An over-capacity energy storage power compensation method and related device

Abstract

The application relates to the technical field of wind farm power compensation, in particular to an over-capacity energy storage power compensation method and related equipment. The method first acquires historical time output power value data of a wind farm, inputs the historical time output power value data into a prediction model, and obtains predicted power value at the next time; a frequency modulation instruction is generated according to the predicted power value, expected power value in the instruction is combined, and the expected compensation power value of the wind farm energy storage system is calculated; then, compensation income is calculated based on the expected compensation power value and the expected power value in the instruction, the power value at the next time is adjusted according to the income, and the energy storage system is controlled according to the adjusted power value. The application solves the problem that current wind farm power compensation is inaccurate and economic optimization cannot be realized, improves power prediction accuracy, guarantees stable output of wind power, and optimizes wind farm income.

Description

Technical Field

[0001] This invention relates to the field of wind farm power compensation technology, specifically to a supercapacitor energy storage power compensation method and related equipment. Background Technology

[0002] Wind farms are a developing new energy source, but their volatility and intermittency negatively impact the power grid. Therefore, energy storage systems can store excess energy when wind power is abundant and release it when wind power is insufficient, thus smoothing out power output fluctuations and making them more stable and predictable. Short-term power forecasting of wind farms improves wind power absorption, and the power grid, for safety reasons, assesses the accuracy of short-term forecasts, penalizing those that fail to meet standards. Energy storage devices can smooth out power generation fluctuations from wind farms, helping new energy power plants with absorption, peak shaving, frequency regulation, and stable output, thereby reducing energy losses, and are therefore widely used in wind farms. Although existing technologies can provide some short-term power forecasting for wind farms based on supercapacity energy storage systems, accurately predicting real-time power changes remains a technical challenge. These technological limitations prevent wind farms from optimizing power production and dispatch based on real-time wind resource conditions. Because the dynamic characteristics of wind farms make it impossible to accurately predict power, the frequency regulation commands generated based on the prediction results also have errors and cannot accurately guide the energy storage system to compensate for power values, thus affecting the profitability of wind farms. Summary of the Invention

[0003] This invention provides a method and related equipment for supercapacity energy storage power compensation, aiming to solve the problems of inaccurate power compensation and inability to achieve economic optimization in current wind farms.

[0004] The objective of this invention is achieved through the following technical solutions:

[0005] In a first aspect, the present invention provides a method for compensating the power of supercapacitive energy storage, comprising:

[0006] Obtain historical data on the output power of wind farms;

[0007] Input the historical wind farm output power data into the prediction model to obtain the predicted power value for the next moment;

[0008] The frequency regulation command is obtained based on the predicted power value at the next moment. The expected compensation power value of the energy storage system in the wind farm is calculated based on the expected power value in the frequency regulation command and the predicted power value at the next moment.

[0009] The compensation benefit is calculated based on the expected compensation power value of the energy storage system and the expected power value in the frequency regulation command. The predicted power value at the next moment is adjusted according to the compensation benefit, and the energy storage system is controlled according to the adjusted predicted power value at the next moment.

[0010] The prediction model is as follows:

[0011]

[0012] In the formula, For the first m Predicted power value at time 10:00 For the first i The prediction coefficient corresponding to time 1. for The output power data of the wind farm at any given time. The time interval between two power levels. The prediction coefficients are derived from the actual historical power values, representing the total amount of historical data used for prediction.

[0013] As a further improvement of the present invention, the calculation of compensation benefit based on the expected compensation power value of the energy storage system and the expected power value in the frequency regulation command, and the adjustment of the predicted power value at the next moment based on the compensation benefit, specifically includes:

[0014] If the maximum output power of the energy storage system is less than the expected compensation power value, the predicted power value for the next moment is adjusted according to the compensation benefit. Then, the expected compensation power value of the energy storage system is adjusted according to the adjusted power value. Finally, the total compensation benefit is calculated based on the adjusted expected compensation power value of the energy storage system to maximize the total benefit of the wind farm. If not, the energy storage system is controlled according to the current predicted power value. The total benefit is the sum of the total compensation benefit of the expected compensation power value and the benefit of the energy storage system participating in primary frequency regulation.

[0015] As a further improvement of the present invention, the prediction coefficients are as follows:

[0016]

[0017] In the formula, August ( ) represents the arithmetic mean. for thousand The actual power value at that moment, for m- ( n+ 1) The actual power value at time t, for m- 1 hour to m The interval of -2 seconds, for m -2 o'clock to m The interval of -4 seconds, for thousand Time to m -( n +3) The time interval, n >2.

[0018] As a further improvement of the present invention, after constructing the prediction model based on the prediction coefficients, the prediction model is further modified based on the revenue per unit price of the wind farm. The modified prediction model is as follows:

[0019]

[0020] In the formula, For the first m Predicted power value at time 10:00 These are the correction factors corresponding to each time point. for is The output power data of the wind farm at any given time. The time interval between two power levels. n The total amount of historical time data used for prediction. The unit price for revenue from energy storage systems participating in primary frequency regulation. The correction factor is used to compensate for the costs incurred by the energy storage system when a wind farm meets the revenue assessment criteria. satisfy:

[0021]

[0022] In the formula, T The number of loops. The time interval is the cycle time. n This represents the total amount of historical time data used for prediction.

[0023] As a further improvement to the present invention, the total number of predicted historical moment data... n The method for determining is as follows: obtain respectively is Time and m -( i +1) All output power values ​​corresponding to time 1, based on m Before the moment i All output power values ​​at each time point are used to predict the output power values ​​using a prediction model. m The first predicted power value at time t, based on m Before the moment i The output power values ​​at time +1 are used to predict the output power values ​​using a prediction model. m The second predicted power value at time t, if the first predicted power value and the second predicted power value satisfy the discrimination condition, then... m Before the moment iThe total number of historical time data corresponding to each time point is used as the total number of data points for prediction. The discrimination condition is:

[0024]

[0025] In the formula, The first predicted power value, This is the second predicted power value.

[0026] As a further improvement of the present invention, the benefits of the energy storage system participating in primary frequency regulation are as follows:

[0027]

[0028] In the formula, A 1 represents the revenue of the energy storage system after participating in primary frequency regulation. M The unit price for revenue from energy storage systems participating in primary frequency regulation. P c1 The power required to participate in frequency modulation t This refers to the frequency modulation time.

[0029] As a further improvement of the present invention, the total compensation benefit of the energy storage system for the expected compensation power value is:

[0030]

[0031] In the formula, A 2 represents the total compensation revenue obtained by the energy storage system through power compensation. N The cost that the energy storage system needs to participate in when a wind farm meets the revenue assessment criteria. P c2 This represents the expected compensation power value of the energy storage system. t This refers to the frequency modulation time.

[0032] Secondly, the present invention also provides a supercapacitive energy storage power compensation system, comprising:

[0033] The data acquisition module is used to obtain the actual output power value of the wind farm at historical moments;

[0034] The power prediction module is used to input the output power data of the wind farm at historical moments into the prediction model to obtain the predicted power value at the next moment.

[0035] The power compensation module is used to obtain the frequency regulation command corresponding to the predicted power value at the next moment, calculate the expected compensation power value of the energy storage system in the wind farm based on the expected power value in the frequency regulation command and the power value at the next moment, calculate the compensation benefit based on the expected compensation power value of the energy storage system and the expected power value in the frequency regulation command, and optimize the benefit by adjusting the prediction results.

[0036] The prediction model is as follows:

[0037]

[0038] In the formula, For the first m Predicted power value at time 10:00 For the first i The prediction coefficient corresponding to time 1. for The output power data of the wind farm at any given time. The time interval between two power levels. The prediction coefficients are derived from the actual historical power values, representing the total amount of historical data used for prediction.

[0039] Thirdly, the present invention also provides an electronic device, including a processor and a memory, wherein the processor is used to execute a computer program stored in the memory to implement the supercapacitive energy storage power compensation method as described above.

[0040] Fourthly, the present invention also provides a computer-readable storage medium storing at least one instruction that, when executed by a processor, implements the supercapacitive energy storage power compensation method as described above.

[0041] The beneficial effects of this invention are as follows: The supercapacity energy storage power compensation method of this invention, by constructing a prediction model based on historical data, can more accurately predict the output power value of a wind farm at the next moment. This prediction not only considers the operating characteristics of the wind farm itself, but also incorporates the regularity and trend of historical data, thereby improving the accuracy and reliability of the prediction. The frequency regulation command generated based on the prediction results can more accurately guide the compensation power value of the energy storage system. By calculating the expected compensation power value of the energy storage system and the expected power value in the frequency regulation command, the charging and discharging strategy of the energy storage system can be adjusted in real time to ensure the stability and response speed of the wind farm during the grid frequency regulation process, while reducing unnecessary energy losses. When the capacity of the energy storage system is limited, the expected compensation power value of the energy storage system is calculated using the frequency regulation command. The compensation benefit is calculated by comparing the expected compensation power value of the energy storage system with the expected power value in the frequency regulation command. This compensation benefit is the predicted benefit for the next moment. By adjusting the prediction results to optimize the expected compensation power value of the energy storage system, it can be ensured that the wind farm maximizes its economic benefits while meeting the grid frequency regulation requirements. This optimization strategy not only improves the operating efficiency of the wind farm, but also enhances its competitiveness in the electricity market. This invention not only provides more accurate power predictions, but also enables the optimization of the economic benefits of wind farms by adjusting the accurate predicted power values. Attached Figure Description

[0042] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0043] Figure 1 This is a schematic diagram of the supercapacitive energy storage power compensation method in an embodiment of the present invention;

[0044] Figure 2 This is a schematic diagram of the electronic device structure in an embodiment of the present invention. Detailed Implementation

[0045] To make the objectives and technical solutions of this invention clearer and easier to understand, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. The specific embodiments described herein are for illustrative purposes only and are not intended to limit the invention.

[0046] The present invention provides a method for compensating the power of supercapacitor energy storage. The method mainly includes: acquiring historical output power data of a wind farm; inputting the historical output power data into a prediction model to obtain the predicted power value for the next time moment; obtaining a frequency regulation command based on the power value for the next time moment; calculating the expected compensation power value of the energy storage system in the wind farm based on the expected compensation power value of the energy storage system and the expected power value in the frequency regulation command; calculating the compensation benefit based on the expected compensation power value of the energy storage system and the expected power value in the frequency regulation command; adjusting the predicted power value for the next time moment based on the compensation benefit; and controlling the energy storage system based on the adjusted predicted power value for the next time moment. The prediction model is as follows:

[0047]

[0048] In the formula, For the first m Predicted power value at time 10:00 For the first i The prediction coefficient corresponding to time 1. for The output power data of the wind farm at any given time. The time interval between two power levels. The prediction coefficients are derived from the actual historical power values, representing the total amount of historical data used for prediction.

[0049] This invention first acquires historical wind farm output power data to provide foundational data for subsequent power prediction. This historical power data is then input into a prediction model to obtain the predicted power value for the next moment. Based on this predicted power value, a frequency regulation command is generated. Subsequently, the expected compensation power value of the wind farm's energy storage system is calculated using the expected power value in the frequency regulation command and the predicted power value. Furthermore, compensation revenue is calculated based on the expected compensation power value of the energy storage system and the expected power value in the frequency regulation command. The predicted power value for the next moment is adjusted according to the compensation revenue, and the adjusted power value is used to control the energy storage system. This invention solves the current technical problems of inaccurate wind farm power compensation and the inability to achieve economic optimization through historical data-driven power prediction, frequency regulation command generation associated with the prediction results, compensation calculation based on the expected power of the command, and revenue-oriented power adjustment. This invention relies on historical data to ensure the effectiveness of the power prediction for the next moment, clarifies the energy storage compensation needs by combining the frequency regulation command and the predicted power, and then adjusts the power value to control the energy storage system based on revenue. This improves the accuracy of power compensation and optimizes the economic benefits of the wind farm through revenue adjustment.

[0050] The technical solution of the present invention will be clearly and completely described below with reference to the accompanying drawings and specific embodiments. The described embodiments are only some embodiments of the present invention, and not all embodiments.

[0051] Example 1

[0052] like Figure 1 The proposed method for compensating the power of supercapacity energy storage mainly includes the following implementation steps.

[0053] First, historical power output data of wind farms are obtained and used as training data. Second, a prediction model is constructed based on prediction coefficients. The historical power output data of wind farms is used as input to the prediction model to predict the power value of wind farms at the next time step, thus obtaining the corresponding prediction results.

[0054] Specifically, the prediction model mentioned in this embodiment is:

[0055]

[0056] In the formula, in the formula, Let m be the predicted power value at time m. Let be the prediction coefficient corresponding to time i. for The output power data of the wind farm at any given time. The time interval between two power levels. Let be the total amount of historical time data used for prediction, where This is used to introduce time-scale effects and enhance the flexibility of the prediction model. The prediction coefficients are as follows:

[0057]

[0058] In the formula, August ( ) represents the arithmetic mean. for thousand The actual power value at that moment, for m- ( n+ 1) The actual power value at time t, for m- 1 hour to m The interval of -2 seconds, for m -2 o'clock to m The interval of -4 seconds, for thousand Time to m -( n +3) The time interval, n >2. Among them i Possible values ​​are 3, 4, ... n .

[0059] The total amount of training data used in this embodiment n It is determined through the coupling of prediction models. Specifically, the determination method is as follows: obtain... is Time and m -( i +1) All output power values ​​corresponding to time 1, based on m Before the moment i All output power values ​​at each time point are used to predict the output power values ​​using a prediction model. m The first predicted power value at time t, based on m Before the moment i The output power values ​​at time +1 are used to predict the output power values ​​using a prediction model. m The second predicted power value at time t, if the first predicted power value and the second predicted power value satisfy the discrimination condition, then... m Before the moment i The total number of historical time data points corresponding to each time point is used as the total number of historical time data points for prediction. Specifically: The total number of historical time data points for prediction. n The method for determining this is as follows: First, select any historical [data / data]. m Using all output power values ​​at time -2 as training data, the prediction model is used to predict the th... m Output power value at time 1 y m Then select from m -3 (i Using all output power values ​​at time ≥10 as training data, the prediction model is used to predict the output power of the 10th time step. m Output power value at time 1 y ` m Based on the predicted output power values ​​at two different times y m and y` m The system uses a discrimination condition to determine whether the condition is met. If the condition is met, the actual output power data corresponding to the two previous historical moments is used as the total number of historical moment data to be predicted. n =2, if not satisfied, then use the previous... m -3 moments and before m- All output power values ​​from 4 were used as training data, and the prediction model was used to predict... m The output power value corresponding to each time point is determined based on a discrimination condition. If the condition is met, the actual output power data corresponding to the three previous historical time points are used as the total number of predicted historical time point data. n =3. If not satisfied, continue judging according to the discrimination condition, and so on, until the previous history is obtained. i time, is ( i ≥10) time and m -( i Using all output power values ​​at time +1 as training data, the prediction model is used to predict... m The first and second predicted power values ​​at time 1 meet the discrimination criteria, and the historical data is then used to determine the next time period. i The total number of historical time data points corresponding to each time point is used as the basis for prediction. n=i The discrimination criteria are as follows:

[0060]

[0061] In the formula, The first predicted power value (i.e., when) n=i The time corresponds to the first m (Predicted power value at time) For the second predicted power value (i.e. when n=i+ The first time corresponding to 1 m (Predicted power value at time).

[0062] Short-term forecasts are made based on the forecast results, with a time scale of 0-72. h The time resolution is 15 thousand It is mainly used to rationally arrange the power generation plan of conventional generating units and solve the problem of power grid peak shaving.

[0063] The method also includes modifying the prediction model based on the revenue per unit price of the wind farm, wherein the modified prediction model is:

[0064]

[0065] In the formula, y m For the first m Predicted power value at time 10:00 These are the correction factors corresponding to each time point. for is The output power data of the wind farm at any given time. For two power time intervals, that is is Time and m The time interval of time, M The unit price for revenue from energy storage systems participating in primary frequency regulation is expressed in ten thousand yuan / ( MWh ), N The cost that the energy storage system needs to participate in compensation for when a wind farm meets the revenue assessment criteria (i.e., the penalty avoided by participating in compensation; for ease of calculation later, it is converted into revenue here) is in ten thousand yuan / ( MWh ),in rand ( ) Random number selection, T The number of iterations, and the correction factor. satisfy:

[0066]

[0067] In the formula, T The number of loops. T =30, This is the cycle time interval.

[0068] After obtaining the predicted power value, the wind farm receives a frequency regulation command corresponding to the power value at the next moment. Based on the expected power value in the frequency regulation command and the power value at the next moment, the expected compensation power value of the energy storage system in the wind farm is calculated. The compensation benefit is calculated based on the expected compensation power value of the energy storage system and the expected power value in the frequency regulation command. The power value at the next moment is adjusted according to the compensation benefit. The energy storage system is controlled according to the adjusted predicted power value at the next moment to optimize the benefit result.

[0069] Specifically, the benefits of an energy storage system participating in a primary frequency regulation are:

[0070]

[0071] In the formula, A 1 represents the revenue of the energy storage system after participating in primary frequency regulation. M The unit price for revenue from energy storage systems participating in primary frequency regulation. P c1The power required to participate in frequency modulation, where t is the frequency modulation time.

[0072] The total compensation benefit based on the expected compensation power value of the energy storage system is:

[0073]

[0074] In the formula, A 2 represents the total compensation revenue obtained by the energy storage system through power compensation. N The cost that the energy storage system needs to participate in when a wind farm meets the revenue assessment criteria. P c2 This represents the expected compensation power value of the energy storage system. t This refers to the frequency modulation time.

[0075] The process involves determining whether the current maximum output power of the energy storage system is less than the expected compensation power value. If the maximum output power of the overcapacity energy storage system is greater than the expected compensation power value, no correction is needed for the predicted power value; instead, the expected compensation power value calculated in this instance is used for compensation. If the maximum output power of the energy storage system is less than the expected compensation power value, the prediction result is adjusted by re-predicting using the corrected prediction model. Based on this adjusted result, the expected compensation power value of the energy storage system is adjusted, and the total compensation revenue is calculated. The total compensation revenue for the wind farm is maximized when the total revenue of the wind farm is at its maximum (i.e., the revenue after the energy storage system participates in one frequency regulation). A 1. Total compensation benefit based on the expected compensation power value of the energy storage system A If the sum of 2 is used, then the adjusted expected compensation power value of the energy storage system will be used for control.

[0076] To demonstrate the practicality of the method, let's take a 100-year-old man from northern China as an example. MW The application focuses on grid-connected wind farms, with the goal of achieving [the goal] at 10:00 AM on May 10th of a certain year (referred to as [date]). m The wind farm output power prediction and overcapacity energy storage power compensation at any given time are based on the following core parameters:

[0077] First, historical wind farm output power data is acquired using a wind farm power sensor with an accuracy of 0.5 and a time synchronization device. The time resolution of this historical wind farm output power data is 15. thousand Obtain data from 0 to 72 hours. Covers the prediction timeframe. m The historical wind farm output power data can also be obtained from the wind farm itself. (The data covers at least the previous 20 moments.) SCADA Retrieved from the system's historical database.

[0078] Based on industry standards and wind farm assessment documents, determine the revenue parameters. M ,N .in, M It is 0.8 million yuan / ( MW h When a wind farm meets the revenue assessment criteria, the energy storage compensation fee is converted into revenue. N =05,000 yuan / ( MW h ); Parameters of the supercapacity energy storage system: Current maximum output power Pmax= 2 MW Frequency modulation response time ≤ 1 s .

[0079] According to Example 1 n The method for determining this is by comparing different i The predicted power deviation under the value satisfies the discrimination condition ( |y 1 -y 2 | / y 2 ≤ 5 % When a threshold is reasonably set to balance accuracy and computational load, it is determined that... n The specific calculations are as follows:

[0080] Initial calculation: i =2 (i.e.) n =2, use m -1、 m (Data at time -2), the uncorrected prediction model output is: y 1 = 94.66 MW .

[0081] Second trial calculation: i =3 (i.e.) n =3, use m- 1 、m- 2 、m- (Data from time 3), the uncorrected prediction model output includes: y 2 = 94.3 MW .

[0082] Deviation percentage: |y 1 –y 2 | / y 2 =| 94.66-94.3 | / 94.3 ≈ 0.38 %≤ 5 % If the discrimination condition is met, then the total number of historical data is determined as follows: n =2; that is, adopting m -1、 m Using the data at time -2 as the prediction input balances accuracy and computational efficiency.

[0083] Based on the model correction formula based on revenue per unit price in Example 1, revenue parameters are introduced. M、N With cyclic correction ( T =30 times, cycle time interval Δt =1 thousand ), calculate the correction factor b 1 = 0.53 b 2 = 0.47. Corrected predicted power y` m 96.59 MW .

[0084] The power grid issues frequency regulation commands based on load demand, including the desired power value. P ref =98 MW That is, the wind farm is required to m The output power is always stable at 98 MW Therefore, the expected compensation power is... P c2 It is 1.41 MW Based on the formula in Example 1, it is assumed that the energy storage participates in the primary frequency regulation power. P 1 = 1MW, frequency modulation time t =1 h So, the benefit of one frequency modulation A 1 is 0.8 million yuan. Compensation income. A 2 is 0.705 million yuan. Therefore, the total profit is 1.505 million yuan.

[0085] The energy storage system can currently output maximum power. Pmax= 2 MW Comparison with expected compensation power P c2 = 1.41 MW .because Pmax （ 2 MW)≥Pc 2 （ 1.41 MW) The maximum output power of the energy storage system itself meets the compensation requirements, and there is no need to adjust the predicted power; if the maximum power Pmax <P c2 Then the prediction model needs to be revised (reduced) y' m ), until P c2 ≤Pmax And recalculate the total revenue to ensure maximum return.

[0086] The wind farm control system sends instructions to the supercapacity energy storage system: m At 10:00, the output compensation power is 1.41. MWThe power output of the wind farm itself (predicted 96.59) MW After superposition, the total output power stabilizes at 98. MW This meets the frequency regulation requirements of the power grid.

[0087] This embodiment also compares the prediction method used here with a general prediction method and with a method that does not use energy storage compensation. The mean absolute error percentage (MAE) is used. MAPE, Mean Absolute Percentage Error The analysis was performed, and the results are shown in Table 1:

[0088] Table 1 Comparison results between this method and existing technologies

[0089]

[0090] As shown in Table 1, the prediction method in this embodiment has an error percentage of only 12.4%, which is more accurate than other prediction methods. It also boasts higher economic efficiency.

[0091] Example 2

[0092] A supercapacitive energy storage power compensation system, used to implement the supercapacitive energy storage power compensation method in Example 1, includes:

[0093] The data acquisition module is used to obtain the actual output power value of the wind farm at historical moments;

[0094] The power prediction module is used to input the output power data of the wind farm at historical moments into the prediction model to obtain the predicted power value at the next moment.

[0095] The power compensation module is used to obtain the frequency regulation command corresponding to the power value at the next moment, calculate the expected compensation power value of the energy storage system in the wind farm based on the expected power value in the frequency regulation command and the power value at the next moment, calculate the compensation benefit based on the expected compensation power value of the energy storage system and the expected power value in the frequency regulation command, and optimize the benefit by adjusting the prediction results.

[0096] Furthermore, if the maximum output power of the supercapacity energy storage system is greater than the expected compensation power value of the energy storage system, then there is no need to correct the predicted power value at this time, and the expected compensation power value of the energy storage system calculated in this instance is used for compensation. If the maximum output power of the energy storage system is less than the expected compensation power value of the energy storage system, the prediction result is adjusted by using the corrected prediction model to make another prediction, obtaining the corrected prediction result, adjusting the expected compensation power value of the energy storage system based on the corrected result, and then calculating the total compensation benefit based on the adjusted expected compensation power value of the energy storage system. When the total benefit of the wind farm is maximized (i.e., the sum of the benefit of the energy storage system participating in primary frequency regulation and the total compensation benefit based on the expected compensation power value of the energy storage system), then the adjusted expected compensation power value of the energy storage system is used for control.

[0097] The prediction model in this embodiment is:

[0098]

[0099] In the formula, These are the prediction coefficients corresponding to each time point. for is The output power data of the wind farm at any given time. For two power time intervals, n The prediction coefficient is the total amount of historical time data used for prediction.

[0100]

[0101] In the formula, August ( ) represents the arithmetic mean. for thousand The actual power value at that moment, for m -( n The actual power value at time +1), for m- 1 hour to m- The interval between 2 moments, for m -2 o'clock to m The interval of -4 seconds, for thousand Time to m -( n +3) The time interval, n >2.

[0102] In addition, this embodiment also includes a power correction module, which is used to correct the prediction model. The corresponding correction formula is as follows:

[0103]

[0104] In the formula, y m For the first m Predicted power value at time 10:00 For the first i The correction factor corresponding to time . for is The output power data of the wind farm at any given time. For two power time intervals, the correction factor satisfy:

[0105]

[0106] In the formula, T The number of loops.T =30, This is the cycle time interval.

[0107] In this embodiment, the benefit of participating in primary frequency regulation based on the energy storage system is:

[0108]

[0109] In the formula, A 1 represents the total revenue after the energy storage system participates in primary frequency regulation. M The unit price for revenue from energy storage systems participating in primary frequency regulation. P c1 The power required to participate in frequency modulation.

[0110] The total compensation benefit based on the expected compensation power value of the energy storage system is:

[0111]

[0112] In the formula, A 2 represents the total compensation benefit. N The cost that the energy storage system needs to participate in when a wind farm meets the revenue assessment criteria. P c2 This represents the expected compensation power value for the energy storage system.

[0113] Example 3

[0114] like Figure 2 The embodiment shown provides an electronic device for implementing the supercapacitive energy storage power compensation method in Embodiment 1. The electronic device 100 includes at least one processor 102, a memory 101, a computer program 103 stored in the memory 101 and executable on at least one processor 102, and at least one communication bus 104. The memory 101 can be used to store the computer program 103. The processor 102 implements the steps of the supercapacitive energy storage power compensation method of Embodiment 1 by running or executing the computer program stored in the memory 101 and by calling data stored in the memory 101. The memory 101 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created based on the use of the electronic device 100 (such as audio data), etc. In addition, memory 101 may include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other non-volatile solid-state storage device.

[0115] At least one processor 102 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Processor 102 may be a microprocessor or any conventional processor. Processor 102 is the control center of electronic device 100, connecting various parts of electronic device 100 via various interfaces and lines.

[0116] The memory 101 in the electronic device 100 stores multiple instructions to implement a supercapacitive energy storage power compensation method, and the processor 102 can execute multiple instructions to achieve the following:

[0117] The system acquires historical wind farm output power data; inputs this data into a prediction model to obtain the predicted power value for the next moment; generates a frequency regulation command based on the power value for the next moment, calculates the expected compensation power value for the energy storage system in the wind farm based on the expected compensation power value of the energy storage system and the expected power value in the frequency regulation command; calculates the compensation benefit based on the expected compensation power value of the energy storage system and the expected power value in the frequency regulation command, adjusts the predicted power value for the next moment based on the compensation benefit, and controls the energy storage system based on the adjusted predicted power value for the next moment.

[0118] The prediction model is:

[0119]

[0120] In the formula, For the first m Predicted power value at time 10:00 For the first i The prediction coefficient corresponding to time 1. for The output power data of the wind farm at any given time. The time interval between two power levels. The total amount of historical data used for prediction is given, and the prediction coefficients are derived from the actual historical power values.

[0121] Example 4

[0122] If the modules / units integrated in the electronic device 100 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying computer program code, a recording medium, etc. U Disks, external hard drives, magnetic disks, optical disks, computer storage devices, and read-only memory (ROMs) ROM, Read OnlyMemory ).

[0123] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0124] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0125] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0126] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the protection scope of the present invention.

Claims

1. A method for compensating the power of supercapacity energy storage, characterized in that, include: Obtain historical data on the output power of wind farms; Input the historical wind farm output power data into the prediction model to obtain the predicted power value for the next moment; The frequency regulation command is obtained based on the predicted power value at the next moment. The expected compensation power value of the energy storage system in the wind farm is calculated based on the expected power value in the frequency regulation command and the predicted power value at the next moment. The compensation benefit is calculated based on the expected compensation power value of the energy storage system and the expected power value in the frequency regulation command. The predicted power value at the next moment is adjusted according to the compensation benefit, and the energy storage system is controlled according to the adjusted predicted power value at the next moment. The prediction model is as follows: In the formula, For the first m Predicted power value at time 10:00 For the first i The prediction coefficient corresponding to time 1. for The output power data of the wind farm at any given time. The time interval between two power levels. The prediction coefficients are derived from the actual historical power values, representing the total amount of historical data used for prediction.

2. The supercapacity energy storage power compensation method according to claim 1, characterized in that, The calculation of compensation benefits based on the expected compensation power value of the energy storage system and the expected power value in the frequency regulation command, and the adjustment of the predicted power value for the next moment based on the compensation benefits, specifically includes: If the maximum output power of the energy storage system is less than the expected compensation power value, the predicted power value for the next moment is adjusted according to the compensation benefit. Then, the expected compensation power value of the energy storage system is adjusted according to the adjusted power value. Finally, the total compensation benefit is calculated based on the adjusted expected compensation power value of the energy storage system to maximize the total benefit of the wind farm. If not, the energy storage system is controlled according to the current predicted power value. The total benefit is the sum of the total compensation benefit of the expected compensation power value and the benefit of the energy storage system participating in primary frequency regulation.

3. The supercapacity energy storage power compensation method according to claim 1, characterized in that, The prediction coefficients are as follows: In the formula, avg ( ) represents the arithmetic mean. for mn The actual power value at that moment, for m- ( n+ 1) The actual power value at time t, for m- 1 hour to m The interval of -2 seconds, for m -2 o'clock to m The interval of -4 seconds, for mn Time to m -( n +3) The time interval, n >2.

4. The supercapacity energy storage power compensation method according to claim 3, characterized in that, After constructing the prediction model based on the prediction coefficients, the model is further corrected based on the revenue per unit price of the wind farm. The corrected prediction model is as follows: In the formula, For the first m Predicted power value at time 10:00 These are the correction factors corresponding to each time point. for mi The output power data of the wind farm at any given time. The time interval between two power levels. n The total amount of historical time data used for prediction. The unit price for revenue from energy storage systems participating in primary frequency regulation. The correction factor is used to compensate for the costs incurred by the energy storage system when a wind farm meets the revenue assessment criteria. satisfy: In the formula, T The number of loops. The time interval is the cycle time. n This represents the total amount of historical time data used for prediction.

5. The supercapacity energy storage power compensation method according to claim 3 or 4, characterized in that, Total number of historical moment data predicted n The method for determining is as follows: obtain respectively mi Time and m -( i +1) All output power values ​​corresponding to time 1, based on m Before the moment i All output power values ​​at each time point are used to predict the output power values ​​using a prediction model. m The first predicted power value at time t, based on m Before the moment i The output power values ​​at time +1 are used to predict the output power values ​​using a prediction model. m The second predicted power value at time t, if the first predicted power value and the second predicted power value satisfy the discrimination condition, then... m Before the moment i The total number of historical time data corresponding to each time point is used as the total number of data points for prediction. The discrimination condition is: In the formula, The first predicted power value, This is the second predicted power value.

6. The supercapacity energy storage power compensation method according to claim 2, characterized in that, The benefit of the energy storage system participating in a primary frequency regulation is: In the formula, A 1 represents the revenue of the energy storage system after participating in primary frequency regulation. M The unit price for revenue from energy storage systems participating in primary frequency regulation. P c1 The power required to participate in frequency modulation t This refers to the frequency modulation time.

7. The supercapacity energy storage power compensation method according to claim 2, characterized in that, The total compensation benefit of the energy storage system for the expected compensation power value is: In the formula, A 2 represents the total compensation revenue obtained by the energy storage system through power compensation. N The cost that the energy storage system needs to participate in when a wind farm meets the revenue assessment criteria. P c2 This represents the expected compensation power value of the energy storage system. t This refers to the frequency modulation time.

8. A supercapacity energy storage power compensation system, characterized in that, include: The data acquisition module is used to obtain the actual output power value of the wind farm at historical moments; The power prediction module is used to input the output power data of the wind farm at historical moments into the prediction model to obtain the predicted power value at the next moment. The power compensation module is used to obtain the frequency regulation command corresponding to the predicted power value at the next moment, calculate the expected compensation power value of the energy storage system in the wind farm based on the expected power value in the frequency regulation command and the predicted power value at the next moment, calculate the compensation benefit based on the expected compensation power value of the energy storage system and the expected power value in the frequency regulation command, and optimize the benefit by adjusting the prediction results. The prediction model is as follows: In the formula, For the first m Predicted power value at time 10:00 For the first i The prediction coefficient corresponding to time 1. for The output power data of the wind farm at any given time. The time interval between two power levels. The prediction coefficients are derived from the actual historical power values, representing the total amount of historical data used for prediction.

9. An electronic device, characterized in that, It includes a processor and a memory, the processor being used to execute a computer program stored in the memory to implement the supercapacitive energy storage power compensation method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one instruction, which, when executed by a processor, implements the supercapacitive energy storage power compensation method as described in any one of claims 1-7.

Images