An energy storage optimization control method and system based on ultra-short-term power prediction data

Abstract

This application proposes a method and system for energy storage optimization control based on ultra-short-term power prediction data. The method includes: acquiring corrected ultra-short-term power prediction data; constructing an energy storage optimization control model, substituting the corrected ultra-short-term power prediction data into the energy storage optimization control model, and then solving the energy storage optimization control model using the Grey Wolf optimization algorithm to obtain the optimized energy storage charging and discharging power at each time point within the prediction period; and optimizing the charging and discharging power at each time point within the energy storage prediction period based on the optimized energy storage charging and discharging power. The technical solution proposed in this application utilizes the Grey Wolf optimization algorithm to solve the energy storage optimization control model to obtain the optimized energy storage charging and discharging power; and optimizes the charging and discharging power at each time point within the energy storage prediction period based on the optimized energy storage charging and discharging power, thereby improving the accuracy of the energy storage charging and discharging control strategy.

Description

Technical Field

[0001] This application relates to the field of energy storage optimization control, and in particular to an energy storage optimization control method and system based on ultra-short-term power prediction data. Background Technology

[0002] In the "wind-storage" scenario, wind farms typically use ultra-short-term power prediction data as the core boundary for the charging and discharging control of the energy storage system (i.e., as the actual generated power of the wind farm). However, due to the intermittent and random nature of wind, the accuracy of ultra-short-term power prediction is generally not high, which in turn affects the charging and discharging control strategy of the energy storage system and indirectly affects the combined output power of "wind-storage".

[0003] In existing technologies, corresponding algorithm models are established based on weather forecast data to predict the ultra-short-term power of wind power, and the accuracy of a day or a period of time is used as the evaluation index. The accuracy is low at finer time granularities such as hours and minutes, and no further processing is done to improve the accuracy of the ultra-short-term power prediction results. This results in low accuracy of the ultra-short-term power prediction data, which in turn leads to low accuracy of the charging and discharging control strategy corresponding to energy storage. Summary of the Invention

[0004] This application provides an energy storage optimization control method and system based on ultra-short-term power prediction data, which at least solves the technical problem of low accuracy of the corresponding charge and discharge control strategy for energy storage.

[0005] The first aspect of this application proposes an energy storage optimization control method based on ultra-short-term power prediction data, the method comprising:

[0006] Obtain the original ultra-short-term power prediction data corresponding to the wind farm at each moment within a preset time period, and correct the original ultra-short-term power prediction data to obtain the corrected ultra-short-term power prediction data.

[0007] An energy storage optimization control model is constructed, and the corrected ultra-short-term power prediction data is substituted into the energy storage optimization control model. Then, the gray wolf optimization algorithm is used to solve the energy storage optimization control model to obtain the energy storage charging and discharging power corresponding to each moment in the optimized prediction period.

[0008] The charging and discharging power of the energy storage is optimized and controlled at each moment during the energy storage prediction period based on the optimized energy storage charging and discharging power.

[0009] Preferably, the step of acquiring the original ultra-short-term power prediction data corresponding to the wind farm at each moment within a preset time period, and correcting the original ultra-short-term power prediction data to obtain corrected ultra-short-term power prediction data, includes:

[0010] Obtain the original ultra-short-term power prediction data, actual power generation data, and ultra-short-term power prediction data correction model for wind farms at each moment within a preset time period;

[0011] The correction coefficients corresponding to the ultra-short-term power prediction data correction model were determined using the Monte Carlo method.

[0012] Based on the original ultra-short-term power prediction data, the actual generated power data, and the correction coefficient, the ultra-short-term power prediction data correction model is solved to obtain the corrected ultra-short-term power prediction data corresponding to the original ultra-short-term power prediction data.

[0013] Furthermore, the calculation formula for the correction model of the ultra-short-term power prediction data is as follows:

[0014] P adjust,t =P predict,t +β1(P real,t-1 -P predict,t-1 )+β2(P real,t-2 -P predict,t-2 )

[0015] In the formula, P adjust,t For the corrected ultra-short-term power prediction data at time t, P predict,t Let P be the original ultra-short-term power prediction data at time t, β1, β2∈[0,1], β1 is the correction coefficient corresponding to the original ultra-short-term power prediction data at time t-1, and P is the original ultra-short-term power prediction data at time t-1. real,t-1 Let P be the actual generated power data at time t-1. predict,t-1 Let P be the original ultra-short-term power prediction data at time t-1, β2 be the correction coefficient corresponding to the original ultra-short-term power prediction data at time t-2, and P be the value of P. real,t-2 Let P be the actual generated power data at time t-2. predict,t-2 This is the raw ultra-short-term power prediction data at time t-2.

[0016] Furthermore, the step of determining the correction coefficients corresponding to the ultra-short-term power prediction data correction model using the Monte Carlo method includes:

[0017] Obtain the ideal discount rate and return on investment for the wind farm within the preset time period;

[0018] The correction coefficient corresponding to the ultra-short-term power prediction data correction model is determined by using the Monte Carlo method when the sum of the investment return rate and the ideal discount rate of the wind farm is maximized within the preset time period.

[0019] Preferably, the construction of the energy storage optimization control model includes:

[0020] An objective function is constructed with the goal of maximizing the sum of the investment return rate and the ideal discount rate for wind farms within a preset time period.

[0021] An energy storage optimization control model is constructed using constraints on the combined output power of wind and energy storage, the combined output electricity of wind and energy storage, the charging and discharging power of energy storage, the SOC of energy storage, and the SOC of energy storage at the end of the period, combined with the objective function.

[0022] A second aspect of this application proposes an energy storage optimization control system based on ultra-short-term power prediction data, comprising:

[0023] The correction module is used to obtain the original ultra-short-term power prediction data corresponding to the wind farm at each moment within a preset time period, and to correct the original ultra-short-term power prediction data to obtain the corrected ultra-short-term power prediction data.

[0024] The solution module is used to construct an energy storage optimization control model, and substitute the corrected ultra-short-term power prediction data into the energy storage optimization control model. Then, the gray wolf optimization algorithm is used to solve the energy storage optimization control model to obtain the energy storage charging and discharging power corresponding to each moment in the optimized prediction period.

[0025] An optimization control module is used to optimize and control the charging and discharging power at each moment within the energy storage prediction period based on the optimized energy storage charging and discharging power.

[0026] Preferably, the correction module includes:

[0027] The acquisition unit is used to acquire the original ultra-short-term power prediction data, actual power generation data and ultra-short-term power prediction data correction model of the wind farm at each moment within a preset time period.

[0028] A determination unit is used to determine the correction coefficients corresponding to the ultra-short-term power prediction data correction model using the Monte Carlo method;

[0029] The solution unit is used to solve the correction model of the ultra-short-term power prediction data based on the original ultra-short-term power prediction data, the actual generated power data and the correction coefficient, so as to obtain the corrected ultra-short-term power prediction data corresponding to the original ultra-short-term power prediction data.

[0030] Furthermore, the calculation formula for the correction model of the ultra-short-term power prediction data is as follows:

[0031] P adjust,t =P predict,t +β1(P real,t-1 -P predict,t-1 )+β2(P real,t-2 -P predict,t-2 )

[0032] In the formula, P adjust,t For the corrected ultra-short-term power prediction data at time t, P predict,t Let P be the original ultra-short-term power prediction data at time t, β1, β2∈[0,1], β1 is the correction coefficient corresponding to the original ultra-short-term power prediction data at time t-1, and P is the original ultra-short-term power prediction data at time t-1. real,t-1 Let P be the actual generated power data at time t-1. predict,t-1 Let P be the original ultra-short-term power prediction data at time t-1, β2 be the correction coefficient corresponding to the original ultra-short-term power prediction data at time t-2, and P be the value of P. real,t-2 Let P be the actual generated power data at time t-2. predict,t-2 This is the raw ultra-short-term power prediction data at time t-2.

[0033] Furthermore, the determining unit is used for:

[0034] Obtain the ideal discount rate and return on investment for the wind farm within the preset time period;

[0035] The correction coefficient corresponding to the ultra-short-term power prediction data correction model is determined by using the Monte Carlo method when the sum of the investment return rate and the ideal discount rate of the wind farm is maximized within the preset time period.

[0036] Preferably, the construction of the energy storage optimization control model includes:

[0037] An objective function is constructed with the goal of maximizing the sum of the investment return rate and the ideal discount rate for wind farms within a preset time period.

[0038] An energy storage optimization control model is constructed using constraints on the combined output power of wind and energy storage, the combined output electricity of wind and energy storage, the charging and discharging power of energy storage, the SOC of energy storage, and the SOC of energy storage at the end of the period, combined with the objective function.

[0039] The technical solutions provided by the embodiments of this application bring at least the following beneficial effects:

[0040] This application proposes a method and system for energy storage optimization control based on ultra-short-term power prediction data. The method includes: acquiring original ultra-short-term power prediction data for wind farms at each moment within a preset time period, and correcting the original ultra-short-term power prediction data to obtain corrected ultra-short-term power prediction data; constructing an energy storage optimization control model, substituting the corrected ultra-short-term power prediction data into the energy storage optimization control model, and then solving the energy storage optimization control model using the Grey Wolf optimization algorithm to obtain the optimized energy storage charging and discharging power at each moment within the prediction time period; and optimizing the charging and discharging power at each moment within the energy storage prediction time period based on the optimized energy storage charging and discharging power. The technical solution proposed in this application uses the Grey Wolf optimization algorithm to solve the energy storage optimization control model to obtain the optimized energy storage charging and discharging power; and optimizes the charging and discharging power at each moment within the energy storage prediction time period based on the optimized energy storage charging and discharging power, thereby improving the accuracy of the energy storage charging and discharging control strategy.

[0041] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0042] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0043] Figure 1 This is a flowchart of an energy storage optimization control method based on ultra-short-term power prediction data according to an embodiment of this application;

[0044] Figure 2 This is a flowchart of an energy storage optimization control system based on ultra-short-term power prediction data according to an embodiment of this application;

[0045] Figure 3 This is a structural diagram of a correction module in an energy storage optimization control system based on ultra-short-term power prediction data, according to an embodiment of this application. Detailed Implementation

[0046] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0047] This application proposes an energy storage optimization control method and system based on ultra-short-term power prediction data. The method includes: acquiring original ultra-short-term power prediction data for wind farms at each moment within a preset time period, and correcting the original ultra-short-term power prediction data to obtain corrected ultra-short-term power prediction data; constructing an energy storage optimization control model, substituting the corrected ultra-short-term power prediction data into the energy storage optimization control model, and then solving the energy storage optimization control model using the Grey Wolf optimization algorithm to obtain the optimized energy storage charging and discharging power at each moment within the prediction time period; and optimizing the charging and discharging power at each moment within the energy storage prediction time period based on the optimized energy storage charging and discharging power. The technical solution proposed in this application uses the Grey Wolf optimization algorithm to solve the energy storage optimization control model to obtain the optimized energy storage charging and discharging power; and optimizes the charging and discharging power at each moment within the energy storage prediction time period based on the optimized energy storage charging and discharging power, thereby improving the accuracy of the energy storage charging and discharging control strategy.

[0048] The following description, with reference to the accompanying drawings, illustrates an energy storage optimization control method and system based on ultra-short-term power prediction data.

[0049] Example 1

[0050] Figure 1 The flowchart below shows an energy storage optimization control method based on ultra-short-term power prediction data according to an embodiment of this application. Figure 1 As shown, the method includes:

[0051] Step 1: Obtain the original ultra-short-term power prediction data corresponding to the wind farm at each moment within the preset time period, and correct the original ultra-short-term power prediction data to obtain the corrected ultra-short-term power prediction data.

[0052] In this embodiment of the disclosure, step 1 specifically includes:

[0053] Step 1-1: Obtain the original ultra-short-term power prediction data, actual power generation data, and ultra-short-term power prediction data correction model for each moment within the preset time period;

[0054] It should be noted that a correlation statistical analysis algorithm is used to systematically statistically analyze the raw ultra-short-term power prediction data and actual power generation data of the wind farm, and to obtain the raw ultra-short-term power prediction values ​​and actual power generation data related to the ultra-short-term power prediction values ​​at each moment within the preset time period.

[0055] The calculation formula for the correction model of the ultra-short-term power prediction data is as follows:

[0056] P adjust,t =P predict,t +β1(Preal,t-1 -P predict,t-1 )+β2(P real,t-2 -P predict,t-2 )

[0057] In the formula, P adjust,t For the corrected ultra-short-term power prediction data at time t, P predict,t Let P be the original ultra-short-term power prediction data at time t, β1, β2∈[0,1], β1 is the correction coefficient corresponding to the original ultra-short-term power prediction data at time t-1, and P is the original ultra-short-term power prediction data at time t-1. real,t-1 Let P be the actual generated power data at time t-1. predict,t-1 Let P be the original ultra-short-term power prediction data at time t-1, β2 be the correction coefficient corresponding to the original ultra-short-term power prediction data at time t-2, and P be the value of P. real,t-2 Let P be the actual generated power data at time t-2. predict,t-2 This is the raw ultra-short-term power prediction data at time t-2.

[0058] Furthermore, the calculation formula for the correction model of the ultra-short-term power prediction data can also be:

[0059] P adjust,t =P predict,t +β(P real,t-1 -P predict,t-1 )

[0060] In the formula, P adjust,t For the corrected ultra-short-term power prediction data at time t, P predict,t Let P be the original ultra-short-term power prediction data at time t, β∈[0,1], where β is the correction coefficient corresponding to the original ultra-short-term power prediction data. real,t-1 Let P be the actual generated power data at time t-1. predict,t-1 This is the raw ultra-short-term power prediction data at time t-1.

[0061] Furthermore, the calculation of the correction model for the ultra-short-term power prediction data can also be as follows:

[0062]

[0063] In the formula, β i P represents the correction coefficient corresponding to the original ultra-short-term power prediction data at time i, where i ∈ [1-N], and N is the total number of times in the N times before time t within the preset time period. real,t-i Let P be the actual generated power data at time ti. predict,t-i The original ultra-short-term power prediction data for time ti, N≤T-1, t∈T, and T is the total number of times within the preset time period.

[0064] Step 1-2: Determine the correction coefficients corresponding to the ultra-short-term power prediction data correction model using the Monte Carlo method;

[0065] Furthermore, steps 1-2 include:

[0066] Step 1-2-1: Obtain the ideal discount rate and return on investment for the wind farm within the preset time period;

[0067] The correction coefficient corresponding to the ultra-short-term power prediction data correction model is determined by using the Monte Carlo method when the sum of the investment return rate and the ideal discount rate of the wind farm is maximized within the preset time period.

[0068] The formula for calculating the ideal discount rate for the wind farm within the preset time period is as follows:

[0069]

[0070] In the formula, IDR is the ideal discount rate corresponding to the wind farm within the preset time period, Actual is the total revenue for the preset time period calculated based on the original ultra-short-term power forecast data, and Ideal is the total revenue for the preset time period calculated based on the actual power generation data.

[0071] The method for obtaining the rate of return on investment can be as follows: obtaining the total revenue and total investment cost of the wind power station within a preset period, and using the ratio of the total revenue to the total investment cost as the rate of return on investment of the wind power station within the preset period.

[0072] It should be noted that the formula for calculating the total revenue within the preset time period can be: in, Benefit is the total revenue within a preset time period. t Let P be the payoff at time t. jishu,t Let Q be the base electricity price at time t. jishu,t Let P be the base amount of electricity at time t. zhong,t Let Q be the medium- to long-term electricity price at time t. zhong,t Let P be the medium- to long-term energy level at time t. riqian,t Let Q be the day-ahead clearing price corresponding to time t. riqian,t Let P be the day-ahead cleared quantity corresponding to time t. shishi,t Let P be the real-time clearing price at time t. adjust,t This is the corrected ultra-short-term power prediction data at time t.

[0073] The formula for calculating the total investment cost within the preset time period is: Cost = H1*S + H2*W + H3, where Cost is the total investment cost within the preset time period, H1 is the unit capacity cost of the energy storage system, S is the rated capacity of the energy storage system, H2 is the unit power cost of the energy storage system, W is the rated power of the energy storage system, and H3 is the fixed cost investment amount of the energy storage system.

[0074] Step 1-2-2: Use the Monte Carlo method to determine the correction coefficient corresponding to the ultra-short-term power prediction data correction model when the sum of the investment return rate and the ideal discount rate of the wind farm is maximized within the preset time period.

[0075] Step 1-2-2 includes:

[0076] Step F1: Randomly select the value corresponding to β1 and the value corresponding to β2 in [0, 1] for the nth time;

[0077] Step F2: Substitute the extracted values ​​of β1 and β2 into the correction model of the ultra-short-term power prediction data to obtain the corrected ultra-short-term power prediction data P at time t corresponding to the currently extracted values ​​of β1 and β2. adjust,t Then, calculate the absolute value of the difference between the corrected ultra-short-term power prediction data at time t corresponding to the currently extracted β1 and β2 values ​​and the actual power data at time t.

[0078] Step F3: Let n = n + 1, and return to step F1 until n = N, then proceed to step F4, where N is the preset number of times the correction coefficient is extracted;

[0079] Step F4: Perform statistical analysis on the N absolute values ​​of the difference to obtain the overall distribution of the absolute values ​​of the difference, and sort the absolute values ​​of the difference from smallest to largest to form a difference sequence. Then select the corrected ultra-short-term power prediction data at time t corresponding to the first m differences in the difference sequence.

[0080] Step F5: Calculate the sum of the investment return rate and the ideal discount rate of the wind farm within the preset time period based on the corrected ultra-short-term power prediction data at the t-th time corresponding to the first m differences, and select the β1 and β2 values ​​corresponding to the maximum sum. Use the selected β1 and β2 values ​​as the correction coefficients corresponding to the ultra-short-term power prediction data correction model.

[0081] It should be noted that the random selection of β in step F1 is based on the number of β values ​​in the modified model of the ultra-short-term power prediction data. This ensures that all β values ​​in the model are selected; if the model has two β values, they are randomly selected separately.

[0082] Steps 1-3: Based on the original ultra-short-term power prediction data, the actual generated power data, and the correction coefficient, solve the ultra-short-term power prediction data correction model to obtain the corrected ultra-short-term power prediction data corresponding to the original ultra-short-term power prediction data.

[0083] For example, substitute the original ultra-short-term power prediction data, the actual power generation data, and the correction coefficient into P. adjust,t =P predict,t +β1(P real,t-1 -P predict,t-1 )+β2(P real,t-2 -P predict,t-2 The solution is obtained by solving the original ultra-short-term power prediction data, and the corrected ultra-short-term power prediction data is obtained.

[0084] Step 2: Construct an energy storage optimization control model, and substitute the corrected ultra-short-term power prediction data into the energy storage optimization control model. Then, use the Grey Wolf optimization algorithm to solve the energy storage optimization control model to obtain the energy storage charging and discharging power corresponding to each moment in the optimized prediction period.

[0085] In this embodiment of the disclosure, the construction of the energy storage optimization control model includes:

[0086] An objective function is constructed with the goal of maximizing the sum of the investment return rate and the ideal discount rate for wind farms within a preset time period.

[0087] An energy storage optimization control model is constructed using constraints on the combined output power of wind and energy storage, the combined output electricity of wind and energy storage, the charging and discharging power of energy storage, the SOC of energy storage, and the SOC of energy storage at the end of the period, combined with the objective function.

[0088] The objective function can be calculated as: J = max(ROI + IDR), where J is the maximum sum of the return on investment and the ideal discount rate for the wind farm within a preset time period, and ROI is the return on investment for the wind farm within a preset time period.

[0089] The formula for calculating the combined wind and energy storage output power constraint can be:

[0090] P g,t =P adjust,t -P es,t

[0091] In the formula, P g,t Let P be the combined output power of wind and energy storage at time t. adjust,t For the corrected ultra-short-term power prediction data at time t, P es,t Let P be the energy storage charging and discharging power at time t. es,tWhen P > 0, it indicates energy storage charging; when P < 0, it indicates energy storage charging. es,t When the value is less than 0, it indicates energy storage discharge; energy storage charging indicates that the excess power generated by the wind farm is stored and utilized, and the actual power generation of the wind farm decreases; energy storage discharge indicates that some battery power is released, which increases the actual power generation of the wind farm.

[0092] The formula for calculating the power output constraint of the combined wind and energy storage can be:

[0093] Q g,t =P g,t Δt

[0094] In the formula, Q g,t Let Δt be the combined output power of wind and energy storage at time t, and Δt be the duration.

[0095] The formula for calculating the energy storage charging and discharging power constraint can be:

[0096] -P es,max ≤P es,t ≤P es,max

[0097] In the formula, P es,max This refers to the rated power of the energy storage system.

[0098] The formula for calculating the energy storage SOC constraint can be:

[0099]

[0100] In the formula, Let be the minimum state of charge of the stored energy at time t. Let t be the state of charge of the stored energy. Let be the maximum state of charge of the stored energy at time t, where the state of charge transition of the stored energy can be expressed by the following equation: The state of charge of the stored energy at time t+1. Let be the charging efficiency of the energy stored at time t. Let E be the discharge efficiency of the stored energy at time t. ini This represents the maximum capacity of the energy storage battery before it degrades.

[0101] The formula for calculating the SOC constraint at the end of the energy storage period can be:

[0102]

[0103] In the formula, S represents the state of charge of the energy storage at the moment immediately following the end of period T. SOC,G This is the preset energy storage state of charge.

[0104] Step 3: Based on the optimized energy storage charging and discharging power, optimize and control the charging and discharging power at each moment during the energy storage prediction period.

[0105] In summary, this embodiment proposes an energy storage optimization control method based on ultra-short-term power prediction data. The method utilizes the Grey Wolf optimization algorithm to solve the energy storage optimization control model, obtaining the optimized energy storage charging and discharging power. Based on the optimized energy storage charging and discharging power, the charging and discharging power at each moment within the energy storage prediction period is optimized and controlled, improving the accuracy of the energy storage charging and discharging control strategy. Furthermore, this application does not involve extensive modeling and calculations, allowing for direct application to actual industrial production. It also allows for flexible and autonomous adjustments based on the actual conditions of different wind farms, demonstrating high generalization ability.

[0106] Example 2

[0107] Figure 2 According to one embodiment of this application, an energy storage optimization control system based on ultra-short-term power prediction data is provided, such as... Figure 2 As shown, it includes:

[0108] The correction module 100 is used to acquire the original ultra-short-term power prediction data corresponding to the wind farm at each moment within a preset time period, and to correct the original ultra-short-term power prediction data to obtain the corrected ultra-short-term power prediction data.

[0109] The solution module 200 is used to construct an energy storage optimization control model, and to substitute the corrected ultra-short-term power prediction data into the energy storage optimization control model. Then, the gray wolf optimization algorithm is used to solve the energy storage optimization control model to obtain the energy storage charging and discharging power corresponding to each moment in the optimized prediction period.

[0110] The optimization control module 300 is used to optimize and control the charging and discharging power at each moment during the energy storage prediction period based on the optimized energy storage charging and discharging power.

[0111] Preferred, such as Figure 3 As shown, the correction module 100 includes:

[0112] The acquisition unit 101 is used to acquire the original ultra-short-term power prediction data, actual power generation data and ultra-short-term power prediction data correction model of the wind farm at each moment within a preset time period.

[0113] Determining unit 102 is used to determine the correction coefficients corresponding to the ultra-short-term power prediction data correction model using the Monte Carlo method;

[0114] The solution unit 103 is used to solve the correction model of the ultra-short-term power prediction data based on the original ultra-short-term power prediction data, the actual generated power data and the correction coefficient, so as to obtain the corrected ultra-short-term power prediction data corresponding to the original ultra-short-term power prediction data.

[0115] Furthermore, the calculation formula for the correction model of the ultra-short-term power prediction data is as follows:

[0116] P adjust,t =P predict,t +β1(P real,t-1 -P predict,t-1 )+β2(P real,t-2 -P predict,t-2 )

[0117] In the formula, P adjust,t For the corrected ultra-short-term power prediction data at time t, P predict,t Let P be the original ultra-short-term power prediction data at time t, β1, β2∈[0,1], β1 is the correction coefficient corresponding to the original ultra-short-term power prediction data at time t-1, and P is the original ultra-short-term power prediction data at time t-1. real,t-1 Let P be the actual generated power data at time t-1. predict,t-1 Let P be the original ultra-short-term power prediction data at time t-1, β2 be the correction coefficient corresponding to the original ultra-short-term power prediction data at time t-2, and P be the value of P. real,t-2 Let P be the actual generated power data at time t-2. predict,t-2 This is the raw ultra-short-term power prediction data at time t-2.

[0118] Furthermore, the determining unit 102 is used for:

[0119] Obtain the ideal discount rate and return on investment for the wind farm within the preset time period;

[0120] The correction coefficient corresponding to the ultra-short-term power prediction data correction model is determined by using the Monte Carlo method when the sum of the investment return rate and the ideal discount rate of the wind farm is maximized within the preset time period.

[0121] In this embodiment of the disclosure, the construction of the energy storage optimization control model includes:

[0122] An objective function is constructed with the goal of maximizing the sum of the investment return rate and the ideal discount rate for wind farms within a preset time period.

[0123] An energy storage optimization control model is constructed using constraints on the combined output power of wind and energy storage, the combined output electricity of wind and energy storage, the charging and discharging power of energy storage, the SOC of energy storage, and the SOC of energy storage at the end of the period, combined with the objective function.

[0124] In summary, the energy storage optimization control system proposed in this embodiment uses the Grey Wolf optimization algorithm to solve the energy storage optimization control model, obtaining the optimized energy storage charging and discharging power. Based on the optimized energy storage charging and discharging power, the charging and discharging power at each moment within the energy storage prediction period is optimized and controlled, improving the accuracy of the energy storage charging and discharging control strategy. At the same time, this application does not involve a large amount of modeling and calculation, and can be directly applied to actual industrial production. Furthermore, it can be flexibly and autonomously adjusted according to the actual conditions of different wind farms, exhibiting high generalization ability.

[0125] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0126] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0127] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled 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 optimal control of energy storage based on ultra-short-term power prediction data, characterized in that, The method includes: Obtain the original ultra-short-term power prediction data corresponding to the wind farm at each moment within a preset time period, and correct the original ultra-short-term power prediction data to obtain the corrected ultra-short-term power prediction data. An energy storage optimization control model is constructed, and the corrected ultra-short-term power prediction data is substituted into the energy storage optimization control model. Then, the gray wolf optimization algorithm is used to solve the energy storage optimization control model to obtain the energy storage charging and discharging power corresponding to each moment in the optimized prediction period. Based on the optimized energy storage charging and discharging power, the charging and discharging power at each moment within the energy storage prediction period is optimized and controlled. The process of acquiring the original ultra-short-term power prediction data corresponding to the wind farm at each moment within a preset time period, and correcting the original ultra-short-term power prediction data to obtain corrected ultra-short-term power prediction data, includes: Obtain the original ultra-short-term power prediction data, actual power generation data, and ultra-short-term power prediction data correction model for wind farms at each moment within a preset time period; The correction coefficients corresponding to the ultra-short-term power prediction data correction model were determined using the Monte Carlo method. Based on the original ultra-short-term power prediction data, the actual generated power data and the correction coefficient, the ultra-short-term power prediction data correction model is solved to obtain the corrected ultra-short-term power prediction data corresponding to the original ultra-short-term power prediction data. The calculation formula for the corrected model of the ultra-short-term power prediction data is as follows: In the formula, This is the corrected ultra-short-term power prediction data at time t. The original ultra-short-term power prediction data is given at time t. , Here are the correction coefficients corresponding to the original ultra-short-term power prediction data at time t-1. This refers to the actual power generation data at time t-1. The original ultra-short-term power prediction data is for time t-1. Here are the correction coefficients corresponding to the original ultra-short-term power prediction data at time t-2. This refers to the actual power generation data at time t-2. This is the raw ultra-short-term power prediction data at time t-2; The step of determining the correction coefficients corresponding to the ultra-short-term power prediction data correction model using the Monte Carlo method includes: Obtain the ideal discount rate and return on investment for the wind farm within the preset time period; The correction coefficient corresponding to the ultra-short-term power prediction data correction model is determined by using the Monte Carlo method when the sum of the investment return rate and the ideal discount rate of the wind farm is maximized within the preset time period; The construction of the energy storage optimization control model includes: An objective function is constructed with the goal of maximizing the sum of the investment return rate and the ideal discount rate for wind farms within a preset time period. An energy storage optimization control model is constructed using constraints on the combined output power of wind and energy storage, the combined output electricity of wind and energy storage, the charging and discharging power of energy storage, the SOC of energy storage, and the SOC of energy storage at the end of the period, combined with the objective function.

2. An energy storage optimization control system based on ultra-short-term power prediction data, characterized in that, include: The correction module is used to obtain the original ultra-short-term power prediction data corresponding to the wind farm at each moment within a preset time period, and to correct the original ultra-short-term power prediction data to obtain the corrected ultra-short-term power prediction data. The solution module is used to construct an energy storage optimization control model, and substitute the corrected ultra-short-term power prediction data into the energy storage optimization control model. Then, the gray wolf optimization algorithm is used to solve the energy storage optimization control model to obtain the energy storage charging and discharging power corresponding to each moment in the optimized prediction period. An optimization control module is used to optimize and control the charging and discharging power at each moment within the energy storage prediction period based on the optimized energy storage charging and discharging power. The correction module includes: The acquisition unit is used to acquire the original ultra-short-term power prediction data, actual power generation data and ultra-short-term power prediction data correction model of the wind farm at each moment within a preset time period. A determination unit is used to determine the correction coefficients corresponding to the ultra-short-term power prediction data correction model using the Monte Carlo method; The solving unit is used to solve the correction model of the ultra-short-term power prediction data based on the original ultra-short-term power prediction data, the actual generated power data and the correction coefficient, so as to obtain the corrected ultra-short-term power prediction data corresponding to the original ultra-short-term power prediction data. The calculation formula for the corrected model of the ultra-short-term power prediction data is as follows: In the formula, This is the corrected ultra-short-term power prediction data at time t. The original ultra-short-term power prediction data is given at time t. , Here are the correction coefficients corresponding to the original ultra-short-term power prediction data at time t-1. This refers to the actual power generation data at time t-1. The original ultra-short-term power prediction data is for time t-1. Here are the correction coefficients corresponding to the original ultra-short-term power prediction data at time t-2. This refers to the actual power generation data at time t-2. This is the raw ultra-short-term power prediction data at time t-2; The determining unit is used for: Obtain the ideal discount rate and return on investment for the wind farm within the preset time period; The correction coefficient corresponding to the ultra-short-term power prediction data correction model is determined by using the Monte Carlo method when the sum of the investment return rate and the ideal discount rate of the wind farm is maximized within the preset time period; The construction of the energy storage optimization control model includes: An objective function is constructed with the goal of maximizing the sum of the investment return rate and the ideal discount rate for wind farms within a preset time period. An energy storage optimization control model is constructed using constraints on the combined output power of wind and energy storage, the combined output electricity of wind and energy storage, the charging and discharging power of energy storage, the SOC of energy storage, and the SOC of energy storage at the end of the period, combined with the objective function.

Images