Method, device and electronic equipment for determining frequency modulation capacity of wind-storage combined system

Abstract

The present application discloses a method, device and electronic device for determining the frequency regulation capacity of a wind-storage combined system. The method includes: obtaining the curtailed wind power of a wind farm, and constructing an energy storage configuration optimization model of the wind-storage combined system according to the curtailed wind power; solving the energy storage configuration optimization model to obtain the target energy storage capacity and target energy storage power of the wind-storage combined system; obtaining the probabilistic interval prediction result of the wind power according to the wind power prediction model; obtaining the operation strategy of the energy storage system, and determining the frequency regulation capacity of the wind-storage combined system based on the operation strategy, the target energy storage capacity, the target energy storage power and the probabilistic interval prediction result. Thus, the present application can give full play to the complementary characteristics of the wind power system and the energy storage system, fully consider various information of the wind power system and the energy storage system, improve the accuracy of determining the frequency regulation capacity of the wind-storage combined system, improve the frequency regulation capacity and performance of the wind-storage combined system, and improve the benefits of the wind-storage combined system.

Description

Technical Field

[0001] The present application relates to the field of new energy technologies, and particularly to a method, device, and electronic equipment for determining the frequency modulation capacity of a wind-storage combined system. Background Art

[0002] The frequency modulation capacity of a wind power system has a certain degree of uncertainty. If the wind power system is not combined with a storage wind power system, the wind power system needs to lower its declared frequency modulation capacity to meet the requirement that the reserved frequency modulation capacity is greater than the declared frequency modulation capacity. The frequency modulation effect is also affected by its random frequency modulation error. If the wind power system is combined with a storage system, the storage system can compensate for the random error of the wind power system. The greater the frequency modulation capacity of the storage system, the more obvious the compensation effect. Then, the declared frequency modulation capacity of the wind power system can be increased, and the frequency modulation effect can be improved. When determining the frequency modulation capacity of a wind-storage combined system, the cost of the storage system is an important factor affecting the profit of the wind-storage combined system. Therefore, how to improve the accuracy of determining the frequency modulation capacity of a wind-storage combined system and increase the profit of the wind-storage combined system has become an urgent problem to be solved. Summary of the Invention

[0003] The present application aims to solve at least one of the technical problems in the related art to some extent.

[0004] To this end, the first object of the present application is to propose a method for determining the frequency modulation capacity of a wind-storage combined system, which is used to solve the technical problem in the prior art that the frequency modulation capacity of a wind-storage combined system cannot be accurately determined, resulting in a low profit of the wind-storage combined system.

[0005] To achieve the above object, the first aspect embodiment of the present application provides a method for determining the frequency modulation capacity of a wind-storage combined system. The method includes: obtaining the curtailed wind power of a wind farm, and constructing an energy storage configuration optimization model of the wind-storage combined system according to the curtailed wind power; solving the energy storage configuration optimization model to obtain the target energy storage capacity and target energy storage power of the wind-storage combined system; obtaining the probabilistic interval prediction result of the wind power according to a wind power prediction model; obtaining the operation strategy of the energy storage system, and determining the frequency modulation capacity of the wind-storage combined system based on the operation strategy, the target energy storage capacity, the target energy storage power, and the probabilistic interval prediction result.

[0006] In addition, according to the method for determining the frequency modulation capacity of a wind-storage combined system in the above embodiment of the present application, the following additional technical features may also be provided:

[0007] According to an embodiment of the present application, the obtaining of the curtailed wind power of the wind farm further includes: obtaining the theoretical power generation and actual power generation of the wind farm; and obtaining the curtailed wind power according to the theoretical power generation and the actual power generation.

[0008] According to an embodiment of the present application, solving the energy storage configuration optimization model to obtain the target energy storage capacity and target energy storage power of the wind-storage combined system further includes: obtaining the costs and benefits of the wind-storage combined system participating in the frequency regulation market; obtaining the constraint conditions of the wind-storage combined system; constructing an objective function of the energy storage configuration optimization model according to the constraint conditions, the costs, and the benefits; and solving the objective function according to the ant lion optimization algorithm to obtain the target energy storage capacity and the target energy storage power.

[0009] According to an embodiment of the present application, obtaining the costs of the wind-storage combined system participating in the frequency regulation market further includes: obtaining the equal annual value annual interest rate of the energy storage system; obtaining the configured power of the energy storage system, the unit investment of the configured power, the configured capacity of the energy storage system, and the unit investment of the configured capacity; and obtaining the costs of the wind-storage combined system participating in the frequency regulation market according to the equal annual value annual interest rate, the configured power, the unit investment of the configured power, the configured capacity, and the unit investment of the configured capacity.

[0010] According to an embodiment of the present application, obtaining the benefits of the wind-storage combined system participating in the frequency regulation market further includes: obtaining the frequency regulation performance index, the mileage benefit factor, the performance clearing price of the frequency regulation market, the frequency regulation capacity price of the frequency regulation market, and the abandoned wind absorption capacity; and obtaining the benefits of the wind-storage combined system participating in the frequency regulation market according to the frequency regulation performance index, the mileage benefit factor, the performance clearing price, the frequency regulation capacity price, and the abandoned wind absorption capacity.

[0011] According to an embodiment of the present application, the training process of the wind power prediction model includes: obtaining sample data, where the sample data includes the historical data and prediction data of the wind farm; inputting the sample data into the wind power prediction model to be trained to obtain the wind power prediction value corresponding to the sample data; obtaining the true wind power value corresponding to the sample data; obtaining the difference between the wind power prediction value and the true wind power value, and adjusting the model parameters of the wind power prediction model to be trained according to the difference by using the whale optimization algorithm WOA until the difference meets the training end condition, and determining the wind power prediction model to be trained after the last adjustment of the model parameters as the trained wind power prediction model.

[0012] According to an embodiment of the present application, obtaining the probabilistic interval prediction result of wind power according to the wind power prediction model further includes: obtaining the prediction error value of the wind power according to the wind power prediction value and the actual wind power value; establishing the cumulative distribution function of the prediction error value according to the Cornish-Fisher series; obtaining the probabilistic prediction interval curve of the wind power at different confidence levels according to the cumulative distribution function; and obtaining the probabilistic interval prediction result according to the probabilistic prediction interval curve.

[0013] According to an embodiment of the present application, obtaining the operation strategy of the energy storage system includes: obtaining the charge and discharge state of the energy storage system; and determining the energy storage operation strategy according to the charge and discharge state.

[0014] According to an embodiment of the present application, determining the frequency regulation capacity of the wind-storage combined system based on the operation strategy, the target energy storage capacity, the target energy storage power, and the probabilistic interval prediction result further includes: obtaining the wind power limit value, and determining the adjustable frequency regulation capacity of the wind-storage combined system according to the wind power limit value; and determining the frequency regulation capacity of the wind-storage combined system according to the adjustable frequency regulation capacity, the energy storage operation strategy, the target energy storage capacity, the target energy storage power, and the probabilistic interval prediction result.

[0015] To achieve the above object, an embodiment of the second aspect of the present application provides a device for determining the frequency regulation capacity of a wind-storage combined system. The device includes: a first acquisition module, configured to obtain the wind curtailment electricity of a wind farm and construct an energy storage configuration optimization model of the wind-storage combined system according to the wind curtailment electricity; a second acquisition module, configured to solve the energy storage configuration optimization model to obtain the target energy storage capacity and the target energy storage power of the wind-storage combined system; a third acquisition module, configured to obtain the probabilistic interval prediction result of the wind power according to the wind power prediction model; and a determination module, configured to obtain the operation strategy of the energy storage system and determine the frequency regulation capacity of the wind-storage combined system based on the operation strategy, the target energy storage capacity, the target energy storage power, and the probabilistic interval prediction result.

[0016] In addition, a device for determining the frequency regulation capacity of a wind-storage combined system according to the above embodiment of the present application may further have the following additional technical features:

[0017] According to an embodiment of the present application, the first acquisition module is further configured to: obtain the theoretical power generation and the actual power generation of the wind farm; and obtain the wind curtailment electricity according to the theoretical power generation and the actual power generation.

[0018] According to an embodiment of the present application, the second acquisition module is further configured to: acquire the costs and benefits of the wind-storage integrated system participating in the frequency regulation market; acquire the constraint conditions of the wind-storage integrated system; construct an objective function of the energy storage configuration optimization model according to the constraint conditions, the costs, and the benefits; and solve the objective function according to the ant lion optimization algorithm to obtain the target energy storage capacity and the target energy storage power.

[0019] According to an embodiment of the present application, the second acquisition module is further configured to: acquire the equal annual value annual interest rate of the energy storage system; acquire the configured power of the energy storage system, the unit investment of the configured power, the configured capacity of the energy storage system, and the unit investment of the configured capacity; and obtain the costs of the wind-storage integrated system participating in the frequency regulation market according to the equal annual value annual interest rate, the configured power, the unit investment of the configured power, the configured capacity, and the unit investment of the configured capacity.

[0020] According to an embodiment of the present application, the second acquisition module is further configured to: acquire the frequency regulation performance index, the mileage benefit factor, the performance clearing price of the frequency regulation market, the frequency regulation capacity price of the frequency regulation market, and the curtailment absorption capacity; and obtain the benefits of the wind-storage integrated system participating in the frequency regulation market according to the frequency regulation performance index, the mileage benefit factor, the performance clearing price, the frequency regulation capacity price, and the curtailment absorption capacity.

[0021] According to an embodiment of the present application, the device is further configured to: acquire sample data, where the sample data includes historical data and prediction data of the wind farm; input the sample data into a wind power prediction model to be trained to obtain a wind power prediction value corresponding to the sample data; acquire the true wind power value corresponding to the sample data; acquire the difference between the wind power prediction value and the true wind power value, and adjust the model parameters of the wind power prediction model to be trained according to the difference by using the whale optimization algorithm WOA until the difference meets the training end condition, and determine the wind power prediction model to be trained after the last adjustment of the model parameters as the trained wind power prediction model.

[0022] According to an embodiment of the present application, the third acquisition module is further configured to: acquire a prediction error value of the wind power according to the wind power prediction value and the true wind power value; establish a cumulative distribution function of the prediction error value according to the Cornish-Fisher series; acquire a probability prediction interval curve of the wind power at different confidence levels according to the cumulative distribution function; and obtain the probability interval prediction result according to the probability prediction interval curve.

[0023] According to an embodiment of the present application, the determining module is further configured to: obtain the charge-discharge state of the energy storage system; and determine the energy storage operation strategy according to the charge-discharge state.

[0024] According to an embodiment of the present application, the determining module is further configured to: obtain the wind power limit, and determine the adjustable frequency regulation capacity of the wind-storage combined system according to the wind power limit; and determine the frequency regulation capacity of the wind-storage combined system according to the adjustable frequency regulation capacity, the energy storage operation strategy, the target energy storage capacity, the target energy storage power, and the probability interval prediction result.

[0025] To achieve the above object, an embodiment of the third aspect of the present application provides an electronic device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the method for determining the frequency regulation capacity of the wind-storage combined system as described in any one of the embodiments of the first aspect of the present application is implemented.

[0026] To achieve the above object, an embodiment of the fourth aspect of the present application provides a non-transitory computer-readable storage medium storing computer instructions, which are used to cause a computer to implement the method for determining the frequency regulation capacity of the wind-storage combined system as described in any one of the embodiments of the first aspect of the present application when executed. Description of the Drawings

[0027] Figure 1 It is a schematic diagram of the method for determining the frequency regulation capacity of the wind-storage combined system disclosed in an embodiment of the present application.

[0028] Figure 2 It is a schematic diagram of the method for determining the frequency regulation capacity of the wind-storage combined system disclosed in another embodiment of the present application.

[0029] Figure 3 It is a schematic diagram of the method for determining the frequency regulation capacity of the wind-storage combined system disclosed in another embodiment of the present application.

[0030] Figure 4 It is a schematic diagram of the method for determining the frequency regulation capacity of the wind-storage combined system disclosed in another embodiment of the present application.

[0031] Figure 5 It is a schematic diagram of the method for determining the frequency regulation capacity of the wind-storage combined system disclosed in another embodiment of the present application.

[0032] Figure 6 It is a schematic diagram of the method for determining the frequency regulation capacity of the wind-storage combined system disclosed in another embodiment of the present application.

[0033] Figure 7 It is a schematic diagram of the structure of the device for determining the frequency regulation capacity of the wind-storage combined system disclosed in an embodiment of the present application.

[0034] Figure 8 This is a schematic structural diagram of an electronic device disclosed in an embodiment of the present application. Detailed implementation manners

[0035] To better understand the above technical solutions, the exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be fully conveyed to those skilled in the art.

[0036] The following describes a method and device for determining the frequency modulation capacity of a wind-storage combined system according to an embodiment of the present application with reference to the drawings.

[0037] Figure 1 This is a schematic flowchart of a method for determining the frequency modulation capacity of a wind-storage combined system according to an embodiment disclosed in the present application.

[0038] As Figure 1 shown, the method for determining the frequency modulation capacity of the wind-storage combined system proposed in the embodiment of the present application specifically includes the following steps:

[0039] S101. Obtain the curtailed wind power of the wind farm, and construct an energy storage configuration optimization model for the wind-storage combined system according to the curtailed wind power.

[0040] Among them, the curtailed wind power refers to the power that the wind farm can generate but fails to generate due to factors such as system peak shaving and grid safety.

[0041] It should be noted that the present disclosure does not limit the specific manner of obtaining the curtailed wind power of the wind farm, and it can be selected according to the actual situation.

[0042] Optionally, the theoretical power generation W t and the actual power generation W a of the wind farm can be obtained, and the difference between the theoretical power generation and the actual power generation is calculated to obtain the curtailed wind power W c .

[0043] For example, the curtailed wind power W c = W t - W a , where W c is the curtailed wind power, W t is the theoretical power generation, and W a is the actual power generation.

[0044] It should be noted that after obtaining the curtailed wind power, a cost and benefit calculation model for a wind-storage combined system to participate in the frequency regulation market can be constructed based on the curtailed wind power, so as to obtain the cost and benefit of the wind-storage combined system participating in the frequency regulation market according to the cost-benefit calculation model, and an energy storage configuration optimization model can be constructed based on the cost and benefit of the wind-storage combined system participating in the frequency regulation market.

[0045] S102. Solve the energy storage configuration optimization model to obtain the target energy storage capacity and target energy storage power of the wind-storage combined system.

[0046] It should be noted that the target energy storage capacity and target energy storage power are the optimal energy storage capacity and optimal energy storage power output by the energy storage configuration optimization model.

[0047] Optionally, after obtaining the energy storage configuration optimization model, the objective function corresponding to the energy storage configuration optimization model can be obtained, and the objective function can be solved by the ant lion optimization algorithm to determine the target energy storage capacity and target energy storage power.

[0048] S103. Obtain the probabilistic interval prediction result of the wind power according to the wind power prediction model.

[0049] Optionally, sample data can be obtained to train the wind power prediction model to be trained until the wind power prediction model converges, and the trained wind power prediction model can be obtained. Based on the trained wind power prediction model, the probabilistic interval prediction result of the wind power can be obtained.

[0050] For example, based on the trained wind power prediction model, the wind power prediction value and the true wind power value can be obtained. According to the wind power prediction value and the true wind power value, the prediction error value of the wind power can be obtained. According to the Cornish-Fisher series, the cumulative distribution function of the prediction error value can be established. According to the cumulative distribution function, the probabilistic prediction interval curve of the wind power at different confidence levels can be obtained. The probabilistic interval prediction result of the wind power can be obtained according to the probabilistic prediction interval curve.

[0051] S104. Obtain the operation strategy of the energy storage system, and determine the frequency regulation capacity of the wind-storage combined system based on the operation strategy, target energy storage capacity, target energy storage power, and probabilistic interval prediction result.

[0052] It should be noted that the present application does not limit the specific manner of obtaining the operation strategy of the energy storage system, which can be selected according to the actual situation.

[0053] Optionally, the charge and discharge state of the energy storage system can be obtained, and the energy storage operation strategy can be determined according to the charge and discharge state.

[0054] For example, when the energy storage system is in the charging state, the energy storage system absorbs the curtailed wind power; when the energy storage system is in the discharging state, the energy storage system participates in the frequency regulation market.

[0055] It should be noted that during the operation of the energy storage system, when the charging state of the energy storage system reaches the full charge or full discharge state, the operation mode of the energy storage system is switched.

[0056] In the embodiment of the present disclosure, after obtaining the operation strategy, the target energy storage capacity, the target energy storage power, and the probability interval prediction result, the frequency regulation capacity of the wind-storage combined system can be determined according to the operation strategy, the target energy storage capacity, the target energy storage power, and the probability interval prediction result.

[0057] The method for determining the frequency regulation capacity of the wind-storage combined system provided by this application obtains the curtailed wind power of the wind farm, constructs an energy storage configuration optimization model for the wind-storage combined system according to the curtailed wind power, solves the energy storage configuration optimization model to obtain the target energy storage capacity and target energy storage power of the wind-storage combined system, obtains the probability interval prediction result of the wind power according to the wind power prediction model, obtains the operation strategy of the energy storage system, and determines the frequency regulation capacity of the wind-storage combined system based on the operation strategy, the target energy storage capacity, the target energy storage power, and the probability interval prediction result. Thus, this application can give full play to the complementary characteristics of the wind power system and the energy storage system, fully consider various information of the wind power system and the energy storage system, improve the accuracy of determining the frequency regulation capacity of the wind-storage combined system, improve the frequency regulation capacity and performance of the wind-storage combined system, and increase the benefits of the wind-storage combined system.

[0058] As a possible implementation, as Figure 2 shown, based on the above embodiment, the specific process of solving the energy storage configuration optimization model in the above step S102 to obtain the target energy storage capacity and target energy storage power of the wind-storage combined system includes the following steps:

[0059] S201. Obtain the costs and benefits of the wind-storage combined system participating in the frequency regulation market.

[0060] As a possible implementation, as Figure 3 shown, based on the above embodiment, the specific process of obtaining the cost of the wind-storage combined system participating in the frequency regulation market in the above step S201 includes the following steps:

[0061] S301. Obtain the equivalent annual value annual interest rate of the energy storage system.

[0062] Optionally, the annual interest rate of the energy storage system and the operation life of the energy storage system can be obtained, and the equivalent annual value annual interest rate of the energy storage system can be obtained according to the annual interest rate of the energy storage system and the operation life of the energy storage system.

[0063] For example, after obtaining the annual interest rate and the operating life of the energy storage system, the equivalent annual value annual interest rate C(r,n) of the energy storage system can be obtained using the following formula:

[0064]

[0065] Where C(r,n) is the equivalent annual value annual interest rate, r is the annual interest rate of the energy storage system, and n is the operating life of the energy storage system.

[0066] S302. Obtain the configured power of the energy storage system, the unit investment of the configured power, the configured capacity of the energy storage system, and the unit investment of the configured capacity.

[0067] S303. Obtain the cost of the wind-storage combined system participating in the frequency regulation market based on the equivalent annual value annual interest rate, the configured power, the unit investment of the configured power, the configured capacity, and the unit investment of the configured capacity.

[0068] It should be noted that for the cost of the wind-storage combined system participating in the frequency regulation market, the cost of wind power is ignored, and only the energy storage cost is considered. The energy storage cost includes the power cost and the energy cost, and the power cost and the energy cost are corrected according to the equivalent annual value interest rate to obtain the cost of the wind-storage combined system participating in the frequency regulation market.

[0069] For example, the following formula can be used to obtain the cost C of the wind-storage combined system participating in the frequency regulation market ln :

[0070] C ln = C(r,n)·(C p ·P ESS + C E ·E ESS )

[0071] Where C ln is the cost of the wind-storage combined system participating in the frequency regulation market, C(r,n) is the equivalent annual value annual interest rate, P ESS is the configured power, E ESS is the configured capacity, C p is the unit investment of the configured power, and C E is the unit investment of the configured capacity.

[0072] As a possible implementation, as Figure 4 shown, on the basis of the above embodiment, the specific process of obtaining the revenue of the wind-storage combined system participating in the frequency regulation market in the above step S401 includes the following steps:

[0073] S401. Obtain the frequency regulation performance index, the mileage benefit factor, the performance clearing price of the frequency regulation market, the frequency regulation capacity price of the frequency regulation market, and the curtailment absorption capacity.

[0074] Optionally, the frequency modulation performance indicators may consider adjustment rate, response time, adjustment accuracy indicators, etc. The mileage benefit factor refers to the ratio of the frequency modulation mileage of this type of frequency modulation resource to that of conventional frequency modulation resources, which can be set as a constant. The wind curtailment absorption capacity is determined by the configured capacity of the energy storage, the configured power of the energy storage, and the wind curtailment power of the wind farm.

[0075] S402. Obtain the revenue of the wind - energy storage combined system participating in the frequency modulation market according to the frequency modulation performance indicators, mileage benefit factor, performance clearing price, frequency modulation capacity price, and wind curtailment absorption capacity.

[0076] It should be noted that the revenue of the wind - energy storage combined system participating in the frequency modulation market includes frequency modulation capacity revenue and frequency modulation performance revenue.

[0077] For example, the revenue R of the wind - energy storage combined system participating in the frequency modulation market can be calculated using the following formula ln :

[0078]

[0079] where R ln is the revenue of the wind - energy storage combined system participating in the frequency modulation market, E ESS(i) is the wind curtailment absorption capacity on the i - th day, K is the frequency modulation performance indicator, λ is the mileage benefit factor, L pr is the performance clearing price, and L cr is the frequency modulation capacity price.

[0080] S202. Obtain the constraint conditions of the wind - energy storage combined system.

[0081] Optionally, the output power constraint of the wind - energy storage combined system, the output power quantity constraint of the wind - energy storage combined system, the energy storage frequency modulation performance performance constraint, etc. can be used as the constraint conditions of the wind - energy storage combined system.

[0082] For example, the constraint conditions of the wind - energy storage combined system can be set as where is the rated power of the energy storage, and P t b is the power of the energy storage at time t.

[0083] S203. Construct the objective function of the energy storage configuration optimization model according to the constraint conditions, cost, and revenue.

[0084] In the embodiments of the present application, after obtaining the constraint conditions, cost, and revenue, the objective function of the energy storage configuration optimization model can be constructed according to the constraint conditions, cost, and revenue.

[0085] For example, the objective function of the energy storage configuration optimization model is F = Max(R ln - C ln ).

[0086] S204. Solve the objective function according to the ant lion optimization algorithm to obtain the target energy storage capacity and the target energy storage power.

[0087] Among them, the ant lion optimization algorithm (Ant Lion Optimizer, abbreviated as ALO) is a process of continuously iteratively searching for the optimal solution, which has the characteristics of global optimization, few adjustable parameters, high convergence accuracy, and good robustness.

[0088] It should be noted that after obtaining the objective function, the objective function can be solved according to the ant lion optimization algorithm to achieve global optimization and obtain the optimal solution of the objective function, that is, to obtain the target energy storage capacity and the target energy storage power of the wind-storage combined system.

[0089] The method for determining the frequency modulation capacity of the wind-storage combined system provided by this application obtains the costs and benefits of the wind-storage combined system participating in the frequency modulation market, obtains the constraint conditions of the wind-storage combined system, constructs the objective function of the energy storage configuration optimization model according to the constraint conditions, costs and benefits, and solves the objective function according to the ant lion optimization algorithm to obtain the target energy storage capacity and the target energy storage power. Thus, this application fully considers the costs, benefits and constraint conditions of the wind-storage combined system participating in the frequency modulation market, and uses the good adaptive boundary contraction mechanism and elitism advantage of the ant lion optimization algorithm to determine a reasonable energy storage configuration plan, that is, to determine the target energy storage capacity and the target energy storage power of the wind-storage combined system, avoiding waste of energy storage resources.

[0090] The training process of the wind power prediction model will be explained below.

[0091] Optionally, sample data can be obtained. Among them, the sample data includes the historical data and prediction data of the wind farm. The sample data is input into the wind power prediction model to be trained to obtain the wind power prediction value corresponding to the sample data, and the true wind power value corresponding to the sample data is obtained.

[0092] Obtain the difference between the wind power prediction value and the true wind power value, and adjust the model parameters of the wind power prediction model to be trained according to the difference through the whale optimization algorithm (abbreviated as WOA) until the difference meets the training end condition. The wind power prediction model to be trained after the last adjustment of the model parameters is the trained wind power prediction model.

[0093] It should be noted that the wind power prediction model consists of a Convolutional Neural Network (CNN for short) and a Gate Recurrent Unit (GRU for short). The convolutional neural network is used to extract the characteristics of sample data. The whale optimization algorithm is used to continuously adjust and optimize the model parameters such as the batch size, learning rate, number of hidden layers, and number of neurons in each layer of the gate recurrent unit until the difference meets the training end condition. The wind power prediction model to be trained after the last adjustment of the model parameters is the trained wind power prediction model.

[0094] Optionally, the training end condition can be that the difference between the wind power prediction value and the actual wind power value is less than a preset difference threshold; the training end condition can also be that the number of times of adjusting the model parameters of the wind power prediction model reaches a preset adjustment times threshold.

[0095] As a possible implementation, as Figure 5 shown, based on the above embodiment, the specific process of obtaining the probability interval prediction result of the wind power according to the wind power prediction model in the above step S103 includes the following steps:

[0096] S501. Obtain the prediction error value of the wind power according to the wind power prediction value and the actual wind power value.

[0097] Optionally, after obtaining the converged wind power prediction model, the wind power prediction value can be obtained according to the wind power prediction model, and the prediction error value of the wind power can be obtained according to the wind power prediction value and the actual wind power value.

[0098] S502. Establish the cumulative distribution function of the prediction error value according to the Cornish-Fisher series.

[0099] In the embodiment of the present application, after obtaining the prediction error value, the cumulative distribution function (CDF for short) of the prediction error value can be obtained by using the Cornish-Fisher series expansion. Among them, the cumulative distribution function can describe the probability distribution of the prediction error value.

[0100] S503. Obtain the probability prediction interval curve of the wind power at different confidence levels according to the cumulative distribution function.

[0101] S504. Obtain the probability interval prediction result according to the probability prediction interval curve.

[0102] Optionally, after obtaining the cumulative distribution function, a probability prediction interval curve of wind power at different confidence levels can be constructed based on the cumulative distribution function, and a probability interval prediction result can be obtained according to the probability prediction interval curve.

[0103] As a possible implementation, as Figure 6 shown, based on the above embodiments, the specific process of determining the frequency modulation capacity of the wind-storage combined system in step S104 based on the operation strategy, target energy storage capacity, target energy storage power, and probability interval prediction result includes the following steps:

[0104] S601. Obtain the wind power limit, and determine the adjustable frequency modulation capacity of the wind-storage combined system according to the wind power limit.

[0105] It should be noted that the adjustable frequency modulation capacity of the wind-storage combined system comes from the energy storage system absorbing the curtailed wind power higher than the wind power limit, where the curtailed wind power is calculated by the probability interval prediction result of the wind power being higher than the wind power dispatched.

[0106] S602. Determine the frequency modulation capacity of the wind-storage combined system according to the adjustable frequency modulation capacity, energy storage operation strategy, target energy storage capacity, target energy storage power, and probability interval prediction result.

[0107] It should be noted that according to information such as the probability interval prediction result, energy storage operation strategy, adjustable frequency modulation capacity, target energy storage capacity, and target energy storage power, the probability interval prediction result at an appropriate confidence level is selected to guide the charge and discharge of the energy storage, so as to determine the frequency modulation capacity of the wind-storage combined system.

[0108] The method for determining the frequency modulation capacity of the wind-storage combined system provided by this application gives full play to the complementary characteristics of the wind power system and the energy storage system, fully considers various information of the wind power system and the energy storage system, improves the accuracy of determining the frequency modulation capacity of the wind-storage combined system, improves the frequency modulation capacity and performance of the wind-storage combined system, increases the revenue of the wind-storage combined system, provides a basis for power system dispatching, and at the same time, based on the energy storage operation strategy, the number of charge and discharge state switches of the energy storage system can be reduced, improving the lifespan of the energy storage system.

[0109] Figure 7 It is a schematic structural diagram of a device for determining the frequency modulation capacity of a wind-storage combined system according to an embodiment disclosed in this application.

[0110] As Figure 7 shown, the device 100 for determining the frequency modulation capacity of the wind-storage combined system includes: a first acquisition module 11, a second acquisition module 12, a third acquisition module 13, and a determination module 14. Among them,

[0111] The first acquisition module 11 is configured to acquire the curtailed wind power of the wind farm and construct an energy storage configuration optimization model for the wind-storage combined system according to the curtailed wind power;

[0112] The second acquisition module 12 is configured to solve the energy storage configuration optimization model to obtain the target energy storage capacity and the target energy storage power of the wind-storage combined system;

[0113] The third acquisition module 13 is configured to obtain the probabilistic interval prediction result of the wind power according to the wind power prediction model;

[0114] The determination module 14 is configured to obtain the operation strategy of the energy storage system, and determine the frequency regulation capacity of the wind-storage combined system based on the operation strategy, the target energy storage capacity, the target energy storage power, and the probabilistic interval prediction result.

[0115] According to an embodiment of the present application, the first acquisition module 11 is further configured to: acquire the theoretical power generation and the actual power generation of the wind farm; and acquire the curtailed wind power according to the theoretical power generation and the actual power generation.

[0116] According to an embodiment of the present application, the second acquisition module 12 is further configured to: acquire the cost and the revenue of the wind-storage combined system participating in the frequency regulation market; acquire the constraint conditions of the wind-storage combined system; construct an objective function of the energy storage configuration optimization model according to the constraint conditions, the cost, and the revenue; and solve the objective function according to the ant lion optimization algorithm to obtain the target energy storage capacity and the target energy storage power.

[0117] According to an embodiment of the present application, the second acquisition module 12 is further configured to: acquire the equal annual value annual interest rate of the energy storage system; acquire the configured power of the energy storage system, the unit investment of the configured power, the configured capacity of the energy storage system, and the unit investment of the configured capacity; and acquire the cost of the wind-storage combined system participating in the frequency regulation market according to the equal annual value annual interest rate, the configured power, the unit investment of the configured power, the configured capacity, and the unit investment of the configured capacity.

[0118] According to an embodiment of the present application, the second acquisition module 12 is further configured to: acquire the frequency regulation performance index, the mileage benefit factor, the performance clearing price of the frequency regulation market, the frequency regulation capacity price of the frequency regulation market, and the curtailed wind power absorption capacity; and acquire the revenue of the wind-storage combined system participating in the frequency regulation market according to the frequency regulation performance index, the mileage benefit factor, the performance clearing price, the frequency regulation capacity price, and the curtailed wind power absorption capacity.

[0119] According to an embodiment of the present application, the device 100 is further configured to: obtain sample data, where the sample data includes historical data and prediction data of the wind farm; input the sample data into a wind power prediction model to be trained to obtain a wind power prediction value corresponding to the sample data; obtain an actual wind power value corresponding to the sample data; obtain a difference between the wind power prediction value and the actual wind power value, and adjust model parameters of the wind power prediction model to be trained according to the difference by using the Whale Optimization Algorithm (WOA) until the difference meets a training end condition, and determine the wind power prediction model with the model parameters adjusted last time as a trained wind power prediction model.

[0120] According to an embodiment of the present application, the third obtaining module 13 is further configured to: obtain a prediction error value of the wind power according to the wind power prediction value and the actual wind power value; establish a cumulative distribution function of the prediction error value according to the Cornish-Fisher series; obtain a probability prediction interval curve of the wind power at different confidence levels according to the cumulative distribution function; and obtain the probability interval prediction result according to the probability prediction interval curve.

[0121] According to an embodiment of the present application, the determining module 14 is further configured to: obtain a charge and discharge state of the energy storage system; and determine the energy storage operation strategy according to the charge and discharge state.

[0122] According to an embodiment of the present application, the determining module 14 is further configured to: obtain a wind power limit, and determine an adjustable frequency capacity of the wind-storage combined system according to the wind power limit; and determine the frequency modulation capacity of the wind-storage combined system according to the adjustable frequency capacity, the energy storage operation strategy, the target energy storage capacity, the target energy storage power, and the probability interval prediction result.

[0123] A device for determining the frequency modulation capacity of a wind-storage combined system provided by an embodiment of the present application constructs an energy storage configuration optimization model of the wind-storage combined system by obtaining the curtailed wind power of a wind farm; solves the energy storage configuration optimization model to obtain a target energy storage capacity and a target energy storage power of the wind-storage combined system; obtains a probability interval prediction result of the wind power according to a wind power prediction model; obtains an operation strategy of the energy storage system, and determines the frequency modulation capacity of the wind-storage combined system based on the operation strategy, the target energy storage capacity, the target energy storage power, and the probability interval prediction result. Therefore, the present application can give full play to the complementary characteristics of the wind power system and the energy storage system, fully consider various information of the wind power system and the energy storage system, improve the accuracy of determining the frequency modulation capacity of the wind-storage combined system, improve the frequency modulation capacity and performance of the wind-storage combined system, and increase the benefits of the wind-storage combined system.

[0124] To implement the above embodiments, the present application also provides an electronic device 2000, as Figure 8 shown, including a memory 210, a processor 220, and a computer program stored on the memory 210 and executable on the processor 220. When the processor executes the program, the method for determining the frequency regulation capacity of the wind-storage combined system described above is implemented.

[0125] To implement the above embodiments, the present application also provides a non-transitory computer-readable storage medium storing computer instructions, which are used to cause a computer to implement the method for determining the frequency regulation capacity of the wind-storage combined system described above when executed.

[0126] In the description of the present application, it should be understood that the terms "center", "longitudinal", "transverse", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc. indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as a limitation to the present application.

[0127] In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the present application, "a plurality" means two or more, unless otherwise specifically defined.

[0128] In the present application, unless otherwise clearly defined and limited, the terms "mounted", "connected", "coupled", "fixed", etc. should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral body; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the internal communication of two elements or the interaction relationship between two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific circumstances.

[0129] In this application, unless otherwise clearly specified or limited, the first feature being "on" or "under" the second feature may mean that the first and second features are in direct contact, or the first and second features are indirectly in contact through an intermediate medium. Moreover, the first feature being "above", "over" and "on top of" the second feature may mean that the first feature is directly above or obliquely above the second feature, or merely indicates that the horizontal height of the first feature is higher than that of the second feature. The first feature being "under", "below" and "beneath" the second feature may mean that the first feature is directly below or obliquely below the second feature, or merely indicates that the horizontal height of the first feature is less than that of the second feature.

[0130] In the description of this specification, the descriptions with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples", etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of this application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, without conflict, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0131] Although the embodiments of this application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limitations to this application. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A method for determining the frequency regulation capacity of a wind-storage combined system, characterized in that The method includes: Obtaining the curtailed wind power of a wind farm and constructing an energy storage configuration optimization model for a wind-storage combined system based on the curtailed wind power; Solving the energy storage configuration optimization model to obtain the target energy storage capacity and target energy storage power of the wind-storage combined system; Obtaining the probabilistic interval prediction result of wind power according to a wind power prediction model; Obtaining the operation strategy of the energy storage system, and determining the frequency modulation capacity of the wind-storage combined system based on the operation strategy, the target energy storage capacity, the target energy storage power, and the probabilistic interval prediction result; The training process of the wind power prediction model includes: Obtaining sample data, where the sample data includes the historical data and prediction data of the wind farm; Inputting the sample data into the wind power prediction model to be trained to obtain the wind power prediction value corresponding to the sample data; Obtaining the true wind power value corresponding to the sample data; Obtaining the difference between the wind power prediction value and the true wind power value, and adjusting the model parameters of the wind power prediction model to be trained by the Whale Optimization Algorithm (WOA) according to the difference until the difference meets the training end condition, and determining the wind power prediction model after the last adjustment of the model parameters as the trained wind power prediction model; The obtaining of the probabilistic interval prediction result of wind power according to the wind power prediction model further includes: Obtaining the prediction error value of the wind power according to the wind power prediction value and the true wind power value; Establishing the cumulative distribution function of the prediction error value according to the Cornish-Fisher series; Obtaining the probabilistic prediction interval curve of wind power at different confidence levels according to the cumulative distribution function; Obtaining the probabilistic interval prediction result according to the probabilistic prediction interval curve.

2. The determination method according to claim 1, characterized in that The obtaining of the curtailed wind power of the wind farm further includes: Obtaining the theoretical power generation and actual power generation of the wind farm; Obtaining the curtailed wind power according to the theoretical power generation and the actual power generation.

3. The determination method according to claim 1, characterized in that The solving of the energy storage configuration optimization model to obtain the target energy storage capacity and target energy storage power of the wind-storage combined system further includes: Obtaining the cost and revenue of the wind-storage combined system participating in the frequency modulation market; Obtaining the constraint conditions of the wind-storage combined system; Constructing the objective function of the energy storage configuration optimization model according to the constraint conditions, the cost, and the revenue; Solving the objective function according to the Ant Lion Optimization Algorithm to obtain the target energy storage capacity and the target energy storage power.

4. The determination method according to claim 3, wherein The obtaining of the cost of the wind-storage combined system participating in the frequency modulation market further includes: Obtaining the equivalent annual value annual interest rate of the energy storage system; Obtaining the configured power of the energy storage system, the unit investment of the configured power, the configured capacity of the energy storage system, and the unit investment of the configured capacity; Obtaining the cost of the wind-storage combined system participating in the frequency modulation market according to the equivalent annual value annual interest rate, the configured power, the unit investment of the configured power, the configured capacity, and the unit investment of the configured capacity.

5. The determination method according to claim 3, wherein The obtaining of the revenue of the wind-storage combined system participating in the frequency regulation market further includes: Obtaining the frequency regulation performance index, the mileage benefit factor, the performance clearing price of the frequency regulation market, the frequency regulation capacity price of the frequency regulation market, and the curtailed wind absorption capacity; Based on the frequency regulation performance index, the mileage benefit factor, the performance clearing price, the frequency regulation capacity price, and the curtailed wind absorption capacity, to obtain the revenue of the wind-storage combined system participating in the frequency regulation market.

6. The determination method according to claim 1, wherein The obtaining of the operation strategy of the energy storage system includes: Obtaining the charge-discharge state of the energy storage system; Based on the charge-discharge state, determining the operation strategy of the energy storage system.

7. The determination method according to any one of claims 1-6, characterized in that, The determining of the frequency regulation capacity of the wind-storage combined system based on the operation strategy, the target energy storage capacity, the target energy storage power, and the probability interval prediction result further includes: Obtaining the wind power limit, and determining the adjustable frequency regulation capacity of the wind-storage combined system according to the wind power limit; Based on the adjustable frequency regulation capacity, the operation strategy of the energy storage system, the target energy storage capacity, the target energy storage power, and the probability interval prediction result, determining the frequency regulation capacity of the wind-storage combined system.

8. A device for determining the frequency regulation capacity of a wind-storage combined system, characterized in that The device includes: A first obtaining module, configured to obtain the curtailed wind power of the wind farm, and construct an energy storage configuration optimization model of the wind-storage combined system according to the curtailed wind power; A second obtaining module, configured to solve the energy storage configuration optimization model according to the ant lion optimization algorithm to obtain the target energy storage capacity and the target energy storage power of the wind-storage combined system; A third obtaining module, configured to obtain the probability interval prediction result of the wind power according to the wind power prediction model; A determining module, configured to obtain the operation strategy of the energy storage system, and based on the operation strategy, the target energy storage capacity, the target energy storage power, and the probability interval prediction result, determine the frequency regulation capacity of the wind-storage combined system; The training process of the wind power prediction model includes: Obtaining sample data, where the sample data includes the historical data and the prediction data of the wind farm; Inputting the sample data into the wind power prediction model to be trained to obtain the wind power prediction value corresponding to the sample data; Obtaining the true wind power value corresponding to the sample data; Obtaining the difference between the wind power prediction value and the true wind power value, and according to the difference, adjusting the model parameters of the wind power prediction model to be trained through the whale optimization algorithm WOA until the difference meets the training end condition, and determining the wind power prediction model after the last adjustment of the model parameters as the trained wind power prediction model; The third obtaining module is further configured to obtain the prediction error value of the wind power according to the wind power prediction value and the true wind power value; Establishing the cumulative distribution function of the prediction error value according to the Cornish-Fisher series; According to the cumulative distribution function, obtaining the probability prediction interval curve of the wind power at different confidence levels; According to the probability prediction interval curve, to obtain the probability interval prediction result.

9. An electronic device, characterized in that, Including a memory and a processor; Wherein, the processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to implement the method according to any one of claims 1-7.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to execute the method according to any one of claims 1-7.

Images