Optimization methods, equipment, media, and program products for supercapacitor energy storage and frequency modulation

Abstract

The present invention discloses an optimization method, device, medium, and program product for supercapacitor energy storage and frequency modulation, and belongs to the field of wind power generation technology. The method provided by the present invention traverses the wind speed sequence, identifies and merges subsequences with similar trends, thereby improving the accuracy of the prediction; at the same time, the method includes an intelligent judgment mechanism. When it is judged that the merging result has an over-merging phenomenon, the wind speed sequence is split and the prediction and error evaluation are re-performed, and the prediction error is further reduced by adjusting the data structure in the wind speed sequence. The method of the present invention can effectively improve the accuracy of wind speed prediction and reduce the prediction error, thereby optimizing the coordinated operation capability between the wind farm and the power grid, and improving the stability and reliability of the power system. In addition, the method is also combined with the rapid response capability of the supercapacitor energy storage system, which can make up for the error between the actual power output of the wind farm and the predicted power, and further improve the credibility of the power grid dispatch.

Description

Technical Field

[0001] The present invention relates to the technical field of wind power generation, and in particular to an optimization method, equipment, medium and program product for supercapacitor energy storage and frequency modulation. Background Art

[0002] Wind power generation, a clean, environmentally friendly and sustainable renewable energy technology, has won wide attention and achieved vigorous development in recent years around the world. With the rapid advancement of technology and the continuous decline in costs, wind power generation has gradually become an indispensable and important part of the energy structure of many countries. However, the randomness and volatility of wind in nature make wind power have a significant impact on the power system during the grid connection process. In order to effectively meet this challenge, it is particularly important to accurately predict wind speed and reduce the impact of wind power on the power grid through optimized scheduling and other means.

[0003] However, the natural randomness of wind speed poses a huge challenge to the grid connection of large-scale wind farms. This randomness causes the output power of wind farms to show significant volatility and uncertainty, greatly increasing the difficulty of prediction and scheduling for power grid dispatching agencies. This not only increases the operating burden of the power grid, but also poses a potential risk to the stability of the power system.

[0004] As a core technology in the field of wind power generation, the accuracy and reliability of wind speed prediction are crucial to the grid connection and dispatching of wind power. However, traditional prediction methods often directly input the original wind speed sequence into the neural network for prediction. Due to the complex nonlinear characteristics of the meteorological system, it is difficult to accurately predict the wind speed sequence. At present, the error rate of wind speed data prediction is still high, even reaching 25%-40%. Therefore, conducting effective wind speed prediction research has important theoretical value and practical significance.

[0005] Existing studies have shown that wind speed has complex nonlinear characteristics and may exhibit chaotic characteristics. By calculating the Lyapunov exponent of the wind speed sequence, it is possible to determine whether it has chaotic characteristics. Since the phase space of a chaotic system has a fractal structure and exhibits self-similarity, a wind speed sequence with chaotic characteristics usually also has the characteristics of fractal dimension and self-similarity.

[0006] Therefore, how to perform similarity processing on the original wind speed data to improve the accuracy and reliability of wind speed prediction has become a key technical problem that needs to be urgently solved by technicians in this field. Summary of the invention

[0007] The purpose of the present invention is to provide a method, device, medium and program product for optimizing supercapacitor energy storage frequency modulation, aiming to fundamentally solve the problem of large error and low accuracy caused by directly predicting the original wind speed sequence.

[0008] The present invention solves the above technical problems through the following technical solutions:

[0009] A method for optimizing supercapacitor energy storage frequency modulation comprises the following steps:

[0010] Step 1: Collect wind speed data and establish an original wind speed sequence; divide the original wind speed sequence into a prediction set wind speed sequence and a verification set wind speed sequence according to a preset ratio; input the prediction set wind speed sequence into a trained neural network model for prediction to obtain a first prediction value, and calculate a benchmark prediction error W based on the first prediction value and the actual value in the verification set wind speed sequence;

[0011] Step 2: traverse the wind speed sequence of the forecast set, construct continuous subsequences, and mark all continuous subsequences with similar trends; determine whether there is a similar trend mark in the wind speed sequence of the forecast set. If the judgment result is yes, execute step 3; if the judgment result is no, execute step 4;

[0012] Step 3: merge the continuous subsequences with trend similarity marks to obtain the merged forecast set wind speed sequence, traverse the merged forecast set wind speed sequence, mark its continuous subsequences with trend similarity, and determine whether the merged forecast set wind speed sequence has trend similarity marks. If the judgment result is yes, execute step 3 again; if the judgment result is no, execute step 4;

[0013] Step 4: Input the wind speed sequence of the current prediction set into the trained neural network model for prediction to obtain the wind speed prediction value of this round. Based on the wind speed prediction value of this round and the actual value in the wind speed sequence of the verification set, calculate the prediction error w;

[0014] Step 5: Determine whether the prediction error w is greater than or equal to the benchmark prediction error W. If the judgment result is yes, execute step 6; if the judgment result is no, combine the wind speed sequence of the current prediction set and the wind speed prediction value of this round to obtain the final wind speed prediction sequence, substitute the final wind speed prediction sequence into the trained neural network model for prediction, obtain the final wind speed prediction result, and execute step 7;

[0015] Step 6: split the current prediction set wind speed sequence to obtain a split prediction set wind speed sequence, use the split prediction set wind speed sequence as the current prediction set wind speed sequence, and execute step 4;

[0016] Step 7. Calculate the predicted power sent by the wind farm to the grid based on the final wind speed prediction result, obtain the actual power sent by the wind farm to the grid, and calculate the difference between the predicted power and the actual power. When the difference is positive, adjust the super-capacity energy storage system connected to the wind farm exit to the charging state; when the difference is 0, the super-capacity energy storage system connected to the wind farm exit maintains the current state unchanged; when the difference is negative, adjust the super-capacity energy storage system connected to the wind farm exit to the discharging state.

[0017] A further improvement of the present invention is that: the wind speed sequence of the prediction set is traversed, continuous subsequences are constructed, and all continuous subsequences are marked with trend similarity, which specifically includes the following steps:

[0018] Assume that the wind speed sequence of the forecast set is x(t)=[x1,x2,x3,...,x N ], N is the number of subsequences in the wind speed sequence of the prediction set, x1,x2,x3,...,x N are the 1st, 2nd, 3rd, ..., Nth subsequences in the wind speed sequence of the prediction set; construct continuous subsequences, and the first subsequences of the continuous subsequences are x1~x N-2 , x N-2 It is the N-2th subsequence in the wind speed sequence of the prediction set; the number of subsequences contained in the continuous subsequence is 3~N, and a trend similarity judgment is performed on each continuous subsequence. If the judgment is yes, the continuous subsequence is marked as trend similar; if the judgment is no, no processing is performed.

[0019] A further improvement of the present invention is that the trend similarity judgment comprises the following steps:

[0020] Determine whether the continuous subsequence satisfies both condition 1 and condition 2. If so, the continuous subsequence is trend-similar; if not, the continuous subsequence is non-trend-similar.

[0021] Condition one:

[0022] ≤Max

[0023] Where Max is the maximum value of the subsequence in the continuous subsequence; Min is the minimum value of the subsequence in the continuous subsequence; E is the maximum absolute value of the difference between any two subsequences in the continuous subsequence;

[0024] Condition two:

[0025] ≤

[0026] Among them, Sin max is the maximum sine value of the subsequence in the continuous subsequence; Cos minis the minimum cosine of the subsequence in the continuous subsequence.

[0027] A further improvement of the present invention is to merge consecutive subsequences with similar trend markers, specifically:

[0028]

[0029] Among them, X i is the merged subsequence; x i is the first subsequence in the continuous subsequences with trend-similar marks; i is the position of the first subsequence in the continuous subsequences with trend-similar marks in the current wind speed sequence; c is the number of subsequences contained in the continuous subsequences with trend-similar marks; tanh() is the activation function; min() is the minimum function; e is a natural constant.

[0030] A further improvement of the present invention is that when merging consecutive subsequences with trend-similar markers, the following rules are adopted:

[0031] When there is only one continuous subsequence with a similar trend mark, the continuous subsequence is directly merged;

[0032] When there are two or more continuous subsequences with trend-similar markers, and there is no identical subsequence among all continuous subsequences, merge all continuous subsequences separately;

[0033] When there are two or more continuous subsequences with trend-similar marks, and at least one subsequence is identical between any two continuous subsequences, the continuous subsequence with trend-similar marks whose first subsequence has the lowest ranking is preferentially merged; if there are two or more continuous subsequences with trend-similar marks whose first subsequence has the lowest ranking is preferentially merged, the continuous subsequence with trend-similar marks containing the largest number of subsequences is preferentially merged.

[0034] A further improvement of the present invention is that the splitting process is to split a subsequence into two subsequences, specifically:

[0035]

[0036]

[0037] Among them, h i is the subsequence of the current wind speed sequence to be split; H i1 , H i2 h i The two subsequences after splitting; sigmoid() is the activation function; gelu() is the Gaussian error linear unit activation function; e is a natural constant; sin() is the sine function.

[0038] A further improvement of the present invention is that the reference prediction error W is specifically:

[0039]

[0040] Among them, y i is the i-th first prediction value, i is the i-th actual value in the wind speed sequence of the validation set, and n is the number of subsequences in the wind speed sequence of the validation set.

[0041] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the steps of the above method are implemented when the processor executes the program.

[0042] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the above method are implemented.

[0043] The present invention also provides a computer program product, comprising a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0044] Compared with the prior art, the positive and progressive effects of the present invention are:

[0045] The optimization method of supercapacitor energy storage frequency modulation provided by the present invention traverses the wind speed sequence, identifies and merges subsequences with similar trends, thereby improving the accuracy of the prediction; at the same time, the method includes an intelligent judgment mechanism. When it is judged that the merging result has an over-merging phenomenon, the wind speed sequence is split and the prediction and error evaluation are re-performed, and the prediction error is further reduced by adjusting the data structure in the wind speed sequence. The method of the present invention can effectively improve the accuracy of wind speed prediction and reduce the prediction error, thereby optimizing the coordinated operation ability between the wind farm and the power grid, and improving the stability and reliability of the power system. In addition, the method is also combined with the rapid response capability of the supercapacitor energy storage system, which can make up for the error between the actual power output of the wind farm and the predicted power, and further improve the credibility of the power grid dispatch. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The drawings in the specification are used to provide further understanding of the present invention and constitute a part of the present invention. The schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0047] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0049] In the description of the present invention, it should be understood that the terms “include” and “comprises” indicate the presence of described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or collections thereof.

[0050] It should also be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, the singular forms "a", "an" and "the" are intended to include plural forms unless the context clearly indicates otherwise.

[0051] It should be understood that, although the terms first, second, third, etc. may be used to describe preset ranges, etc. in the embodiments of the present invention, these preset ranges should not be limited to these terms. These terms are only used to distinguish preset ranges from each other. For example, without departing from the scope of the embodiments of the present invention, the first preset range may also be referred to as the second preset range, and similarly, the second preset range may also be referred to as the first preset range.

[0052] The word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)", depending on the context.

[0053] Various structural schematic diagrams of the embodiments disclosed in the present invention are shown in the accompanying drawings. These figures are not drawn to scale, and some details are magnified and some details may be omitted for the purpose of clear expression. The shapes of various regions and layers shown in the figures and the relative sizes and positional relationships therebetween are only exemplary, and may deviate in practice due to manufacturing tolerances or technical limitations, and those skilled in the art may additionally design regions / layers with different shapes, sizes, and relative positions according to actual needs.

[0054] The present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments, which are intended to explain the present invention rather than to limit it.

[0055] See also Figure 1 , a supercapacitor energy storage frequency modulation optimization method, comprising the following steps:

[0056] Step 1: Collect wind speed data and establish an original wind speed sequence; divide the original wind speed sequence into a prediction set wind speed sequence and a verification set wind speed sequence according to a preset ratio; input the prediction set wind speed sequence into a trained neural network model for prediction to obtain a first prediction value, and calculate a benchmark prediction error W based on the first prediction value and the actual value in the verification set wind speed sequence;

[0057] Step 2: traverse the wind speed sequence of the forecast set, construct continuous subsequences, and mark all continuous subsequences with similar trends; determine whether there is a similar trend mark in the wind speed sequence of the forecast set. If the judgment result is yes, execute step 3; if the judgment result is no, execute step 4;

[0058] Step 3: merge the continuous subsequences with trend similarity marks to obtain the merged forecast set wind speed sequence, traverse the merged forecast set wind speed sequence, mark its continuous subsequences with trend similarity, and determine whether the merged forecast set wind speed sequence has trend similarity marks. If the judgment result is yes, execute step 3 again; if the judgment result is no, execute step 4;

[0059] Step 4: Input the wind speed sequence of the current prediction set into the trained neural network model for prediction to obtain the wind speed prediction value of this round. Based on the wind speed prediction value of this round and the actual value in the wind speed sequence of the verification set, calculate the prediction error w;

[0060] Step 5: Determine whether the prediction error w is greater than or equal to the benchmark prediction error W. If the judgment result is yes, execute step 6; if the judgment result is no, combine the wind speed sequence of the current prediction set and the wind speed prediction value of this round to obtain the final wind speed prediction sequence, substitute the final wind speed prediction sequence into the trained neural network model for prediction, obtain the final wind speed prediction result, and execute step 7;

[0061] Step 6: split the current prediction set wind speed sequence to obtain a split prediction set wind speed sequence, use the split prediction set wind speed sequence as the current prediction set wind speed sequence, and execute step 4;

[0062] Step 7. Calculate the predicted power sent by the wind farm to the grid based on the final wind speed prediction result, obtain the actual power sent by the wind farm to the grid, and calculate the difference between the predicted power and the actual power. When the difference is positive, adjust the super-capacity energy storage system connected to the wind farm exit to the charging state; when the difference is 0, the super-capacity energy storage system connected to the wind farm exit maintains the current state unchanged; when the difference is negative, adjust the super-capacity energy storage system connected to the wind farm exit to the discharging state.

[0063] The optimization method of supercapacitor energy storage frequency modulation provided by the present invention traverses the wind speed sequence, identifies and merges subsequences with similar trends, thereby improving the accuracy of the prediction; at the same time, the method includes an intelligent judgment mechanism. When it is judged that the merging result has an over-merging phenomenon, the wind speed sequence is split and the prediction and error evaluation are re-performed, and the prediction error is further reduced by adjusting the data structure in the wind speed sequence. The method of the present invention can effectively improve the accuracy of wind speed prediction and reduce the prediction error, thereby optimizing the coordinated operation ability between the wind farm and the power grid, and improving the stability and reliability of the power system. In addition, the method is also combined with the rapid response capability of the supercapacitor energy storage system, which can make up for the error between the actual power output of the wind farm and the predicted power, and further improve the credibility of the power grid dispatch.

[0064] Specifically, the wind speed sequence of the forecast set is traversed, continuous subsequences are constructed, and all continuous subsequences are marked with trend similarity, which specifically includes the following steps:

[0065] Assume that the wind speed sequence of the forecast set is x(t)=[x1,x2,x3,...,x N ], N is the number of subsequences in the wind speed sequence of the prediction set, x1,x2,x3,...,x N are the 1st, 2nd, 3rd, ..., Nth subsequences in the wind speed sequence of the prediction set; construct continuous subsequences, and the first subsequences of the continuous subsequences are x1~x N-2 , x N-2 It is the N-2th subsequence in the wind speed sequence of the prediction set; the number of subsequences contained in the continuous subsequence is 3~N, and a trend similarity judgment is performed on each continuous subsequence. If the judgment is yes, the continuous subsequence is marked as trend similar; if the judgment is no, no processing is performed.

[0066] In a specific embodiment of the present invention, the prediction set wind speed sequence x(t)=[x1,x2,x3,x4,x5,x6] is assumed, and x1,x2,x3,x4,x5,x6 are the 1st, 2nd, 3rd, 4th, 5th, and 6th subsequences in the prediction set wind speed sequence respectively; a continuous subsequence is constructed, and the first subsequence of the continuous subsequence is x1~x4 respectively, and the number of subsequences included in the continuous subsequence is 3~6. Specifically, the prediction set wind speed sequence includes the following continuous subsequences:

[0067] x1,x2,x3,x1,x2,x3,x4,x1,x2,x3,x4,x5,x1,x2,x3,x4,x5,x6;

[0068] x2,x3,x4,x2,x3,x4,x5,x2,x3,x4,x5,x6;

[0069] x3,x4,x5,x3,x4,x5,x6;

[0070] x4,x5,x6;

[0071] The above continuous subsequences are respectively judged to be trend similar. If the judgment is yes, the continuous subsequence is marked as trend similar; if the judgment is no, no processing is performed.

[0072] Specifically, trend similarity judgment includes the following steps:

[0073] Determine whether the continuous subsequence satisfies both condition 1 and condition 2. If so, the continuous subsequence is trend-similar; if not, the continuous subsequence is non-trend-similar.

[0074] Condition one:

[0075] ≤Max

[0076] Where Max is the maximum value of the subsequence in the continuous subsequence; Min is the minimum value of the subsequence in the continuous subsequence; E is the maximum absolute value of the difference between any two subsequences in the continuous subsequence;

[0077] Condition two:

[0078] ≤

[0079] Among them, Sin max is the maximum sine value of the subsequence in the continuous subsequence; Cos min is the minimum cosine of the subsequence in the continuous subsequence.

[0080] Specifically, continuous subsequences with similar trend markers are merged, specifically:

[0081]

[0082] Among them, X i is the merged subsequence; x iis the first subsequence in the continuous subsequences with trend-similar marks; i is the position of the first subsequence in the continuous subsequences with trend-similar marks in the current wind speed sequence; c is the number of subsequences contained in the continuous subsequences with trend-similar marks; tanh() is the activation function; min() is the minimum function; e is a natural constant.

[0083] Specifically, when merging consecutive subsequences with similar trend markers, the following rules are used:

[0084] When there is only one continuous subsequence with a similar trend mark, the continuous subsequence is directly merged;

[0085] When there are two or more continuous subsequences with trend-similar markers, and there is no identical subsequence among all continuous subsequences, merge all continuous subsequences separately;

[0086] When there are two or more continuous subsequences with trend-similar marks, and at least one subsequence is identical between any two continuous subsequences, the continuous subsequence with trend-similar marks whose first subsequence has the lowest ranking is preferentially merged; if there are two or more continuous subsequences with trend-similar marks whose first subsequence has the lowest ranking is preferentially merged, the continuous subsequence with trend-similar marks containing the largest number of subsequences is preferentially merged.

[0087] In a specific embodiment of the present invention, in the prediction set wind speed sequence x(t)=[x1,x2,x3,x4,x5,x6], assuming that the continuous subsequences with similar trends are only x1, x2, x3, then the continuous subsequences are directly merged to obtain A, and the merged prediction set wind speed sequence = [A,x4,x5,x6].

[0088] In a specific embodiment of the present invention, in the prediction set wind speed sequence x(t)=[x1,x2,x3,x4,x5,x6], it is assumed that continuous subsequences with similar trends include x1,x2,x3,x4,x5,x6; all continuous subsequences are merged respectively to obtain A and B, and the merged prediction set wind speed sequence = [A,B].

[0089] In a specific embodiment of the present invention, in the prediction set wind speed sequence x(t)=[x1,x2,x3,x4,x5,x6], suppose that continuous subsequences with similar trends include x2,x3,x4, x4,x5,x6; the continuous subsequence with the lowest ranking of the first subsequence is x2,x3,x4, which are merged to obtain A, and the merged prediction set wind speed sequence = [x1,A,x5,x6].

[0090] In a specific embodiment of the present invention, in the prediction set wind speed sequence x(t)=[x1,x2,x3,x4,x5,x6], suppose that continuous subsequences with similar trends include x1,x2,x3, x1,x2,x3,x4; the trend-similar continuous subsequence containing the largest number of subsequences is x1,x2,x3,x4, which are merged to obtain A, and the merged prediction set wind speed sequence = [A,x5,x6].

[0091] Specifically, the splitting process is to split a subsequence into two subsequences, specifically:

[0092]

[0093]

[0094] Among them, h i is the subsequence of the current wind speed sequence to be split; H i1 , H i2 h i The two subsequences after splitting; sigmoid() is the activation function; gelu() is the Gaussian error linear unit activation function; e is the benchmark prediction error W, which is:

[0095]

[0096] Among them, y i is the i-th first prediction value, i is the i-th actual value in the wind speed sequence of the validation set, and n is the number of subsequences in the wind speed sequence of the validation set.

[0097] In a specific embodiment of the present invention, after collecting wind speed data, the following steps are also included: deleting and supplementing abnormal data; the neural network model is LSTM (Long Short-Term Memory); when the original wind speed sequence is divided into a prediction set wind speed sequence and a verification set wind speed sequence according to a preset ratio, the preset ratio is 9:1.

[0098] In order to further verify the advantages of this method, the wind speed is predicted by using the method of this application and the traditional prediction method VMD (Variational Mode Decomposition). In the experiment of this application, MAPE (Mean Absolute Percentage Error) is selected as the evaluation standard of each model. The prediction results (i.e., MAPE values) are as follows:

[0099]

[0100] It can be seen that the use of this method reduces the prediction error, and the wind speed prediction is more accurate and reliable.

[0101] Based on the same inventive concept, an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the optimization method of supercapacitor energy storage frequency modulation when executing the computer program, wherein the memory may include a memory, such as a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk memory, etc.; the processor, the network interface, and the memory are interconnected through an internal bus, and the internal bus may be an industrial standard architecture bus, a peripheral component interconnection standard bus, an extended industrial standard structure bus, etc., and the bus may be divided into an address bus, a data bus, a control bus, etc. The memory is used to store programs, and specifically, the program may include a program code, and the program code includes computer operation instructions. The memory may include a memory and a non-volatile memory, and provide instructions and data to the processor.

[0102] Based on the same inventive concept, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps of the optimization method of supercapacitor energy storage frequency modulation are implemented. Specifically, the computer-readable storage medium includes, but is not limited to, for example, volatile memory and / or non-volatile memory. The volatile memory may include RAM (Random Access Memory) and / or cache memory (cache), etc. The non-volatile memory may include ROM (Read-Only Memory), hard disk, flash memory, optical disk, magnetic disk, etc.

[0103] Based on the same inventive concept, an embodiment of the present application provides a computer program product, which includes a computer program stored on a computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer device, the computer device executes the steps of the above-mentioned supercapacitor energy storage frequency modulation optimization method.

[0104] It should be understood by those skilled in the art that the embodiments of the present invention may be provided as methods or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM (Compact Disc Read-Only Memory), optical storage, etc.) containing computer-usable program codes.

[0105] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer device or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0106] These computer program instructions may also be stored in a computer readable memory capable of directing a computer device or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0107] These computer program instructions can also be loaded onto a computer device or other programmable data processing device so that a series of operation steps are executed on the computer device or other programmable device to produce a process implemented by the computer device, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0108] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0109] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for optimizing supercapacitor energy storage frequency modulation, characterized in that: The following steps are involved: Step 1: Collect wind speed data and establish an original wind speed sequence; divide the original wind speed sequence into a prediction set wind speed sequence and a verification set wind speed sequence according to a preset ratio; The wind speed sequence of the prediction set is input into the trained neural network model for prediction to obtain a first prediction value, and a benchmark prediction error W is calculated based on the first prediction value and the actual value in the wind speed sequence of the verification set; Step 2: traverse the wind speed sequence of the forecast set, construct continuous subsequences, and mark all continuous subsequences as having similar trends; Determine whether there is a trend similarity mark in the wind speed sequence of the forecast set. If the judgment result is yes, execute step 3; If the judgment result is no, go to step 4; Step 3: merge the continuous subsequences with trend similarity marks to obtain the merged forecast set wind speed sequence, traverse the merged forecast set wind speed sequence, mark the continuous subsequences with trend similarity, and determine whether the merged forecast set wind speed sequence has trend similarity marks. If the determination result is yes, execute step 3 again. If the judgment result is no, go to step 4; Step 4: Input the wind speed sequence of the current prediction set into the trained neural network model for prediction to obtain the wind speed prediction value of this round. Based on the wind speed prediction value of this round and the actual value in the wind speed sequence of the verification set, calculate the prediction error w; Step 5: Determine whether the prediction error w is greater than or equal to the reference prediction error W. If the determination result is yes, execute step 6. If the judgment result is no, then combine the wind speed sequence of the current prediction set and the wind speed prediction value of this round to obtain the final wind speed prediction sequence, substitute the final wind speed prediction sequence into the trained neural network model for prediction, obtain the final wind speed prediction result, and execute step seven; Step 6: split the current prediction set wind speed sequence to obtain a split prediction set wind speed sequence, use the split prediction set wind speed sequence as the current prediction set wind speed sequence, and execute step 4; Step 7. Calculate the predicted power sent by the wind farm to the grid based on the final wind speed prediction result, obtain the actual power sent by the wind farm to the grid, and calculate the difference between the predicted power and the actual power. When the difference is positive, adjust the super-capacity energy storage system connected to the wind farm exit to the charging state; when the difference is 0, the super-capacity energy storage system connected to the wind farm exit maintains the current state unchanged; when the difference is negative, adjust the super-capacity energy storage system connected to the wind farm exit to the discharging state.

2. The optimization method of supercapacitor energy storage frequency modulation according to claim 1, characterized in that: Traverse the wind speed sequence of the forecast set, construct continuous subsequences, and mark all continuous subsequences for trend similarity. Specifically, the following steps are included: Assume that the wind speed sequence of the forecast set is x(t)=[x1,x2,x3,...,x N ], N is the number of subsequences in the wind speed sequence of the prediction set, x1,x2,x3,...,x N are the 1st, 2nd, 3rd, ..., Nth subsequences in the wind speed sequence of the prediction set; construct continuous subsequences, and the first subsequences of the continuous subsequences are x1~x N-2 , x N-2 It is the N-2th subsequence in the wind speed sequence of the prediction set; the number of subsequences contained in the continuous subsequence is 3~N, and a trend similarity judgment is performed on each continuous subsequence. If the judgment is yes, the continuous subsequence is marked as trend similar; if the judgment is no, no processing is performed.

3. The optimization method of supercapacitor energy storage frequency modulation according to claim 2, characterized in that: The trend similarity judgment comprises the following steps: Determine whether the continuous subsequence satisfies both condition 1 and condition 2. If so, the continuous subsequence is trend-similar; if not, the continuous subsequence is non-trend-similar. Condition one: ≤Max Where Max is the maximum value of the subsequence in the continuous subsequence; Min is the minimum value of the subsequence in the continuous subsequence; E is the maximum absolute value of the difference between any two subsequences in the continuous subsequence; Condition two: ≤ Among them, Sin max is the maximum sine value of the subsequence in the continuous subsequence; Cos min is the minimum cosine of the subsequence in the continuous subsequence.

4. The optimization method of supercapacitor energy storage frequency modulation according to claim 2, characterized in that: Merge consecutive subsequences with similar trend markers, specifically: Among them, X i is the merged subsequence; x i is the first subsequence in the continuous subsequences with trend-similar marks; i is the position of the first subsequence in the continuous subsequences with trend-similar marks in the current wind speed sequence; c is the number of subsequences contained in the continuous subsequences with trend-similar marks; tanh() is the activation function; min() is the minimum function; e is a natural constant.

5. The method for optimizing supercapacitor energy storage frequency modulation according to claim 2, characterized in that: When merging consecutive subsequences with similar trend markers, the following rules are applied: When there is only one continuous subsequence with a similar trend mark, the continuous subsequence is directly merged; When there are two or more continuous subsequences with trend-similar markers, and there is no identical subsequence among all continuous subsequences, merge all continuous subsequences separately; When there are two or more continuous subsequences with trend-similar marks, and at least one subsequence is identical between any two continuous subsequences, the continuous subsequence with trend-similar marks whose first subsequence has the lowest ranking is preferentially merged; if there are two or more continuous subsequences with trend-similar marks whose first subsequence has the lowest ranking is preferentially merged, the continuous subsequence with trend-similar marks containing the largest number of subsequences is preferentially merged.

6. The method for optimizing supercapacitor energy storage frequency modulation according to claim 1, characterized in that: The splitting process is to split a subsequence into two subsequences, specifically: Among them, h i is the subsequence of the current wind speed sequence to be split; H i1 , H i2 h i The two subsequences after splitting; sigmoid() is the activation function; gelu() is the Gaussian error linear unit activation function; e is a natural constant; sin() is the sine function.

7. The method for optimizing supercapacitor energy storage frequency modulation according to claim 1, characterized in that: The benchmark prediction error W is specifically: Among them, y i is the i-th first prediction value, i is the i-th actual value in the wind speed sequence of the validation set, and n is the number of subsequences in the wind speed sequence of the validation set.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the method according to any one of claims 1 to 7 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images