in an embodiment of this application is shown. Detailed Implementation

[0024] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0025] At the same time, it should be understood that, for ease of description, the dimensions of the various parts shown in the accompanying drawings are not drawn according to actual scale.

[0026] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit the scope of this application and its application or use.

[0027] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and equipment should be considered part of the specification.

[0028] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.

[0029] The embodiments of this application can be applied to computer systems / servers that can operate with a wide range of other general-purpose or special-purpose computing system environments or configurations. Examples of well-known computing systems, environments, and / or configurations suitable for use with computer systems / servers include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, handheld or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputer systems, mainframe computer systems, and distributed cloud computing environments that include any of the above systems, etc.

[0030] Computer systems / servers can be described in the general context of computer system executable instructions (such as program modules) executed by the computer system. Typically, program modules can include routines, programs, object programs, components, logic, data structures, etc., which perform specific tasks or implement specific abstract data types. Computer systems / servers can be implemented in distributed cloud computing environments, where tasks are performed by remote processing devices linked through a communication network. In distributed cloud computing environments, program modules can reside on local or remote computing system storage media, including storage devices.

[0031] This application provides a method for generating an energy storage system configuration and scheduling scheme, such as... Figure 1 As shown, the method includes: 101. Obtain the historical load forecast data set and the historical load actual data set of the target power grid, and construct a load uncertainty probability fuzzy set based on Wasserstein distance according to the historical load forecast data set and the historical load actual data set.

[0032] The historical load forecast dataset contains load forecast data for nodes at multiple historical moments, and the load forecast data is based on prediction models; the historical load real dataset contains the actual measured load of nodes at the same historical moment; the Wasserstein distance is used to measure the difference between two probability distributions; and the load uncertainty probability fuzzy set is used to describe the possible range of load fluctuations.

[0033] In this embodiment of the application, the current execution end can be the planning and operation optimization module of the power distribution system.

[0034] It should be noted that constructing a fuzzy set of load uncertainty probabilities based on Wasserstein distance can make full use of statistical information in historical data, describe the possible range of load fluctuations in a data-driven manner, and prevent the model from being overly conservative while considering uncertainty. This reduces redundant investment caused by conservatism while ensuring the robustness of the model.

[0035] 102. Based on a two-stage decision-making architecture, an optimization model for energy storage system configuration and scheduling schemes is constructed with the goal of minimizing the total cost function.

[0036] The first stage is the energy storage system configuration decision stage, which is used to determine the capacity and power configuration decisions of stationary and mobile energy storage systems at various nodes in the target power grid. The second stage is the energy storage system scheduling decision stage, which is used to optimize the scheduling decisions of the energy storage system under the worst probability distribution contained in the load uncertainty probability fuzzy set. The worst probability distribution is used to characterize the probability distribution that makes the scheduling cost of the energy storage system reach the maximum value during the operation phase under the load uncertainty probability fuzzy set, i.e. the worst load fluctuation mode. The total cost includes the configuration cost of the energy storage system configuration decision stage and the scheduling cost of the energy storage system scheduling decision stage.

[0037] It should be noted that in this embodiment, an optimization model for energy storage system configuration and scheduling is constructed based on a two-stage decision-making architecture. This model jointly optimizes energy storage configuration and operation scheduling, and introduces scheduling costs under the worst-case probability distribution into the objective function. This enables the configuration scheme to proactively defend against various adverse scenarios that may occur in the future, taking into account both investment economy and ensuring safety and flexibility during the operation phase.

[0038] 103. In the optimization model of energy storage system configuration and scheduling scheme, construct a collaborative operation mechanism between stationary energy storage system and mobile energy storage system.

[0039] The collaborative operation mechanism is used to achieve energy complementarity and scheduling coordination between stationary and mobile energy storage systems in the spatiotemporal dimensions. It includes the dynamic capacity allocation model and location status model of the mobile energy storage system, as well as the operation model of the stationary energy storage system. The dynamic capacity allocation model of the mobile energy storage system describes the energy changes of each mobile energy storage system during movement and charging / discharging. The location status model of the mobile energy storage system describes the changes in the node location of the mobile energy storage system during each scheduling period. The operation model of the stationary energy storage system describes the dynamic changes in the state of charge of the stationary energy storage system during each period.

[0040] It should be noted that, in the embodiments of this application, the mobile energy storage system is constrained in many aspects such as transportation loss, movement delay and location migration through the dynamic capacity allocation model and location status model of the mobile energy storage system. This enables the mobile energy storage to dynamically adjust its access location according to the real-time demand of the power grid, forming a spatiotemporal complement with the fixed energy storage system. This effectively solves the problem that traditional fixed energy storage cannot respond to the power shortage or blockage that is dynamic and regional in nature in the power grid due to its fixed geographical location. The flexible scheduling of the mobile energy storage system enables cross-regional energy support, which significantly improves the power grid's ability to respond to local emergencies.

[0041] 104. Based on the column and constraint generation algorithm, the optimization model of energy storage system configuration and scheduling scheme is solved iteratively to obtain the configuration scheme of fixed energy storage system and mobile energy storage system, as well as the scheduling scheme of fixed energy storage system and mobile energy storage system.

[0042] The configuration schemes for stationary and mobile energy storage systems include the configuration capacity and rated power of the stationary energy storage system at each node in the target power grid, as well as the configuration capacity and rated power of the mobile energy storage system. The scheduling schemes for stationary and mobile energy storage systems include the charging / discharging power of the stationary energy storage system at each node in the target power grid during each time period, the charging / discharging power of each mobile energy storage system during each time period and the node number, the power purchased by each node from the main grid during each time period, and the charging / discharging state variables of each energy storage system during each time period.

[0043] It should be noted that in the embodiments of this application, a column and constraint generation algorithm is used for iterative solution, which decomposes the complex sub-barbaric optimization model into a main problem and sub-problems to be solved alternately. By identifying the worst-case scenario and dynamically adding constraints, it can efficiently approximate the global optimal solution and generate an energy storage system configuration and scheduling scheme that is both economical and robust.

[0044] Compared with existing technologies, the embodiments of this application first adopt a two-stage decision-making architecture to jointly optimize energy storage configuration and operation scheduling. The scheduling cost under the worst probability distribution is introduced into the objective function, enabling the configuration scheme to proactively defend against various adverse scenarios that may occur in the future. This balances investment economy with the safety and flexibility of the operation phase. Furthermore, by using a fuzzy set of load uncertainty probabilities, the possible range of load fluctuations is described in a data-driven manner, allowing the model to avoid over-conservatism while considering uncertainty. This reduces the problem of over-investment caused by conservative configuration while ensuring the robustness of the model. Second, a collaborative operation mechanism between fixed energy storage systems and mobile energy storage systems is constructed. Through the dynamic capacity allocation model and location status model of the mobile energy storage system, constraints such as transportation loss, movement delay, and location migration are imposed on it. This allows the mobile energy storage to dynamically adjust its access location according to the real-time demand of the power grid, forming a spatiotemporal complementarity with the fixed energy storage system. This effectively solves the problem that traditional fixed energy storage cannot respond to the rapidly changing and regionally significant power shortages or congestion in the power grid due to its fixed geographical location. The flexible scheduling of the mobile energy storage system enables cross-regional energy support, significantly improving the power grid's ability to respond to local emergencies.

[0045] In one embodiment of this application, for further definition and explanation, such as Figure 2As shown, in step 101 of the embodiment, a fuzzy set of load uncertainty probability is constructed based on the Wasserstein distance according to the historical load forecast data set and the historical load real data set, including: 201. Based on the historical load forecast data set and the historical load actual data set, calculate the historical load error data set of the target power grid, and calculate the corresponding normalized random error set based on the historical load error data set.

[0046] In this embodiment of the application, for each node at each historical moment, the difference between the historical load prediction data and the historical load actual data is calculated to obtain the corresponding historical load error data. Then, all historical load error data are normalized to obtain the normalized random error set.

[0047] 202. Construct historical empirical probability distributions based on normalized random error sets.

[0048] The historical probability distribution is as follows: , Represents the probability distribution based on historical experience. This represents the number of data points in the normalized random error set. Represents the Dirac function, This represents the normalized random error.

[0049] 203. Determine the radius of the probabilistic fuzzy set based on the pre-set confidence level, and construct the load uncertainty probabilistic fuzzy set with the historical experience probability distribution as the center of the sphere and the radius of the probabilistic fuzzy set as the radius of the sphere.

[0050] The radius of the probabilistic fuzzy set is used to measure the difference between historical empirical probability distributions and arbitrary probability distributions. The load uncertainty probabilistic fuzzy set contains all probability distributions whose Wasserstein distance from the historical empirical probability distribution is within the radius of the probabilistic fuzzy set.

[0051] In this embodiment of the application, the relationship between the preset confidence level and the radius of the probabilistic fuzzy set is as follows: , , , in, Represents random variables and joint distribution The first marginal distribution, , , Represents random variables and joint distribution The second marginal distribution, Represents the support set of random variables. Indicates the preset credit level. Represents the radius of the probabilistic fuzzy set. Represents the characteristic constants of the sample support set. Representing a constant, it can be used to solve optimization problems. To obtain.

[0052] The probability fuzzy set of load uncertainty is, , , in, This represents a fuzzy set representing the probability of load uncertainty. Indicates the support set of random variables The set of all possible probability distributions on the , Indicates the first marginal distribution With the second marginal distribution Wasserstein distance between them Let represent the joint distribution. The expected value of the following mathematical expression The order of the norm.

[0053] In one embodiment of this application, for further definition and explanation, the energy storage system configuration and scheduling scheme optimization model in step 102 of the embodiment is as follows: , in, This represents the configuration cost of configuration scheme X for both stationary and mobile energy storage systems. This indicates the random error in configuration scheme X and load. The scheduling cost below represents This represents the probability fuzzy set of load uncertainty. Take the worst probability distribution , This represents the feasible constraint domain for energy storage configuration schemes.

[0054] Furthermore, the configuration cost function is: , in, This represents the pre-designated set of nodes in the power grid where energy storage systems are expected to be installed. This represents the unit capacity cost of a stationary energy storage system. This represents the configured capacity of the fixed energy storage system at node i. This represents the unit power cost of a stationary energy storage system. This represents the rated power of the stationary energy storage system at node i. This represents the unit capacity cost of a mobile energy storage system. This represents the configured capacity of the mobile energy storage system at node i. This represents the unit power cost of a mobile energy storage system. This represents the rated power of the mobile energy storage system at node i.

[0055] The scheduling cost function is, , in, Let N represent the scheduling cost, N represent the number of nodes, and T represent the number of time points. express, This represents the grid purchase cost of node i during time period t. This represents the actual amount of electricity purchased by node i from the power grid during time period t. This represents the cost of power grid transmission losses. Indicates the penalty coefficient. This represents the predicted electricity purchases by node i during time period t.

[0056] In one embodiment of this application, for further definition and explanation, the dynamic capacity allocation model of the mobile energy storage system included in the collaborative operation mechanism between the stationary energy storage system and the mobile energy storage system constructed in step 103 of the embodiment is as follows: , in, This represents the remaining energy of the k-th mobile energy storage system at time t+1. This represents the transportation energy loss coefficient of the k-th mobile energy storage system. Let represent the remaining energy of the k-th mobile energy storage system during time period t. This represents the discharge power of the k-th mobile energy storage system during time period t at node i. This represents the discharge efficiency of the k-th mobile energy storage system. This represents the charging efficiency of the k-th mobile energy storage system. This represents the charging power of the k-th mobile energy storage system during time period t at node i. This represents the set of mobile energy storage system numbers. This represents the set of scheduling periods.

[0057] In one embodiment of this application, for further definition and explanation, the location state model of the mobile energy storage system included in the collaborative operation mechanism between the stationary energy storage system and the mobile energy storage system constructed in step 103 of the embodiment is as follows: , , in, This indicates the node where the k-th mobile energy storage system is located during time period t+1. This represents the correlation between mobility delay and power grid topology, characterizing the spatiotemporal evolution of location parameters. This represents the node where the k-th mobile energy storage system is located during time period t. This represents the travel time of the k-th mobile energy storage system. This represents the average moving speed of the k-th mobile energy storage system. This represents the actual distance traveled based on the power grid topology.

[0058] In one embodiment of this application, for further definition and explanation, the operational model of the fixed energy storage system included in the collaborative operation mechanism between the fixed energy storage system and the mobile energy storage system constructed in step 103 of the embodiment is as follows: , , in, This represents the remaining energy of the f-th stationary energy storage system at node i during time period t+1. This represents the remaining energy of the f-th stationary energy storage system at node i during time period t. This represents the discharge power of the f-th stationary energy storage system at node i during time period t. This represents the discharge efficiency of the f-th stationary energy storage system. Let f represent the charging efficiency of the f-th stationary energy storage system. Let represent the charging power of the f-th stationary energy storage system at node i during time period t. This represents the power of the f-th stationary energy storage system at node i. This represents the minimum power value of the f-th stationary energy storage system. This represents the maximum power value of the f-th stationary energy storage system.

[0059] In specific application scenarios, the collaborative operation mechanism between the stationary energy storage system and the mobile energy storage system constructed in step 103 of the embodiment also includes a power constraint model for the mobile energy storage system. , in, This represents the minimum power value of the k-th mobile energy storage system. This represents the power of the k-th mobile energy storage system at node i. This represents the maximum power value of the k-th mobile energy storage system.

[0060] In one embodiment of this application, for further definition and explanation, the energy storage system configuration and scheduling scheme optimization model in step 102 of the embodiment also includes grid operation safety constraints.

[0061] Among them, the power grid operation safety constraints include line power flow constraints, node power balance constraints, and node voltage safety constraints.

[0062] The power flow constraints for the line are as follows. , , , in, This represents the square of the voltage amplitude at node i during time period t. Let represent the squares of the voltage amplitudes at nodes i and j during time period t. This represents the resistance of the line (i,j). This represents the active power flowing from node i to node j during time period t. This represents the reactance of line (i,j). This represents the reactive power flowing from node i to node j during time period t. Let represent the square of the current amplitude flowing through line (i,j) during time period t. Represents the set of all lines in the power grid. This represents the maximum apparent power capacity allowed for line (i,j).

[0063] The node power balance constraint is as follows: , in, This represents the active power flowing from node j to node i during time period t. This represents the resistance of the line (j,i). Let represent the square of the current amplitude flowing through line (j,i) during time period t. This represents the total power output of node i during time period t. This represents the basic active power load demand of node i during time period t. This represents the discharge power of node i during time period t. This represents the charging power of node i during time period t.

[0064] The node voltage safety constraint is as follows: , in, This represents the minimum allowable voltage value for node i. This represents the highest voltage value allowed for node i.

[0065] In one embodiment of this application, for further definition and explanation, step 104 of the embodiment is based on a column and constraint generation algorithm to iteratively solve the optimization model of the energy storage system configuration and scheduling scheme, obtaining the configuration scheme of the fixed energy storage system and the mobile energy storage system, as well as the scheduling scheme of the fixed energy storage system and the mobile energy storage system, including: The master problem is established based on the energy storage system configuration decision-making stage, where the master problem is used to determine the trial configuration scheme; Based on the energy storage system scheduling decision-making stage, a sub-problem is established. The sub-problem is used to query the probability distribution that maximizes the scheduling cost value in the fuzzy set of load uncertainty probability under the trial configuration scheme, as the worst probability distribution, and generate the corresponding scheduling scheme and constraints. Add the constraints corresponding to the worst probability distribution as new constraints to the main problem to update the main problem; The main problem and subproblems are solved iteratively until the difference between the total cost value obtained after solving the main problem and the cost value returned by the subproblems is less than the preset tolerance, thus obtaining the configuration scheme of the fixed energy storage system and the mobile energy storage system, as well as the scheduling scheme of the fixed energy storage system and the mobile energy storage system.

[0066] The total cost value obtained after solving the main problem includes the configuration cost of the proposed configuration scheme and the operation and scheduling costs under all currently considered adverse scenarios. The cost value returned by the subproblem is the operation and scheduling cost under the configuration scheme determined by the main problem, and the probability distribution that maximizes the scheduling cost value by querying the fuzzy set of load uncertainty probabilities. The difference between the two is less than the preset tolerance, indicating that the conservative estimated cost under known partial adverse scenarios is sufficiently close to the potential risk cost under the worst-case scenario that has not yet been considered under the given configuration. That is, the current configuration can withstand all newly discovered adverse scenarios, and at this point, the algorithm converges.

[0067] This application provides a method for generating an energy storage system configuration and scheduling scheme. First, it acquires a set of historical load forecast data and a set of historical load actual data for the target power grid. Then, based on these data, it constructs a load uncertainty probability fuzzy set using Wasserstein distance. Second, based on a two-stage decision architecture, it constructs an optimization model for the energy storage system configuration and scheduling scheme, using minimizing the total cost function as the objective function. The first stage is the energy storage system configuration decision stage, used to optimize the scheduling decision of the energy storage system under the worst-case probability distribution contained in the load uncertainty probability fuzzy set. The second stage is the energy storage system scheduling decision stage, used to determine the energy storage system under the worst-case probability distribution contained in the load uncertainty probability fuzzy set. The scheduling decision includes the total cost of the energy storage system configuration decision stage and the scheduling cost of the energy storage system scheduling decision stage. Further, in the energy storage system configuration and scheduling scheme optimization model, a collaborative operation mechanism between fixed energy storage systems and mobile energy storage systems is constructed. This collaborative operation mechanism is used to achieve energy complementarity and scheduling coordination between fixed and mobile energy storage systems in the spatiotemporal dimension, including a dynamic capacity allocation model and a location status model for the mobile energy storage system, and an operation model for the fixed energy storage system. Finally, based on a column and constraint generation algorithm, the energy storage system configuration and scheduling scheme optimization model is iteratively solved to obtain the configuration schemes for fixed and mobile energy storage systems, as well as the scheduling schemes for both. Compared with existing technologies, the embodiments of this application first adopt a two-stage decision-making architecture to jointly optimize energy storage configuration and operation scheduling. The scheduling cost under the worst probability distribution is introduced into the objective function, enabling the configuration scheme to proactively defend against various adverse scenarios that may occur in the future. This balances investment economy with the safety and flexibility of the operation phase. Furthermore, by using a fuzzy set of load uncertainty probabilities, the possible range of load fluctuations is described in a data-driven manner, allowing the model to avoid over-conservatism while considering uncertainty. This reduces the problem of over-investment caused by conservative configuration while ensuring the robustness of the model. Second, a collaborative operation mechanism between fixed energy storage systems and mobile energy storage systems is constructed. Through the dynamic capacity allocation model and location status model of the mobile energy storage system, constraints such as transportation loss, movement delay, and location migration are imposed on it. This allows the mobile energy storage to dynamically adjust its access location according to the real-time demand of the power grid, forming a spatiotemporal complementarity with the fixed energy storage system. This effectively solves the problem that traditional fixed energy storage cannot respond to the rapidly changing and regionally significant power shortages or congestion in the power grid due to its fixed geographical location. The flexible scheduling of the mobile energy storage system enables cross-regional energy support, significantly improving the power grid's ability to respond to local emergencies.

[0068] Furthermore, as a response to the above Figure 1The implementation of the method shown in this application provides an apparatus for generating an energy storage system configuration and scheduling scheme, such as... Figure 3 As shown, the device includes: Load uncertainty probability fuzzy set construction module 31, energy storage system configuration and scheduling scheme optimization model construction module 32, collaborative operation mechanism construction module 33, energy storage system configuration and scheduling scheme optimization model solving module 34; The load uncertainty probability fuzzy set construction module 31 is used to obtain the historical load prediction data set and the historical load real data set of the target power grid, and construct the load uncertainty probability fuzzy set based on the Wasserstein distance according to the historical load prediction data set and the historical load real data set. The energy storage system configuration and scheduling scheme optimization model construction module 32 is used to construct an energy storage system configuration and scheduling scheme optimization model based on a two-stage decision architecture, with minimizing the total cost function as the objective function. The first stage is the energy storage system configuration decision stage, which is used to optimize the scheduling decision of the energy storage system under the worst probability distribution contained in the load uncertainty probability fuzzy set. The second stage is the energy storage system scheduling decision stage, which is used to determine the scheduling decision of the energy storage system under the worst probability distribution contained in the load uncertainty probability fuzzy set. The total cost includes the configuration cost of the energy storage system configuration decision stage and the scheduling cost of the energy storage system scheduling decision stage. The collaborative operation mechanism construction module 33 is used to construct a collaborative operation mechanism between the fixed energy storage system and the mobile energy storage system in the energy storage system configuration and scheduling scheme optimization model. The collaborative operation mechanism is used to realize energy complementarity and scheduling coordination between the fixed energy storage system and the mobile energy storage system in the spatiotemporal dimension, including the dynamic capacity allocation model and location status model of the mobile energy storage system and the operation model of the fixed energy storage system. The energy storage system configuration and scheduling scheme optimization model solving module 34 is used to iteratively solve the energy storage system configuration and scheduling scheme optimization model based on the column and constraint generation algorithm, so as to obtain the configuration scheme of fixed energy storage system and mobile energy storage system, as well as the scheduling scheme of fixed energy storage system and mobile energy storage system.

[0069] In specific application scenarios, the load uncertainty probability fuzzy set construction module is used for: Based on the historical load forecast data set and the historical load actual data set, the historical load error data set of the target power grid is calculated, and the corresponding normalized random error set is calculated based on the historical load error data set. A historical empirical probability distribution is constructed based on the normalized random error set; The radius of the probabilistic fuzzy set is determined based on a preset confidence level. A load uncertainty probabilistic fuzzy set is constructed with the historical empirical probability distribution as the center of the sphere and the radius of the probabilistic fuzzy set as the radius of the sphere. The radius of the probabilistic fuzzy set is used to measure the difference between the historical empirical probability distribution and any probability distribution. The load uncertainty probabilistic fuzzy set contains all probability distributions whose Wasserstein distance from the historical empirical probability distribution is within the radius of the probabilistic fuzzy set.

[0070] In specific application scenarios, the optimization model for the energy storage system configuration and scheduling scheme is as follows: , in, This represents the configuration cost of configuration scheme X for both stationary and mobile energy storage systems. This indicates the random error in configuration scheme X and load. The scheduling cost below represents This represents the probability fuzzy set of load uncertainty. Take the worst probability distribution , This represents the feasible constraint domain for energy storage configuration schemes.

[0071] In specific application scenarios, the dynamic capacity allocation model of the mobile energy storage system is as follows: , in, This represents the remaining energy of the k-th mobile energy storage system at time t+1. This represents the transportation energy loss coefficient of the k-th mobile energy storage system. Let represent the remaining energy of the k-th mobile energy storage system during time period t. This represents the discharge power of the k-th mobile energy storage system during time period t at node i. This represents the discharge efficiency of the k-th mobile energy storage system. This represents the charging efficiency of the k-th mobile energy storage system. This represents the charging power of the k-th mobile energy storage system during time period t at node i. This represents the set of mobile energy storage system numbers. This represents the set of scheduling periods.

[0072] In specific application scenarios, the location state model of the mobile energy storage system is as follows: , , in, This indicates the node where the k-th mobile energy storage system is located during time period t+1. This represents the correlation between mobility delay and power grid topology, characterizing the spatiotemporal evolution of location parameters. This represents the node where the k-th mobile energy storage system is located during time period t. This represents the travel time of the k-th mobile energy storage system. This represents the average moving speed of the k-th mobile energy storage system. This represents the actual distance traveled based on the power grid topology.

[0073] In specific application scenarios, the operating model of the stationary energy storage system is as follows: , , in, This represents the remaining energy of the f-th stationary energy storage system at node i during time period t+1. This represents the remaining energy of the f-th stationary energy storage system at node i during time period t. This represents the discharge power of the f-th stationary energy storage system at node i during time period t. This represents the discharge efficiency of the f-th stationary energy storage system. Let f represent the charging efficiency of the f-th stationary energy storage system. Let represent the charging power of the f-th stationary energy storage system at node i during time period t. This represents the power of the f-th stationary energy storage system at node i. This represents the minimum power value of the f-th stationary energy storage system. This represents the maximum power value of the f-th stationary energy storage system. This represents the set of nodes in the power grid that are pre-designated to have energy storage systems installed.

[0074] In specific application scenarios, the energy storage system configuration and scheduling scheme optimization model also includes power grid operation safety constraints, which include line power flow constraints, node power balance constraints, and node voltage safety constraints.

[0075] This application provides a device for generating an energy storage system configuration and scheduling scheme. First, it acquires a set of historical load forecast data and a set of historical load actual data for the target power grid. Based on these data, it constructs a load uncertainty probability fuzzy set using Wasserstein distance. Second, based on a two-stage decision architecture, it constructs an optimization model for the energy storage system configuration and scheduling scheme, using minimizing the total cost function as the objective function. The first stage is the energy storage system configuration decision stage, used to optimize the scheduling decision of the energy storage system under the worst-case probability distribution contained in the load uncertainty probability fuzzy set. The second stage is the energy storage system scheduling decision stage, used to determine the energy storage system under the worst-case probability distribution contained in the load uncertainty probability fuzzy set. The scheduling decision includes the total cost of the energy storage system configuration decision stage and the scheduling cost of the energy storage system scheduling decision stage. Further, in the energy storage system configuration and scheduling scheme optimization model, a collaborative operation mechanism between fixed energy storage systems and mobile energy storage systems is constructed. This collaborative operation mechanism is used to achieve energy complementarity and scheduling coordination between fixed and mobile energy storage systems in the spatiotemporal dimension, including a dynamic capacity allocation model and a location status model for the mobile energy storage system, and an operation model for the fixed energy storage system. Finally, based on a column and constraint generation algorithm, the energy storage system configuration and scheduling scheme optimization model is iteratively solved to obtain the configuration schemes for fixed and mobile energy storage systems, as well as the scheduling schemes for both. Compared with existing technologies, the embodiments of this application first adopt a two-stage decision-making architecture to jointly optimize energy storage configuration and operation scheduling. The scheduling cost under the worst probability distribution is introduced into the objective function, enabling the configuration scheme to proactively defend against various adverse scenarios that may occur in the future. This balances investment economy with the safety and flexibility of the operation phase. Furthermore, by using a fuzzy set of load uncertainty probabilities, the possible range of load fluctuations is described in a data-driven manner, allowing the model to avoid over-conservatism while considering uncertainty. This reduces the problem of over-investment caused by conservative configuration while ensuring the robustness of the model. Second, a collaborative operation mechanism between fixed energy storage systems and mobile energy storage systems is constructed. Through the dynamic capacity allocation model and location status model of the mobile energy storage system, constraints such as transportation loss, movement delay, and location migration are imposed on it. This allows the mobile energy storage to dynamically adjust its access location according to the real-time demand of the power grid, forming a spatiotemporal complementarity with the fixed energy storage system. This effectively solves the problem that traditional fixed energy storage cannot respond to the rapidly changing and regionally significant power shortages or congestion in the power grid due to its fixed geographical location. The flexible scheduling of the mobile energy storage system enables cross-regional energy support, significantly improving the power grid's ability to respond to local emergencies.

[0076] According to one embodiment of this application, a storage medium is provided, the storage medium storing at least one executable instruction, which can execute the method for generating an energy storage system configuration scheduling scheme in any of the above method embodiments.

[0077] Based on this understanding, the technical solution of this application can be embodied in the form of a software product. The software product can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, or portable hard drive), and includes several instructions to cause a computer device (such as a personal computer, server, or network device) to execute the methods described in the various implementation scenarios of this application.

[0078] Figure 4 The diagram shows a structural schematic of a terminal according to one embodiment of the present application. The specific embodiments of the present application do not limit the specific implementation of the terminal.

[0079] like Figure 4 As shown, the terminal may include: a processor 402, a communications interface 404, a memory 406, and a communications bus 408.

[0080] The processor 402, communication interface 404, and memory 406 communicate with each other via communication bus 408.

[0081] Communication interface 404 is used to communicate with other network elements such as clients or other servers.

[0082] The processor 402 is used to execute program 410, which can specifically execute the relevant steps in the above-described embodiment of the method for generating energy storage system configuration and scheduling scheme.

[0083] Specifically, program 410 may include program code that includes computer operation instructions.

[0084] Processor 402 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application. The computer device includes one or more processors, which may be processors of the same type, such as one or more CPUs; or they may be processors of different types, such as one or more CPUs and one or more ASICs.

[0085] Memory 406 is used to store program 410. Memory 406 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0086] Specifically, program 410 can be used to cause processor 402 to perform the following operations: Obtain the historical load forecast data set and the historical load actual data set of the target power grid, and construct a load uncertainty probability fuzzy set based on the Wasserstein distance according to the historical load forecast data set and the historical load actual data set; Based on a two-stage decision-making architecture, an optimization model for energy storage system configuration and scheduling is constructed with minimizing the total cost function as the objective function. The first stage is the energy storage system configuration decision-making stage, which is used to optimize the scheduling decision of the energy storage system under the worst probability distribution contained in the load uncertainty probability fuzzy set. The second stage is the energy storage system scheduling decision-making stage, which is used to optimize the scheduling decision of the energy storage system under the worst probability distribution contained in the load uncertainty probability fuzzy set. The total cost includes the configuration cost of the energy storage system configuration decision-making stage and the scheduling cost of the energy storage system scheduling decision-making stage. In the energy storage system configuration and scheduling scheme optimization model, a collaborative operation mechanism between fixed energy storage system and mobile energy storage system is constructed. The collaborative operation mechanism is used to realize energy complementarity and scheduling coordination between fixed energy storage system and mobile energy storage system in the spatiotemporal dimension, including dynamic capacity allocation model and location status model of mobile energy storage system and operation model of fixed energy storage system. Based on the column and constraint generation algorithm, the optimization model of the energy storage system configuration and scheduling scheme is iteratively solved to obtain the configuration scheme of the fixed energy storage system and the mobile energy storage system, as well as the scheduling scheme of the fixed energy storage system and the mobile energy storage system.

[0087] The storage medium may also include an operating system and a network communication module. The operating system is a program that manages the hardware and software resources of the physical device used to generate the configuration and scheduling scheme for the aforementioned energy storage system, supporting the operation of information processing programs and other software and / or programs. The network communication module is used to enable communication between the various components within the storage medium, as well as communication with other hardware and software in the information processing physical device.

[0088] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For system embodiments, since they largely correspond to method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0089] The methods and systems of this application may be implemented in many ways. For example, they may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order of steps for the methods is for illustrative purposes only, and the steps of the methods of this application are not limited to the order specifically described above, unless otherwise specifically stated. Furthermore, in some embodiments, this application may also be implemented as a program recorded on a recording medium, the program including machine-readable instructions for implementing the methods according to this application. Thus, this application also covers recording media storing programs for performing the methods according to this application.

[0090] Obviously, those skilled in the art should understand that the modules or steps of this application described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby storing them in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those presented here, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, this application is not limited to any particular combination of hardware and software.

[0091] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for generating a configuration and scheduling scheme for an energy storage system, characterized in that, include: Obtain the historical load forecast data set and the historical load actual data set of the target power grid, and construct a load uncertainty probability fuzzy set based on the Wasserstein distance according to the historical load forecast data set and the historical load actual data set; Based on a two-stage decision-making architecture, an optimization model for energy storage system configuration and scheduling is constructed with minimizing the total cost function as the objective function. The first stage is the energy storage system configuration decision-making stage, which is used to optimize the scheduling decision of the energy storage system under the worst probability distribution contained in the load uncertainty probability fuzzy set. The second stage is the energy storage system scheduling decision-making stage, which is used to optimize the scheduling decision of the energy storage system under the worst probability distribution contained in the load uncertainty probability fuzzy set. The total cost includes the configuration cost of the energy storage system configuration decision-making stage and the scheduling cost of the energy storage system scheduling decision-making stage. In the energy storage system configuration and scheduling scheme optimization model, a collaborative operation mechanism between fixed energy storage system and mobile energy storage system is constructed. The collaborative operation mechanism is used to realize energy complementarity and scheduling coordination between fixed energy storage system and mobile energy storage system in the spatiotemporal dimension, including dynamic capacity allocation model and location status model of mobile energy storage system and operation model of fixed energy storage system. Based on the column and constraint generation algorithm, the optimization model of the energy storage system configuration and scheduling scheme is iteratively solved to obtain the configuration scheme of the fixed energy storage system and the mobile energy storage system, as well as the scheduling scheme of the fixed energy storage system and the mobile energy storage system.

2. The method according to claim 1, characterized in that, The step of constructing a fuzzy set of load uncertainty probabilities based on the historical load forecast data set and the historical load actual data set includes: Based on the historical load forecast data set and the historical load actual data set, the historical load error data set of the target power grid is calculated, and the corresponding normalized random error set is calculated based on the historical load error data set. A historical empirical probability distribution is constructed based on the normalized random error set; The radius of the probabilistic fuzzy set is determined based on a preset confidence level. A load uncertainty probabilistic fuzzy set is constructed with the historical empirical probability distribution as the center of the sphere and the radius of the probabilistic fuzzy set as the radius of the sphere. The radius of the probabilistic fuzzy set is used to measure the difference between the historical empirical probability distribution and any probability distribution. The load uncertainty probabilistic fuzzy set contains all probability distributions whose Wasserstein distance from the historical empirical probability distribution is within the radius of the probabilistic fuzzy set.

3. The method according to claim 1, characterized in that, The optimization model for the energy storage system configuration and scheduling scheme is as follows: ， in, This represents the configuration cost of configuration scheme X for both stationary and mobile energy storage systems. This indicates the random error in configuration scheme X and load. The scheduling cost below represents This represents the probability fuzzy set of load uncertainty. Take the worst probability distribution , This represents the feasible constraint domain for energy storage configuration schemes.

4. The method according to claim 1, characterized in that, The dynamic capacity allocation model of the mobile energy storage system is as follows: ， in, This represents the remaining energy of the k-th mobile energy storage system at time t+1. This represents the transportation energy loss coefficient of the k-th mobile energy storage system. Let represent the remaining energy of the k-th mobile energy storage system during time period t. This represents the discharge power of the k-th mobile energy storage system during time period t at node i. This represents the discharge efficiency of the k-th mobile energy storage system. This represents the charging efficiency of the k-th mobile energy storage system. This represents the charging power of the k-th mobile energy storage system during time period t at node i. This represents the set of mobile energy storage system numbers. This represents the set of scheduling periods.

5. The method according to claim 1, characterized in that, The location state model of the mobile energy storage system is as follows: ， ， in, This indicates the node where the k-th mobile energy storage system is located during time period t+1. This represents the correlation between mobility delay and power grid topology, characterizing the spatiotemporal evolution of location parameters. This represents the node where the k-th mobile energy storage system is located during time period t. This represents the travel time of the k-th mobile energy storage system. This represents the average moving speed of the k-th mobile energy storage system. This represents the actual distance traveled based on the power grid topology.

6. The method according to claim 1, characterized in that, The operating model of the stationary energy storage system is as follows: ， ， in, This represents the remaining energy of the f-th stationary energy storage system at node i during time period t+1. This represents the remaining energy of the f-th stationary energy storage system at node i during time period t. This represents the discharge power of the f-th stationary energy storage system at node i during time period t. This represents the discharge efficiency of the f-th stationary energy storage system. Let f represent the charging efficiency of the f-th stationary energy storage system. Let represent the charging power of the f-th stationary energy storage system at node i during time period t. This represents the power of the f-th stationary energy storage system at node i. This represents the minimum power value of the f-th stationary energy storage system. This represents the maximum power value of the f-th stationary energy storage system. This represents the set of nodes in the power grid that are pre-designated to have energy storage systems installed.

7. The method according to claim 1, characterized in that, The energy storage system configuration and scheduling scheme optimization model also includes power grid operation safety constraints, which include line power flow constraints, node power balance constraints, and node voltage safety constraints.

8. A device for generating a configuration and scheduling scheme for an energy storage system, characterized in that, include: The load uncertainty probability fuzzy set construction module is used to obtain the historical load prediction data set and the historical load actual data set of the target power grid, and construct the load uncertainty probability fuzzy set based on the Wasserstein distance according to the historical load prediction data set and the historical load actual data set. The energy storage system configuration and scheduling scheme optimization model construction module is used to construct an energy storage system configuration and scheduling scheme optimization model based on a two-stage decision architecture, with minimizing the total cost function as the objective function. The first stage is the energy storage system configuration decision stage, which is used to optimize the scheduling decision of the energy storage system under the worst probability distribution contained in the load uncertainty probability fuzzy set. The second stage is the energy storage system scheduling decision stage, which is used to determine the scheduling decision of the energy storage system under the worst probability distribution contained in the load uncertainty probability fuzzy set. The total cost includes the configuration cost of the energy storage system configuration decision stage and the scheduling cost of the energy storage system scheduling decision stage. The collaborative operation mechanism construction module is used to construct a collaborative operation mechanism between fixed energy storage systems and mobile energy storage systems in the energy storage system configuration and scheduling scheme optimization model. The collaborative operation mechanism is used to realize energy complementarity and scheduling coordination between fixed energy storage systems and mobile energy storage systems in the spatiotemporal dimension, including the dynamic capacity allocation model and location status model of mobile energy storage systems and the operation model of fixed energy storage systems. The energy storage system configuration and scheduling scheme optimization model solution module is used to iteratively solve the energy storage system configuration and scheduling scheme optimization model based on the column and constraint generation algorithm, so as to obtain the configuration scheme of fixed energy storage system and mobile energy storage system, as well as the scheduling scheme of fixed energy storage system and mobile energy storage system.

9. A storage medium storing at least one executable instruction, characterized in that, The executable instructions cause the processor to perform the operations corresponding to the energy storage system configuration scheduling scheme generation method as described in any one of claims 1-7.

10. A terminal, comprising: The processor, memory, communication interface, and communication bus are provided, wherein the processor, memory, and communication interface communicate with each other via the communication bus. The memory is used to store at least one executable instruction, characterized in that the executable instruction causes the processor to perform the operation corresponding to the method for generating the energy storage system configuration scheduling scheme as described in any one of claims 1-7.

Images