A method, device, medium, and product for energy storage capacity and power configuration

Abstract

This application discloses a method, device, medium, and product for configuring energy storage capacity and power, relating to the field of energy storage data processing. The method includes establishing an investment and operation cost model for the system under a shared reservoir operation mode to obtain an outer-layer optimization model; constructing outer-layer optimization constraints, an inner-layer optimization model, and inner-layer optimization constraints; under the outer-layer optimization constraints, using a particle swarm optimization algorithm to optimize the outer-layer optimization model to obtain the optimal outer-layer command; under the inner-layer optimization constraints, using a whale optimization algorithm to optimize the inner-layer optimization model to obtain the optimal inner-layer command; returning the optimal inner-layer command to the outer-layer optimization model to obtain the system's economic characteristics; and based on the system's economic characteristics, determining that scheduling is completed based on the optimal inner-layer command and the optimized outer-layer optimization model, provided the outer-layer optimization model meets the set conditions. This application can minimize the operating cost of pumped storage systems while improving the flexibility and reliability of energy storage systems.

Description

Technical Field

[0001] This application relates to the field of energy storage data processing, and particularly to a method, device, medium and product for energy storage capacity and power configuration. Background Art

[0002] The volatility of wind energy and solar energy will affect the stability and reliability of the power system. Energy storage can alleviate this problem by peak shaving and valley filling. Among them, energy storage batteries have the advantages of small floor area, high energy density, smaller space requirements, more flexible deployment locations, etc., and pumped storage power stations have the advantages of high energy storage capacity, relatively long cycle life, and better economy. The combination of large-scale and high-proportion renewable energy and energy storage is the main way to achieve carbon neutrality. Therefore, the reasonable configuration of renewable energy and energy storage is particularly important.

[0003] In actual projects, it is determined by the deviation between the installed capacity of local new energy and the electricity consumption capacity of the load and the carrying capacity of the local power grid. The existing capacity configuration method is to configure the energy storage capacity and power through a two-layer optimization structure, that is, optimizing the energy storage capacity and power in the outer layer and optimizing the scheduling model in the inner layer. However, the energy interaction link of the existing capacity configuration method does not pass through the power grid and is not restricted by the power grid line capacity, which leads to obvious restrictions on the energy transmission of different substations by the power grid line capacity. It cannot reduce the operating cost of the pumped energy storage system to the greatest extent on the basis of improving the flexibility and reliability of the energy storage system. Summary of the Invention

[0004] The purpose of this application is to provide a method, device, medium and product for energy storage capacity and power configuration, which can reduce the operating cost of the pumped energy storage system to the greatest extent on the basis of improving the flexibility and reliability of the energy storage system.

[0005] To achieve the above purpose, this application provides the following solutions:

[0006] In the first aspect, this application provides a method for energy storage capacity and power configuration, including:

[0007] Obtain system economic information; the system economic information includes one or more of the investment cost unit price of wind turbines in each substation, the investment cost unit price of photovoltaic cells, the investment cost unit price of reversible pump turbines, the investment cost unit price of energy storage batteries, the investment cost unit price of reservoir storage capacity, the operation and maintenance cost unit price of wind turbines in each substation, the operation and maintenance cost unit price of photovoltaic cells, the operation and maintenance cost unit price of reversible pump turbines, the operation and maintenance cost unit price of energy storage batteries, the operation and maintenance cost of energy storage battery charging and discharging, the operation and maintenance cost unit price of reservoir storage capacity, the discount rate, and the project cycle.

[0008] Based on the system's economic information, establish an investment cost model and an operation and maintenance cost model for the system under the shared reservoir operation mode;

[0009] An outer optimization model is constructed based on the aforementioned investment cost model and operation and maintenance cost model;

[0010] Based on the shared reservoir operation mode of pumped storage power stations, outer-layer optimization constraints are constructed.

[0011] Under the aforementioned outer optimization constraints, the outer optimization model is optimized using a particle swarm optimization algorithm to obtain the outer optimal command for the energy storage capacity and power configuration of the distribution station area.

[0012] Historical data of the power distribution network is acquired, and a prediction model is established based on the historical data of the power distribution network; the historical data of the power distribution network includes historical power of photovoltaic power, historical power of wind power, and historical power of load.

[0013] The current data of the distribution network is acquired and input into the prediction model to obtain the distribution network prediction data; the current data of the distribution network includes photovoltaic power, wind power, and load power; the distribution network prediction data includes photovoltaic predicted power, wind power predicted power, and load predicted power.

[0014] In the pumped storage power station's shared reservoir operation mode, an inner-layer optimization model and inner-layer optimization constraints are established based on the aforementioned power distribution network prediction data.

[0015] Under the aforementioned inner-layer optimization constraints, the inner-layer optimization model is optimized using the whale intelligent optimization algorithm to obtain the inner-layer optimal command for the energy storage capacity and power configuration of the distribution substation.

[0016] The inner-layer optimal command for the energy storage capacity and power configuration of the distribution substation area is returned to the outer-layer optimization model to obtain the system's economic characteristics; the economic characteristics include: investment cost and operation and maintenance cost.

[0017] Based on the economic characteristics of the system, determine whether the outer optimization model meets the set conditions;

[0018] When the outer optimization model meets the set conditions, the inner optimal command based on the energy storage capacity and power configuration of the distribution substation at this time and the optimized outer optimization model are used to complete the energy storage capacity and power configuration.

[0019] When the outer optimization model does not meet the set conditions, the particle velocity and particle position of the particle swarm intelligent optimization algorithm are adjusted, and the process returns to execute "under the outer optimization constraints, the outer optimization model is optimized using the particle swarm intelligent optimization algorithm to obtain the outer optimal command for the distribution station's energy storage capacity and power configuration."

[0020] Optionally, the outer optimization constraints include one or more of the following: constraints on the upstream reservoir configuration capacity of each distribution area, constraints on the downstream reservoir configuration capacity of each distribution area, constraints on the pump configuration power of each distribution area, constraints on the turbine configuration power of each distribution area, and constraints on the energy storage capacity of a single energy storage battery in each distribution area.

[0021] Optionally, under the outer optimization constraints, the outer optimization model is optimized using a particle swarm optimization algorithm to obtain the outer optimal command for the distribution substation's energy storage capacity and power configuration, specifically including:

[0022] The optimization variables of the outer optimization model are determined; the optimization variables include the installed capacity of the pumps in each substation, the installed capacity of the turbines, the upstream reservoir capacity, and the downstream reservoir capacity.

[0023] A variable space is formed based on the optimized variables, and particles are placed in the variable control.

[0024] Set the maximum number of iterations, initialize the number of iterations and the initial position and initial velocity of each particle in the particle swarm, and iteratively solve the outer optimization model until the maximum number of iterations is reached. Obtain the position information of each particle, and use the position information of each particle as the outer optimal command for the energy storage capacity and power configuration of the distribution station area; the position information includes particle position and velocity.

[0025] Optionally, the pumped storage power station's shared reservoir operation mode includes: a shared upstream reservoir operation mode and a shared downstream reservoir operation mode;

[0026] In the shared upstream reservoir operation mode, the downstream reservoirs of each substation share the same upstream reservoir;

[0027] In the shared downstream reservoir operation mode, the upstream reservoirs of each substation share the same downstream reservoir.

[0028] Optionally, the prediction model is an extreme learning machine, a support vector machine, or an autoregressive model.

[0029] Optionally, the inner-layer optimization constraints include one or more of the following: constraints on the power of wind power plants and photovoltaic power plants, constraints on the power of pumped storage units, constraints on the charging and discharging power of energy storage batteries, constraints on system power balance, constraints on reservoir water storage, constraints on energy storage battery capacity, and constraints on the change in power injected into the transmission network.

[0030] Optionally, in the shared reservoir operation mode of the pumped storage power station, an inner-layer optimization model is established based on the distribution network prediction data, including:

[0031] In the pumped storage power station's shared reservoir operation mode, based on the aforementioned power distribution network prediction data, functions for abandoned wind and photovoltaic power generation, transmission line occupancy, and load shedding are established.

[0032] The inner optimization model is obtained by integrating the abandoned wind and photovoltaic power generation functions, the transmission line occupancy function, and the load shedding function, and assigning weights to each function.

[0033] Secondly, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the energy storage capacity and power configuration method provided above.

[0034] Thirdly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the energy storage capacity and power configuration method provided above.

[0035] Fourthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the energy storage capacity and power configuration method provided above.

[0036] According to the specific embodiments provided in this application, the following technical effects are disclosed:

[0037] This application provides a method, equipment, medium, and product for configuring energy storage capacity and power. Based on the different energy states, energy storage capacities, transmission line carrying capacities, power supply conditions, and load consumption conditions of new energy and pumped storage systems in various distribution areas, a multi-mode energy dispatch model (investment cost model and operation and maintenance cost model) and an optimized control structure (i.e., outer optimization model and inner optimization model) are formed between new energy and pumped storage systems. The system capacity and power configuration are optimized according to the optimized control structure of the system under this operation mode, which can reduce the operating cost of pumped storage systems to the greatest extent while improving the flexibility and reliability of energy storage systems. Furthermore, by utilizing swarm intelligence optimization algorithms (i.e., particle swarm intelligence optimization algorithm and whale intelligence optimization algorithm) to consider the control optimization process between different transformer substations from the perspective of the local power grid, and to calculate the optimal collaborative control results and operating modes between different transformer substations, the energy supply relationship between multiple transformer substations is effectively changed from a single energy mutual assistance mode to a mode of mutual assistance between electricity and water, forming the optimal control of the overall system. While considering the optimal control of the inner layer, the capacity and power configuration of the outer system are also considered using swarm intelligence optimization algorithms, which will be of great significance to the stability and economy of the local power grid operation. Attached Figure Description

[0038] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0039] Figure 1 This is an application environment diagram of an energy storage capacity and power configuration method according to an embodiment of this application;

[0040] Figure 2 A flowchart illustrating a method for configuring energy storage capacity and power according to an embodiment of this application;

[0041] Figure 3 This is a schematic diagram of the operation mode of a pumped storage power station with a downstream reservoir provided in one embodiment of this application;

[0042] Figure 4 This application provides an embodiment of a pumped storage power station operating mode with an upstream reservoir.

[0043] Figure 5 This is a flowchart illustrating the process of obtaining the optimal inner-layer control command using the whale intelligent optimization algorithm, as provided in an embodiment of this application.

[0044] Figure 6 A schematic diagram illustrating the implementation process of an energy storage capacity and power configuration method according to an embodiment of this application;

[0045] Figure 7 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0046] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0047] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0048] The energy storage capacity and power configuration method provided in this application embodiment can be applied to, for example... Figure 1In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be set up independently, integrated into server 104, or placed in the cloud or on other servers. Terminal 102 can send system economic information and current distribution network data to server 104. After receiving the system economic information and current distribution network data, server 104 establishes an investment and operation cost model for the system under the shared reservoir operation mode to obtain an outer optimization model; constructs outer optimization constraints, an inner optimization model, and inner optimization constraints; under the outer optimization constraints, it uses a particle swarm optimization algorithm to optimize the outer optimization model to obtain the outer optimal instruction; under the inner optimization constraints, it uses a whale optimization algorithm to optimize the inner optimization model to obtain the inner optimal instruction; it returns the inner optimal instruction to the outer optimization model to obtain the system economic characteristics; based on the system economic characteristics, it determines the energy storage capacity and power configuration based on the inner optimal instruction and the optimized outer optimization model, provided the outer optimization model meets the set conditions. Server 104 can feed back the obtained energy storage capacity and power configuration scheme to terminal 102. Furthermore, in some embodiments, the energy storage capacity and power configuration method can also be implemented independently by server 104 or terminal 102. For example, terminal 102 can directly configure the energy storage capacity and power based on system economic information and current distribution network data, or server 104 can obtain system economic information and current distribution network data from the data storage system and configure the energy storage capacity and power based on the system economic information and current distribution network data.

[0049] The terminal 102 can be, but is not limited to, various desktop computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, and smart in-vehicle devices. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted devices. The server 104 can be implemented using a standalone server or a server cluster composed of multiple servers, or it can be a cloud server.

[0050] In one exemplary embodiment, such as Figure 2 As shown, a method for configuring energy storage capacity and power is provided. This method is executed by a computer device, specifically by a terminal or server alone, or by both a terminal and a server. In this embodiment, the method is applied to... Figure 1 Taking server 104 as an example, the explanation includes the following steps 200 to 212. Wherein:

[0051] Step 200: Obtain system economic information. System economic information includes the unit investment cost of wind turbines, photovoltaic cells, reversible pump-turbines, energy storage batteries, reservoir capacity, operation and maintenance costs of wind turbines, photovoltaic cells, reversible pump-turbines, energy storage batteries, energy storage battery charging and discharging operation and maintenance costs, reservoir capacity, discount rate, and one or more of the following: project cycle.

[0052] Step 201: Based on the system's economic information, establish the investment cost model and operation and maintenance cost model of the system under the shared reservoir operation mode.

[0053] Step 202: Construct an outer optimization model based on the investment cost model and the operation and maintenance cost model.

[0054] Step 203: Construct outer-layer optimization constraints based on the shared reservoir operation mode of the pumped storage power station.

[0055] Step 204: Under the constraints of the outer layer optimization, the outer layer optimization model is optimized using the particle swarm optimization algorithm to obtain the optimal outer layer command for the energy storage capacity and power configuration of the distribution station area.

[0056] Step 205: Obtain historical data of the distribution network and establish a prediction model based on the historical data. Historical data of the distribution network includes historical power of photovoltaic power, historical power of wind power, and historical power of load.

[0057] Step 206: Obtain the current data of the distribution network and input it into the prediction model to obtain the distribution network prediction data. The current data includes photovoltaic power, wind power, and load power. The prediction data includes the predicted photovoltaic power, predicted wind power, and predicted load power.

[0058] Step 207: Under the common reservoir operation mode of the pumped storage power station, establish an inner-layer optimization model and inner-layer optimization constraints based on the distribution network prediction data.

[0059] Step 208: Under the inner layer optimization constraints, the inner layer optimization model is optimized using the whale intelligent optimization algorithm to obtain the inner layer optimal command for the energy storage capacity and power configuration of the distribution substation.

[0060] Step 209: Return the inner-layer optimal command for the energy storage capacity and power configuration of the distribution substation to the outer-layer optimization model to obtain the system's economic characteristics. These economic characteristics include investment costs and operation and maintenance costs.

[0061] Step 210: Determine whether the outer-layer optimization model meets the set conditions based on the system's economic characteristics.

[0062] Step 211: When the outer optimization model meets the set conditions, the inner optimal command and the optimized outer optimization model are used to complete the energy storage capacity and power configuration based on the energy storage capacity and power configuration of the distribution area at this time.

[0063] Step 212: When the outer optimization model does not meet the set conditions, adjust the particle velocity and particle position of the particle swarm intelligent optimization algorithm, and return to step 204.

[0064] Implementing steps 201 to 212 above can minimize the operating cost of pumped energy storage systems while improving their flexibility and reliability. Furthermore, this application utilizes swarm intelligence optimization algorithms (i.e., particle swarm intelligence optimization algorithm and whale intelligence optimization algorithm) to consider the control optimization process between different distribution stations from the perspective of the local power grid, and calculates the optimal collaborative control results and operating modes between different distribution stations. This effectively changes the energy supply relationship between multiple distribution stations, transforming it from a single energy mutual aid mode to a dual energy mutual aid mode of electricity and water, forming the optimal control of the overall system. While considering the optimal control of the inner layer, the application of swarm intelligence optimization algorithms to consider the capacity and power configuration of the outer system will have significant implications for the stability and economy of the local power grid operation.

[0065] In another exemplary embodiment of this application, regarding system economics, relevant information about new energy power plants and energy storage systems is obtained to form basic economic information (i.e., system economic information) of the distribution substation under the micro pumped storage power station co-reservoir operation mode. For example, taking a local power grid structure with two substations, a micro pumped storage power station co-reservoir, a new energy power plant, and load access to the grid as an example, the basic economic information of the substation includes the unit investment cost of the i-th substation's wind turbine, photovoltaic cells, reversible pump-turbine, energy storage battery, and reservoir capacity, denoted as _____. and The unit cost of operation and maintenance for the wind turbine, photovoltaic cells, reversible water pump turbine, energy storage battery, energy storage battery charging and discharging, and reservoir capacity in the i-th transformer area is denoted as follows: The discount rate r is set to 5%. The project duration is T. a .

[0066] In another exemplary embodiment of this application, the investment cost model and operation and maintenance cost model in step 201 constitute the economic cost model of the system under the shared reservoir operation mode. Taking a micro pumped storage shared reservoir power station, a new energy power station, and load access to the grid in a certain local power grid structure as an example, the initial investment cost of the i-th substation is:

[0067]

[0068] In the formula, Let represent the number of wind turbines in the i-th wind farm area. This refers to the number of photovoltaic cells in a photovoltaic power station. This refers to the total installed capacity of the water pumps and turbines. The number of energy storage batteries, This refers to the total storage capacity of the reservoir. Let be the total installed capacity of the pumps and turbines in the i-th distribution area. For the installed capacity of the water pump, This refers to the installed capacity of the water turbine. Let be the total reservoir capacity of the i-th substation, which consists of 50% of the shared reservoir capacity and the non-shared reservoir capacity. In the shared downstream reservoir model, In the upstream reservoir model, For the upstream reservoir capacity, This refers to the storage capacity of the downstream reservoir.

[0069] The maintenance cost of the i-th transformer area is

[0070]

[0071] In the formula, For wind power generation capacity, Photovoltaic power generation capacity, This refers to the total operating power of the water pump and turbine. This refers to the charging and discharging power of energy storage batteries.

[0072] In another exemplary embodiment of this application, taking a local power grid structure with two micro pumped storage power stations, a new energy power station, and load access to the grid as an example, to make the system more economical, the investment cost and operation and maintenance cost of the system are considered, and an objective function related to the system investment cost and operation and maintenance cost is established to obtain the outer optimization model. For example, the outer optimization model is expressed as:

[0073]

[0074] In another exemplary embodiment of this application, the outer optimization constraints constructed in this application include one or more of the following: constraints on the configured capacity of upstream reservoirs for each distribution area, constraints on the configured capacity of downstream reservoirs for each distribution area, constraints on the configured power of water pumps for each distribution area, constraints on the configured power of water turbines for each distribution area, and constraints on the energy storage capacity of a single energy storage battery for each distribution area. For example, the configured capacity of the upstream reservoir for the i-th distribution area... Configuration capacity of the downstream reservoir of the i-th distribution area Configuration power of the water pump in the i-th distribution area The configured power of the i-th transformer area turbine The energy storage capacity of a single energy storage battery in the i-th transformer area

[0075] In another exemplary embodiment of this application, in step 204, the particle swarm optimization algorithm is used to obtain the outer-layer optimal instruction for the energy storage capacity and power configuration of the distribution substation under the co-reservoir operation mode of the micro pumped storage power station, considering system investment costs and operation and maintenance costs, and the configuration instruction is transmitted to the inner-layer computing system operation strategy, including:

[0076] Step 1: Determine the optimization variables for the outer optimization model. The optimization variables include the number of wind turbines in the i-th wind farm area. Number of photovoltaic cells in a photovoltaic power station Number of energy storage battery packs The installed power of energy storage batteries for charging and discharging Water pump installed capacity Installed capacity of water turbines Upstream reservoir capacity Downstream reservoir capacity and the total storage capacity of upstream and downstream reservoirs

[0077] Step 2: Form a B1-dimensional variable space based on the optimization variables, and place N1 particles in the variable control. The position of each particle represents the installed capacity of the pump, the installed capacity of the turbine, the upstream reservoir capacity, and the downstream reservoir capacity. For example, if there is 1 pump, 1 turbine, 1 upstream reservoir, and 1 downstream reservoir, then there are 4 optimization variables, denoted as x1, x2, x3, x4. The position of a particle is a variable composed of these 4 variables, denoted as [x1, x2, x3, x4].

[0078] Step 3: Set the maximum number of iterations to S, and initialize the iteration count s = 0, as well as the initial positions and velocities of each particle in the particle swarm. Iteratively solve the outer-layer optimization model until the maximum number of iterations is reached. Obtain the position information of each particle, and use this position information as the outer-layer optimal command for configuring the energy storage capacity and power of the distribution station area. Position information includes particle position and velocity. For example, after the s-th iteration, the position of the j-th particle is... speed is Outputting the current position and passing it to the inner layer can then serve as a constraint condition for that inner layer.

[0079] In another exemplary embodiment of this application, based on the position information of each particle in the outer layer of the system and information such as the power network structure, new energy power plants, energy storage systems, and loads within the region, the pumped storage power station's shared reservoir operation mode is set to include both a shared upstream reservoir operation mode and a shared downstream reservoir operation mode. The information such as the power network structure, new energy power plants, energy storage systems, and loads within the region includes, but is not limited to, the maximum change value δ of the injected power that the power grid can withstand, and the configured power of the pumps and turbines in the i-th distribution area. The pumping and storage efficiency and the turbine power generation efficiency of the i-th transformer area The configuration of upstream and downstream reservoirs in the i-th distribution area. The head h between the upstream and downstream reservoirs of the i-th distribution area (i) The configuration charging and discharging power of the energy storage battery in the i-th distribution area The charging efficiency of the energy storage battery in the i-th transformer area and discharge efficiency The maximum capacity of a single energy storage battery in the i-th transformer area is: The number of energy storage battery packs is Selected time interval Δt, DOD (i) This represents the depth of discharge of the energy storage battery in the i-th substation.

[0080] Unlike traditional pumped-storage power stations, pumped-storage power stations operate under a shared reservoir mode, where one upstream reservoir can correspond to multiple downstream reservoirs, or vice versa. Simultaneously, in conjunction with energy storage batteries, they enable energy conversion and integrated energy scheduling across multiple power distribution areas. Specifically:

[0081] (1) A shared downstream reservoir operation mode for pumped storage power stations is established, where the upstream reservoirs of each distribution area share the same downstream reservoir. This shared downstream reservoir enables coordinated control of water volume across different distribution areas. The established shared downstream reservoir operation mode for pumped storage power stations is as follows: Figure 3 As shown.

[0082] For example, to ensure the continuity of the system's daytime scheduling, a final time T is set for each day. N The water volume of the upper and lower reservoirs is a constant. This represents the final water storage of the upstream reservoir at the end of a typical day in the i-th substation under the shared reservoir model. V L,end V represents the final water storage of the downstream reservoir at the end of a typical day under the shared downstream reservoir model. L (T N ) = V L,end .

[0083] For example, in the downstream reservoir operation mode, the water volume V of the downstream reservoir at time (k+1) is... L(k+1) and the reservoir water volume V at time k L The relevant expression for (k) is:

[0084]

[0085] The water volume of the upstream reservoir of the i-th distribution area at time (k+1) Water volume at time k The relevant expression is:

[0086]

[0087] Where ρ is the density of water, g is the local gravitational acceleration, and h (i) Let i be the water head of the i-th transformer area. Let be the pump energy storage efficiency of the i-th transformer area. Let be the turbine power generation efficiency of the i-th transformer zone, and Δt be a given time interval. Let be the operating power of the water pump in the i-th distribution area. Let be the operating power of the turbine in the i-th substation. The total operating power of the pumps and turbines is: In the downstream reservoir operation mode, the total reservoir capacity of the i-th substation is

[0088] (2) A shared upstream reservoir operation mode for pumped storage power stations is established, where downstream reservoirs in each distribution area share the same upstream reservoir. This shared downstream reservoir enables coordinated control of water volume across different distribution areas. The established shared upstream reservoir operation mode for pumped storage power stations is as follows: Figure 4 As shown.

[0089] For example, to ensure the continuity of the system's daytime scheduling, a final time T is set for each day. N The water volume in the upper and lower reservoirs is a constant. V H,end V represents the final water storage of the upstream reservoir at the end of a typical day under the upstream reservoir model. H (T N ) = V H,end . This represents the final water storage of the downstream reservoir at the end of a typical day in the i-th area under the upstream reservoir model. In the upstream reservoir operation mode, the water volume V of the upstream reservoir at time (k+1) is... H (k+1) and the upstream reservoir water volume V at time k H The relevant expression for (k) is:

[0090]

[0091] The expression relating the water volume of the downstream reservoir of the i-th distribution area at time (k+1) to the water volume of the reservoir at time k is:

[0092]

[0093] In the upstream reservoir operation mode, the total reservoir capacity of the i-th distribution area is represented as:

[0094] In another exemplary embodiment of this application, in steps 205 and 206, a prediction model such as an Extreme Learning Machine, Support Vector Machine, or Autoregressive Model can be established based on historical power data of the distribution network, such as the historical power of photovoltaic, wind power, and load. By inputting the historical power of photovoltaic, wind power, and load, a day-ahead prediction is performed to obtain the predicted power of photovoltaic, wind power, and load for the second day. On a given day, the maximum power generation of the i-th distribution area's wind power plant and photovoltaic power plant at time k within a day is represented as... The line load power of the i-th transformer area at time k on a day is expressed as:

[0095] In another exemplary embodiment of this application, the inner-layer optimization constraints include, but are not limited to, one or more of the following: constraints on the power of wind power plants and photovoltaic power plants, constraints on the power of pumped storage units, constraints on the charging and discharging power of energy storage batteries, constraints on system power balance, constraints on reservoir storage capacity, constraints on energy storage battery capacity, and constraints on the change in power injected into the transmission network. Based on this, the process of establishing the inner-layer optimization model and inner-layer optimization constraints based on distribution network prediction data in step 207, under the pumped storage power station's shared reservoir operation mode, can be described as follows:

[0096] Step 1: The output power of the wind power plants in each distribution area at any time during a typical day is less than the maximum power output at that time; the output power of the photovoltaic power plants in each distribution area at any time during a typical day is less than the maximum power output at that time.

[0097] For example, the output power of the wind power plant in the i-th distribution area at time k during a typical day. Less than the maximum power generation at this moment Right now The output power of the photovoltaic power plant in the i-th transformer area at time k on a typical day Less than the maximum power generation at this moment Right now Select the wind power generation capacity at time k of a typical day in the i-th transformer area. Photovoltaic power generation For inner layer optimization variables.

[0098] Step 2: Based on the data of each particle in the outer layer, obtain the configuration information corresponding to each particle in each distribution area. This configuration information includes, but is not limited to, the installed capacity of the water pumps and the installed capacity of the water turbines for each particle in each distribution area, the energy storage power of the water pumps in each distribution area at any time during a typical day being less than their installed capacity, and the power generation power of the water turbines in each distribution area at any time during a typical day being less than their installed capacity. Select the pumping energy storage power of the water pumps and the power generation power of the water turbines in each distribution area at a certain time during a typical day as the inner layer variables for optimization.

[0099] For example, based on the data of the outer N1 particles, the configuration information corresponding to each particle in the i-th station area is obtained, where the installed capacity of the water pump corresponding to the j-th particle in the i-th station area is... The installed capacity of the water turbine is The energy storage capacity of the water pump in the i-th transformer area is less than its installed capacity at time k during a typical day. Right now The power generation capacity of the water turbine in the i-th transformer area at time k during a typical day. Less than its installed capacity Right now Select the pumping and storage power of the water pump at time k within a typical day in the i-th transformer area. and the power generation capacity of the water turbine For inner layer optimization variables.

[0100] Step 3: Based on the data of each particle in each outer layer, obtain the configured storage capacity of the upstream reservoir and the configured storage capacity of the downstream reservoir. The water storage of the upstream reservoir in each layer at a certain moment on a typical day is less than its configured capacity. The water storage (i.e., capacity) of the downstream reservoir in each layer at a certain moment on a typical day is less than its configured capacity.

[0101] For example, the upstream reservoir's configured storage capacity can be obtained based on the data of the j-th particle in the i-th outermost zone. Downstream reservoir configuration storage capacity The water storage capacity of the upstream reservoir of the i-th distribution area at time k within a typical day. Less than its configured capacity Right now The water storage capacity of the downstream reservoir of the i-th distribution area at time k on a typical day. Less than its configured capacity Right now

[0102] Step 4: Based on the data of each particle in each outer layer, obtain the number of energy storage battery groups and establish constraints on the energy range of each energy storage battery in a typical day at a certain time.

[0103] For example, based on the data of the j-th particle in the i-th outermost region, the number of energy storage battery groups is obtained as follows: The energy range of the i-th energy storage battery at time k during a typical day for Among them, the maximum capacity of a single energy storage battery in the i-th transformer area is DOD (i) This represents the depth of discharge of the energy storage battery in the i-th distribution area. This represents the configured energy of the energy storage battery corresponding to the j-th particle in the i-th station area.

[0104] Step 5: Based on the data of each particle in each outer layer, obtain the configuration charging and discharging power of the energy storage battery in each layer, and establish the constraint range of the charging and discharging power of the energy storage battery pack in each layer at time k within a typical day.

[0105] For example, based on the data of the j-th particle in the i-th outermost region, the configured charge / discharge power of the energy storage battery in the i-th region is obtained as follows: The charging and discharging power of the i-th energy storage battery pack within a typical day at time k is subject to the following constraints:

[0106] Step 6: Establish the power balance equation for the i-th transformer area. The sum of the photovoltaic power generation, wind power generation, transmission line transmission power, pumped storage power, energy storage battery power, and power consumed by the line load in each transformer area at a certain moment on a typical day is zero.

[0107] For example, to establish the power balance equation for the i-th transformer area, the sum of the photovoltaic power generation, wind power generation, transmission line power, total pumped storage power, total energy storage battery power, and power consumed by the line load in the i-th transformer area at time k within a typical day is zero.

[0108]

[0109] The total power generation capacity of the reservoir's energy storage in the i-th distribution area at time k on a typical day is:

[0110] Or 1, Or 1 and It is an integer. This indicates the activation status of the pumped storage unit at time k within a typical day in the i-th area. When the pumped storage unit stops operating, At that time, the pumped storage unit started operation. This indicates the activation status of the turbine generator unit at time k within a typical day in the i-th area. At that time, the turbine generator unit stopped operating. At time k, the turbine generator unit starts operation. The total charging and discharging power of the energy storage battery at time k in the i-th distribution area during a typical day is...

[0111]

[0112] Or 1, Or 1 and It is an integer. This represents the charging status of the energy storage battery at time k within a typical day in the i-th distribution area. When the energy storage battery stops charging, At that time, the energy storage battery begins to charge. This represents the discharge status of the energy storage battery at time k within a typical day in the i-th distribution area. At that time, the energy storage battery stops discharging. At that time, the energy storage battery begins to discharge.

[0113] Step 7: To reduce the impact of each transformer substation on the transmission network during energy transmission, establish constraints on the change in injected power into the transmission network of each substation at a certain time. For example, control the change in injected power into the transmission networks of two substations at time k. satisfy

[0114] In another exemplary embodiment of this application, in order to ensure that the system meets the requirements of minimizing the curtailment of wind and solar power generation, minimizing the occupation of transmission lines, and minimizing the load shedding, the process of establishing an inner-layer optimization model based on distribution network forecast data in step 207 can be described as follows:

[0115] Step 1: Under the shared reservoir operation mode of the pumped storage power station, establish functions for curtailed wind and photovoltaic power generation, transmission line occupancy, and load shedding based on distribution network forecast data. Wherein:

[0116] (1) To ensure the system meets the requirements of minimizing wind and solar power curtailment, minimizing transmission line occupancy, and minimizing load shedding, the curtailment of solar and wind power generation in two transformer substations during a typical day is considered. A function related to the curtailment of solar and wind power generation is established, namely, the wind and solar power curtailment function, expressed as:

[0117]

[0118] (2) To reduce the occupancy of the transmission line between the two transformer stations, ensure the stability of the transmission line, and maximize the advantage of energy transmission between the two transformer stations in the shared reservoir operation mode of the pumped storage power station, a function for the local grid injection power is established. Considering the line injection power of the two transformer stations during a typical day, a function related to the line injection power, i.e., the transmission line occupancy function, is set as follows:

[0119]

[0120] (3) To maximize power supply to the line load and reduce load shedding, a correlation function with the system load shedding is established, namely the load shedding function, expressed as:

[0121]

[0122] Step 2: Integrate the functions for abandoned wind and solar power generation, transmission line occupancy, and load shedding, and assign weights to each function to obtain the inner-layer optimization model. Set the inner-layer optimization model as the system's objective function, expressed as:

[0123]

[0124] In the formula, ε is the weight of the function considering the minimum abandonment of wind and photovoltaic power generation, σ is the weight of the function considering the reduction of the occupancy of the transmission line between the two stations, (1-ε-σ) is the weight of the function considering the load shedding, and J represents the objective function.

[0125] In another exemplary embodiment of this application, in step 208, the whale intelligent optimization algorithm is used to obtain the real-time optimal control commands for wind, solar, energy storage batteries, and pumped storage in the distribution area of ​​the inner micro pumped storage power station under the co-reservoir operation mode under the conditions corresponding to each outer particle. This aims to minimize the curtailment of wind and solar power generation, minimize the occupation of transmission lines, and minimize the load shedding. The specific implementation process of this process is as follows: Figure 5 As shown, it includes:

[0126] Step 1: The optimization variables of the model include the photovoltaic power generation at time k during a typical day in the i-th transformer area. Wind power generation capacity Water pump pumping power storage Hydropower generation capacity Water pump operating status variables Water turbine operating state variables Total power of pumped storage Upstream reservoir storage Downstream reservoir storage Energy storage battery charging power Energy storage battery discharge power Energy storage battery charging state variables Energy storage battery discharge state variables Total power of energy storage batteries Energy storage battery capacity Power injected into the grid Changes in grid-injected power Total power supplied by the system to the load in, When the water pump stops running, At that time, the water pump starts running. At that time, the turbine generator unit stopped operating. At that time, the turbine generator set started operation. Due to... Non-continuous variables, when Time to take when Pick Similarly, When to take when Pick When the energy storage battery stops charging, The energy storage battery begins charging. When the energy storage battery stops discharging, The energy storage battery begins to discharge. Due to... Non-continuous variables, when Time to take when Pick Similarly, When to take when Pick Δt represents a typical intraday time interval. N² whales are placed in a B² space comprised of the above variables.

[0127] Step 2: Set the number of whales N2 and the maximum number of inner iterations V of the algorithm, and initialize the position information X(s) of each whale. Where v represents the number of inner optimization iterations.

[0128] Step 3: Calculate the fitness of each whale and find the current optimal whale position X. * (s) and retain them. And calculate the coefficient vectors A and C.

[0129] A = 2a·r1-a (15)

[0130] C = 2r² (16)

[0131] In the formula, r1 and r2 are random vectors in [0,1]. p represents the probability of the predation mechanism, a random number in the range [0,1]. a decreases linearly from 2 to 0 throughout the iteration. The probability p is checked to see if it is less than 50% (i.e., 0.5). If so, proceed to step 4 below; otherwise, the bubble net predation mechanism is used. The bubble net predation mechanism uses the following formula for position updating:

[0132] X(v+1)=D'·e bl ·cos(2πl)+X * (v) (17)

[0133] D'=|X * (v)-X(v)| (18)

[0134] In the formula, D' represents the distance between the current search individual and the current optimal solution. b represents the spiral shape parameter. l represents a random number uniformly distributed in the range [-1, 1]. X * X(v) represents the position of the current optimal solution, and X(v) represents the position of the current searched individual.

[0135] Step 4: Determine if the absolute value of the coefficient vector A is less than 1. If so, surround the prey and update the position according to the following formula.

[0136] X(v+1)=X * (v)-A·D (19)

[0137] D = |C·X * (v)-X(v)| (20)

[0138] Otherwise, a global random search for prey is performed, and the position is updated according to the following formula:

[0139] X(v+1)=X rand (v)-A·D” (21)

[0140] D”=|C·X rand (v)-X(v)| (22)

[0141] In the formula, D” represents the distance between the current searched individual and the random individual. X rand (v) represents the current position of the random individual.

[0142] Step 5: After the position update is complete, calculate the fitness of each whale and compare it with the previously retained best whale position. If the position is better, replace it with the new best solution.

[0143] Step 6: Determine whether the current iteration number v has reached the maximum iteration number V. If so, the optimal solution is obtained and the calculation ends. Otherwise, proceed to the next iteration and return to step 3.

[0144] In another exemplary embodiment of this application, step 209 involves returning the optimal solution of the inner layer corresponding to each outer layer particle to the outer layer to continue calculating the economic characteristics of the system.

[0145] For example, based on the information of the optimal solution of the inner layer corresponding to each outer particle, the value of the objective function M at the position of each particle at this moment is calculated. The information of the optimal solution of the inner layer corresponding to each outer particle includes the power generation of the wind power station at time k of a typical day in the i-th area. Photovoltaic power station power generation capacity Water pump pumping power storage Hydropower generation capacity Upstream reservoir storage Downstream reservoir storage Energy storage battery charging power Energy storage battery discharge power

[0146] Among them, the total operating power of the water pumps and turbines at time k in a typical day of the i-th area is: In the downstream reservoir operation mode, the total reservoir capacity at time k of a typical day in the i-th distribution area is: In the upstream reservoir operation mode, the total reservoir capacity at time k of a typical day in the i-th distribution area is:

[0147] Update the optimal position found by the particle at this point. The optimal solution for the j-th particle after s iterations is: The objective function value corresponding to this optimal solution is denoted as . This refers to the objective function value corresponding to the individual optimal solution of the j-th particle after s iterations. The optimal position searched for by the entire particle swarm is updated, and the optimal solution searched by the particle swarm after s iterations is: The objective function value corresponding to this optimal solution is denoted as . That is, the objective function value corresponding to the s-th iteration optimal solution of the particle swarm.

[0148] In another exemplary embodiment of this application, the implementation process of steps 210 to 212 can be described as follows:

[0149] Step 1: Determine if the iteration count s is less than the maximum iteration count S of the particle swarm optimization algorithm. If yes, then s = s + 1 and proceed to the next step. If no, output the value of the objective function M corresponding to the current swarm optimum and the swarm optimum itself, completing the scheduling.

[0150] Step 2: Update the position and velocity of the particles according to the particle swarm optimization algorithm, obtain the new positions, and continue iterative optimization. Update the velocities of N particles according to the velocity update formula.

[0151]

[0152] In the formula, The inertial component, consisting of inertial weights and the particle's own velocity, represents the particle's confidence in its previous state of motion. The cognitive part represents the particle's own thinking, that is, the particle's own experience, which can be understood as the distance and direction between the particle's current position and its own historical best position. The social component represents information sharing and cooperation among particles, derived from the experience of other excellent particles in the group. It can be understood as the distance and direction between a particle's current position and the group's historical best position. ω represents the inertia weight. c1 represents the individual learning factor. c2 represents the group learning factor. r1 and r2 represent random numbers within the interval [0,1], increasing the randomness of the search. Let represent the b-th dimension velocity vector of particle j after the s-th iteration. Let represent the position vector of particle j in the b-th dimension after the s-th iteration. This represents the historical optimal position of particle j in the b-th dimension after the s-th iteration, which is the optimal solution obtained by the j-th particle after the s-th iteration. This represents the historical optimal position of the swarm in dimension b after the s-th iteration, which is the optimal solution in the entire particle swarm after the s-th iteration.

[0153] The positions of N particles are updated according to the position update formula, expressed as:

[0154]

[0155] In the formula, This represents the position of the b-dimensional vector of the j-th particle after the (s+1)-th iteration. This represents the position of the b-dimensional vector of the j-th particle after the s-th iteration. Let represent the velocity of the b-dimensional vector of the j-th particle after the s-th iteration. Return the updated positions of the N1 particles to step 204, output the current positions, and pass them to the inner layer as constraints.

[0156] In summary, the implementation process of the energy storage capacity and power configuration method provided in this application can be as follows: Figure 6As shown. Compared to traditional research on energy storage capacity and power configuration methods for pumped storage systems, this application focuses on the configuration method of energy storage capacity and power for distribution substations under the shared reservoir operation mode of micro pumped storage power stations. Energy transfer between different substations is achieved through a shared reservoir, which can be divided into two types: sharing an upstream reservoir and sharing a downstream reservoir. The key feature of this application is that, based on the different energy states, energy storage capacities, transmission line capacity, power supply conditions, and load conditions of the new energy and pumped storage systems in each substation, a multi-mode energy dispatch model and optimized control structure are formed between the new energy and pumped storage systems. The system capacity and power configuration are optimized according to the control structure of the system under this operation mode. A swarm intelligence optimization algorithm is used to consider the control optimization process between different substations from the perspective of the local power grid, and the optimal collaborative control results and operation modes between different substations are calculated, effectively changing the energy supply relationship between multiple substations. The shift from a single energy sharing mode to a dual energy sharing mode involving electricity and water enables optimal control of the overall system. By considering optimal control at the inner layer and utilizing swarm intelligence optimization algorithms to address the capacity and power configuration issues of the outer system, this approach will significantly improve the stability and economy of the local power grid operation.

[0157] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal, and its internal structure diagram may be as follows. Figure 7 As shown, the computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores energy storage capacity and power configuration data. The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements an energy storage capacity and power configuration method.

[0158] Those skilled in the art will understand that Figure 7The structures shown are merely block diagrams of some structures related to the present application and do not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than shown in the figures, or combine certain components, or have different component arrangements. In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0159] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0160] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0161] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0162] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0163] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0164] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0165] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for configuring energy storage capacity and power, characterized in that, The energy storage capacity and power configuration method includes: Obtain system economic information; the system economic information includes one or more of the following: investment cost per unit of wind turbine units in each distribution area, investment cost per unit of photovoltaic cells, investment cost per unit of reversible pump-turbine units, investment cost per unit of energy storage batteries, investment cost per unit of reservoir capacity, operation and maintenance cost per unit of wind turbine units in each distribution area, operation and maintenance cost per unit of photovoltaic cells, operation and maintenance cost per unit of reversible pump-turbine units, operation and maintenance cost per unit of energy storage batteries, operation and maintenance cost per unit of energy storage battery charging and discharging, operation and maintenance cost per unit of reservoir capacity, discount rate, and project cycle; Based on the system's economic information, establish an investment cost model and an operation and maintenance cost model for the system under the shared reservoir operation mode; An outer optimization model is constructed based on the aforementioned investment cost model and operation and maintenance cost model; Based on the shared reservoir operation mode of pumped storage power stations, outer-layer optimization constraints are constructed. Under the aforementioned outer optimization constraints, the outer optimization model is optimized using a particle swarm optimization algorithm to obtain the outer optimal command for the energy storage capacity and power configuration of the distribution station area. Historical data of the power distribution network is acquired, and a prediction model is established based on the historical data of the power distribution network; the historical data of the power distribution network includes historical power of photovoltaic power, historical power of wind power, and historical power of load. The current data of the distribution network is acquired and input into the prediction model to obtain the distribution network prediction data; the current data of the distribution network includes photovoltaic power, wind power, and load power; the distribution network prediction data includes photovoltaic predicted power, wind power predicted power, and load predicted power. In the pumped storage power station's shared reservoir operation mode, an inner-layer optimization model and inner-layer optimization constraints are established based on the aforementioned power distribution network prediction data. Under the aforementioned inner-layer optimization constraints, the inner-layer optimization model is optimized using the whale intelligent optimization algorithm to obtain the inner-layer optimal command for the energy storage capacity and power configuration of the distribution substation. The inner-layer optimal command for the energy storage capacity and power configuration of the distribution substation area is returned to the outer-layer optimization model to obtain the system's economic characteristics; the economic characteristics include: investment cost and operation and maintenance cost. Based on the economic characteristics of the system, determine whether the outer optimization model meets the set conditions; When the outer optimization model meets the set conditions, the inner optimal command based on the energy storage capacity and power configuration of the distribution substation at this time and the optimized outer optimization model are used to complete the energy storage capacity and power configuration. When the outer optimization model does not meet the set conditions, the particle velocity and particle position of the particle swarm intelligent optimization algorithm are adjusted, and the process returns to "under the outer optimization constraints, the outer optimization model is optimized using the particle swarm intelligent optimization algorithm to obtain the outer optimal command for the distribution station's energy storage capacity and power configuration." 2. The energy storage capacity and power configuration method according to claim 1, characterized in that, The outer optimization constraints include one or more of the following: constraints on the upstream reservoir capacity of each distribution area, constraints on the downstream reservoir capacity of each distribution area, constraints on the pump power of each distribution area, constraints on the turbine power of each distribution area, and constraints on the energy storage capacity of a single energy storage battery in each distribution area.

3. The energy storage capacity and power configuration method according to claim 1, characterized in that, Under the aforementioned outer-layer optimization constraints, the outer-layer optimization model is optimized using a particle swarm optimization algorithm to obtain the optimal outer-layer command for the distribution substation's energy storage capacity and power configuration, specifically including: The optimization variables of the outer optimization model are determined; the optimization variables include the installed capacity of the pumps in each substation, the installed capacity of the turbines, the upstream reservoir capacity, and the downstream reservoir capacity. A variable space is formed based on the optimized variables, and particles are placed in the variable control. Set the maximum number of iterations, initialize the number of iterations and the initial position and initial velocity of each particle in the particle swarm, and iteratively solve the outer optimization model until the maximum number of iterations is reached. Obtain the position information of each particle, and use the position information of each particle as the outer optimal command for the energy storage capacity and power configuration of the distribution station area; the position information includes particle position and velocity.

4. The energy storage capacity and power configuration method according to claim 1, characterized in that, The pumped storage power station's shared reservoir operation modes include: a shared upstream reservoir operation mode and a shared downstream reservoir operation mode; In the shared upstream reservoir operation mode, the downstream reservoirs of each substation share the same upstream reservoir; In the shared downstream reservoir operation mode, the upstream reservoirs of each substation share the same downstream reservoir.

5. The energy storage capacity and power configuration method according to claim 1, characterized in that, The prediction model is an extreme learning machine, a support vector machine, or an autoregressive model.

6. The energy storage capacity and power configuration method according to claim 1, characterized in that, The inner-layer optimization constraints include one or more of the following: power constraints of wind power plants and photovoltaic power plants, power constraints of pumped storage units, power constraints of energy storage batteries, system power balance constraints, water storage constraints of reservoirs, energy storage battery capacity constraints, and power variation constraints of the transmission network.

7. The energy storage capacity and power configuration method according to claim 1, characterized in that, In the shared reservoir operation mode of the pumped storage power station, an inner-layer optimization model is established based on the predicted data of the distribution network, including: In the pumped storage power station's shared reservoir operation mode, based on the aforementioned power distribution network prediction data, functions for abandoned wind and photovoltaic power generation, transmission line occupancy, and load shedding are established. The inner optimization model is obtained by integrating the abandoned wind and photovoltaic power generation functions, the transmission line occupancy function, and the load shedding function, and assigning weights to each function.

8. A computer device, comprising: The memory and processor contain a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the energy storage capacity and power configuration method according to any one of claims 1-7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the energy storage capacity and power configuration method as described in any one of claims 1-7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the energy storage capacity and power configuration method as described in any one of claims 1-7.

Images