A prediction method and system for energy storage frequency modulation commands with complementary advantages

Abstract

The present invention discloses a method and system for predicting energy storage frequency modulation commands with complementary advantages, which relates to the field of predicting energy storage frequency modulation commands. The method includes: performing VMD decomposition and CEEMDAN decomposition on the frequency modulation commands to be predicted, respectively obtaining a first subsequence set and a second subsequence set; performing sequence interspersing and making a first judgment; based on the result of the first judgment, performing sequence segment exchange on all mutually matching subsequences; predicting the subsequences after sequence segment exchange through a GRU network, and correcting the prediction result to obtain the final prediction result of the energy storage frequency modulation commands. The present invention combines the advantages of the VMD and CEEMDAN decomposition methods, reduces the influence of noise and initial conditions on the decomposition effect, improves the stability and reliability of the decomposition; improves the prediction accuracy of the frequency modulation commands; predicts the magnitude of the frequency modulation commands in advance, enables the over-capacity / battery to act in advance, reduces the response time difference, and thereby improves the revenue value of the power plant.

Description

Technical Field

[0001] The present invention relates to the field of energy storage frequency modulation command prediction, and particularly to a method and system for predicting energy storage frequency modulation commands with complementary advantages. Background Art

[0002] With the continuous development of the power system, the requirements for the frequency stability of the power grid are increasing day by day. Energy storage systems play an important role in assisting thermal power units in frequency modulation. Among them, hybrid energy storage (supercapacitor + lithium battery) assisting thermal power units in frequency modulation is a common technical means. In the traditional method of hybrid energy storage assisting thermal power units in frequency modulation, the difference between the frequency modulation command and the thermal power unit is transmitted to the hybrid energy storage. The low-frequency part is borne by the battery, and the high-frequency part is borne by the supercapacitor. However, this method has certain limitations. It takes time for the signal to be transmitted from the frequency modulation command to the supercapacitor or lithium battery, and at the same time, the response of the supercapacitor or lithium battery itself also takes time, which leads to the problem of response time difference. This response time difference will have a negative impact on the frequency modulation effect and thus affect the benefits of the power plant.

[0003] To solve the problem of response time difference, some methods for predicting the magnitude of frequency modulation commands have emerged. Traditional prediction methods usually use techniques such as variational mode decomposition (VMD) or complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) to decompose the original sequence into a series of subsequences, and then predict these subsequences separately, and finally superimpose the prediction results to obtain the final predicted value. However, these traditional decomposition methods have their own inherent drawbacks. VMD decomposition has problems of mode mixing and end chaos, which will affect the accuracy of the decomposition results. And when the CEEMDAN algorithm processes signals containing noise, the decomposition results are easily affected by the noise. Since the noise is close to the signal frequency, useful signals may be misidentified as noise, thus reducing the decomposition effect. In addition, the CEEMDAN algorithm is greatly affected by the initial conditions, which may lead to differences in the decomposition results of different times. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by the present invention is: how to improve the accuracy of frequency modulation command prediction and reduce the impact of response time difference on the benefits of the power plant.

[0006] To solve the above technical problem, the present invention provides the following technical solutions:

[0007] In a first aspect, an embodiment of the present invention provides a method for predicting energy storage frequency modulation commands with complementary advantages, including:

[0008] Perform VMD decomposition and CEEMDAN decomposition on the frequency modulation command to be predicted to obtain a first subsequence set and a second subsequence set respectively;

[0009] Perform sequence interspersing based on the first subsequence set and the second subsequence set, and make a first judgment;

[0010] The sequence interspersing based on the first subsequence set and the second subsequence set includes:

[0011] Let a certain subsequence in the first subsequence set, that is, a subsequence obtained by VMD decomposition, be IMF i =[X i1 ,X i2 ,X i3 ,...,X ii ,...,X iN , and let the experimental group error of this sequence be W i ;

[0012] Let a certain subsequence in the second subsequence set, that is, a subsequence obtained by CEEMDAN decomposition, be IMF j 、 =[X j1 、 ,X j2 、 ,X j3 、 ,...,X ji 、 ,...,X jN 、 , and let the experimental group error of this sequence be W j 、 ;

[0013] Intersperse the two subsequences, denoted as [X i1 ,X j1 、 ,X i2 ,X j2 、 ,X i3 ,X j3 、 ,...,X ii ,X ji 、 ,...,X iN ,X jN 、 , and the experimental group error generated is W ij ,W ij =(W i +W j 、 ) / 2;

[0014] The first judgment includes:

[0015] Judge the experimental group error generated by the two subsequences with sequence interspersion. If and

[0016] , it is considered that the two subsequences with sequence interspersion match each other, where avg() represents taking the average value;

[0017] Based on the result of the first judgment, perform sequence segment exchange on all matching subsequences; for non-matching subsequences, do not perform sequence segment exchange operations; the so-called matching means that the complete subsequences match each other;

[0018] The performing sequence segment exchange on all matching subsequences based on the result of the first judgment includes:

[0019] Let any pair of matching subsequences be: the subsequence IMF of VMD decomposition i =[X i1 ,X i2 ,X i3 ,...,X ii ,...,X iN and the subsequence IMF of CEEMDAN decomposition j 、 =[X j1 、 ,X j2 、 ,X j3 、 ,...,X ji 、 ,...,X jN 、 , and perform sequence segment exchange of length Q on this pair of subsequences;

[0020] The performing sequence segment exchange of length Q includes:

[0021] The random range of the length of Q is expressed as:

[0022] , where N is the length of the subsequence for which sequence segment exchange is performed, and [ ] represents rounding down;

[0023] The performing sequence segment exchange on all matching subsequences based on the result of the first judgment further includes:

[0024] For each pair of matching subsequences, when determining the length Q of the swapped sequence segment, segments of length Q are selected at different starting positions in the subsequence for the swapping operation; after each swapping operation of selecting segments at different starting positions, the corresponding average error is calculated, and the swapping with the minimum average error is taken as the final result of the sequence segment swapping;

[0025] All the subsequences that have undergone the sequence segment swapping operation are input into the GRU network for prediction, and the prediction result is corrected to obtain the final prediction result of the energy storage frequency modulation command.

[0026] As a preferred scheme of the energy storage frequency modulation command prediction method with complementary advantages, wherein:

[0027] The step of inputting all the subsequences that have undergone the sequence segment swapping operation into the GRU network for prediction and correcting the prediction result includes:

[0028] The subsequences after the sequence segment swapping are predicted through the GRU network. Let the prediction result sequences of the obtained prediction groups be C1, C2, C3,..., C K and C1 、 , C2 、 , C3 、 ,..., C K 、 .

[0029] As a preferred scheme of the energy storage frequency modulation command prediction method with complementary advantages, wherein:

[0030] The step of inputting all the subsequences that have undergone the sequence segment swapping operation into the GRU network for prediction and correcting the prediction result further includes:

[0031] Let the prediction result of a certain sequence after the sequence segment swapping be: C r =[X N+1 , X N+2 , X N+3 ,..., X N+i ,..., X N+0.1N ;

[0032] The corresponding result is corrected to: , where is the length of the DNA segment when the corresponding sequence undergoes segment swapping.

[0033] As a preferred scheme of the energy storage frequency modulation command prediction method with complementary advantages, wherein:

[0034] The step of inputting all the subsequences that have undergone the sequence segment swapping operation into the GRU network for prediction and correcting the prediction result further includes:

[0035] The predicted result of the final energy storage frequency modulation command is expressed as 0.5 (C1 + C2 + C3 +... + C K + C1 、 + C2 、 + C3 、 +... + C K 、 ).

[0036] In a second aspect, an embodiment of the present invention provides a complementary energy storage frequency modulation command prediction system, including:

[0037] An initial decomposition module, configured to perform VMD decomposition and CEEMDAN decomposition on the frequency modulation command to be predicted, respectively obtaining a first subsequence set and a second subsequence set;

[0038] A matching and judging module, configured to perform sequence interspersing based on the first subsequence set and the second subsequence set, and perform a first judgment;

[0039] The sequence interspersing based on the first subsequence set and the second subsequence set includes:

[0040] Let a certain subsequence in the first subsequence set, that is, a subsequence obtained by VMD decomposition, be IMF i =[X i1 , X i2 , X i3 ,..., X ii ,..., X iN , and let the experimental group error of this sequence be W i ;

[0041] Let a certain subsequence in the second subsequence set, that is, a subsequence obtained by CEEMDAN decomposition, be IMF j 、 =[X j1 、 , X j2 、 , X j3 、 ,..., X ji 、 ,..., X jN 、 , and let the experimental group error of this sequence be W j 、 ;

[0042] Intersperse the two subsequences, expressed as [X i1 , X j1 、 , X i2 , X j2 、 , Xi3 , X j3 、 ,..., X ii , X ji 、 ,..., X iN , X jN 、 , the experimental group error generated is W ij , W ij = (W i + W j 、 ) / 2;

[0043] The first judgment described above includes:

[0044] Judge the experimental group errors generated by the two subsequences with sequence interspersing. If and

[0045] , it is considered that the two subsequences with sequence interspersing match each other, where avg() represents taking the average value;

[0046] The segment exchange module is used to perform sequence segment exchange on all matching subsequences based on the result of the first judgment; for non-matching subsequences, no sequence segment exchange operation is performed; the so-called matching means that the complete subsequences match each other;

[0047] Performing sequence segment exchange on all matching subsequences based on the result of the first judgment includes:

[0048] Let any pair of matching subsequences be: the subsequence IMF of VMD decomposition i = [X i1 , X i2 , X i3 ,..., X ii ,..., X iN and the subsequence IMF of CEEMDAN decomposition j 、 = [X j1 、 , X j2 、 , X j3 、 ,..., X ji 、 ,..., X jN 、 , and perform sequence segment exchange of length Q on this pair of subsequences;

[0049] Performing sequence segment exchange of length Q includes:

[0050] The random range of the length of Q is expressed as:

[0051] , where N is the length of the subsequence for sequence segment exchange, and [ ] represents rounding down;

[0052] Based on the result of the first judgment, the sequence segment exchange for all mutually matching subsequences further includes:

[0053] For each pair of mutually matching subsequences, when determining the length Q of the exchanged sequence segment, select segments of length Q at different starting positions in the subsequence for the exchange operation; after each exchange operation of selecting segments at different starting positions, calculate the corresponding average error, and take the exchange with the smallest average error as the final result of the sequence segment exchange.

[0054] A prediction module, configured to input all subsequences that have undergone the sequence segment exchange operation into a GRU network for prediction, and correct the prediction result to obtain the final prediction result of the energy storage frequency modulation command.

[0055] In a third aspect, an embodiment of the present invention provides a computing device, including:

[0056] A memory and a processor;

[0057] The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the one or more programs are executed by the one or more processors, the one or more processors implement the complementary energy storage frequency modulation command prediction method as described in any embodiment of the present invention.

[0058] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are executed by a processor, the complementary energy storage frequency modulation command prediction method as described above is implemented.

[0059] Advantages of the present invention: Traditional VMD decomposition has problems of mode mixing and end chaos. The present invention can effectively suppress these disadvantages of VMD decomposition through a complementary prediction method, making signal decomposition more accurate; when the CEEMDAN algorithm processes noisy signals, the decomposition result is easily affected by noise and is greatly affected by the initial conditions, and there may be differences in the decomposition results of different times. The present invention combines the advantages of VMD and CEEMDAN decomposition methods, reduces the influence of noise and initial conditions on the decomposition effect, and improves the stability and reliability of decomposition; the present invention combines VMD and CEEMDAN decomposition methods, and through sequence matching and DNA exchange operations, gives full play to the advantages of the two methods, comprehensively processes the frequency modulation command sequence, thereby improving the prediction accuracy of the frequency modulation command; predicts the exchanged subsequence and corrects the prediction result, further reducing the prediction error and making the prediction result closer to the actual value; can predict the magnitude of the frequency modulation command in advance, make the over-capacity / battery act in advance, reduce the response time difference, and thus improve the revenue value of the power plant. Description of the Drawings

[0060] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0061] Figure 1 It is the overall flowchart of the complementary energy storage frequency modulation command prediction method described in the present invention. Detailed Embodiments

[0062] In order to make the above objects, features and advantages of the present invention more obvious and understandable, the following will make a detailed description of the specific embodiments of the present invention in conjunction with the drawings of the specification. Obviously, the described embodiments are some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0063] Many specific details are set forth in the following description in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the spirit of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0064] Secondly, the so-called "one embodiment" or "embodiment" herein refers to specific features, structures, or characteristics that may be included in at least one implementation manner of the present invention. The appearances of "in one embodiment" in different places in this specification do not all refer to the same embodiment, nor are they separate or selectively exclusive embodiments from other embodiments.

[0065] Embodiment 1, referring to Figure 1 , is the first embodiment of the present invention. This embodiment provides a method for predicting energy storage frequency modulation commands with complementary advantages, including:

[0066] S1: Perform VMD decomposition and CEEMDAN decomposition on the frequency modulation command to be predicted, respectively obtaining a first subsequence set and a second subsequence set;

[0067] S2: Interleave the sequences based on the first subsequence set and the second subsequence set, and make a first judgment;

[0068] S3: Based on the result of the first judgment, exchange sequence segments for all mutually matching subsequences;

[0069] S4: Predict the subsequences after sequence segment exchange through a GRU network, and correct the prediction result to obtain the final prediction result of the energy storage frequency modulation command.

[0070] It should be noted that through steps S1 - S4, first apply VMD decomposition and CEEMDAN decomposition to the frequency modulation command to be predicted to generate corresponding subsequence sets. Then interleave these subsequences and judge the matching property, and then exchange sequence segments for the matching subsequences. Finally, use the GRU network to predict the exchanged subsequences and correct the prediction result to obtain the final prediction result of the energy storage frequency modulation command. This process combines multiple signal decomposition, processing, and prediction methods, effectively leveraging the advantages of different decomposition methods, and can more accurately predict the energy storage frequency modulation command, providing strong support for the frequency modulation control and revenue improvement of related power systems.

[0071] Embodiment 2, referring to Figure 1 , is an embodiment of the present invention. Based on the previous embodiment, a method for predicting energy storage frequency modulation commands with complementary advantages is provided, including:

[0072] In this embodiment, the step S1 of performing VMD decomposition and CEEMDAN decomposition on the frequency modulation command to be predicted, respectively obtaining a first subsequence set and a second subsequence set, includes:

[0073] Let the frequency modulation command be P t , after VMD decomposition, it becomes IMF1, IMF2, IMF3, IMF i ,..., IMF K, that is, the first subsequence set; the same frequency modulation instruction becomes IMF1 after CEEMDAN decomposition 、 , IMF2 、 , IMF3 、 , IMF i ,..., IMF K 、 , that is, the second subsequence set.

[0074] In this embodiment, the sequence interspersing based on the first subsequence set and the second subsequence set in the above step S2 includes:

[0075] Let a certain subsequence in the first subsequence set, that is, a subsequence obtained by VMD decomposition, be IMF i = [X i1 , X i2 , X i3 ,..., X ii ,..., X iN , and let the experimental group error of this sequence be W i .

[0076] Let a certain subsequence in the second subsequence set, that is, a subsequence obtained by CEEMDAN decomposition, be IMF j 、 = [X j1 、 , X j2 、 , X j3 、 ,..., X ji 、 ,..., X jN 、 , and let the experimental group error of this sequence be W j 、 .

[0077] Intersperse the two subsequences, denoted as [X i1 , X j1 、 , X i2 , X j2 、 , X i3 , X j3 、 ,..., X ii , X ji 、 ,..., X iN , X jN 、 , and the generated experimental group error is W ij , W ij = (W i + W j、 ) / 2.

[0078] It should be noted that let the frequency modulation command be P t = [X1, X2, X3,..., X i ,..., X N , N is the length of the initial frequency modulation command sequence, and the series of the first 0.9N length [X1, X2, X3,..., X 0.9N is used as the input to pre-test the values of the test group [X 0.9N+1 , X 0.9N+2 , X 0.9N+3 ,..., X N and the unknown group [X N+1 , X N+2 , X N+3 ,..., X N+0.1N . Among them, the actual value and the predicted value of the test group generate all the errors (MAPE) of this embodiment, and what this embodiment truly predicts is the value of the unknown group. MAPE is the average value of the absolute errors, expressed as: ;

[0079] In this embodiment, the first judgment in the above step S2 includes:

[0080] If and

[0081] , it is considered that the two subsequences for sequence interspersing match each other, where avg() represents taking the average value.

[0082] It should be noted that based on the detailed analysis of the sequence characteristics and error metrics, the subsequence pairs with complementarity can be accurately found.

[0083] In this embodiment, based on the result of the first judgment in the above step S3, the sequence segment exchange for all the mutually matching subsequences includes:

[0084] The so-called mutual matching means that the complete subsequences match each other.

[0085] Let any pair of mutually matching subsequences be: the subsequence IMF of VMD decomposition i = [X i1 , X i2 , X i3 ,..., X ii ,..., X iN and the subsequence IMF of CEEMDAN decomposition j 、 = [X j1 、 , X j2、 ,X j3 、 ,X ji 、 ,...,X jN 、 , perform a sequence segment exchange of length Q on this pair of subsequences.

[0086] The random range of the length of Q is expressed as:

[0087] , where N is the length of the subsequence for which the sequence segment exchange is performed, and [ ] represents rounding down.

[0088] Exemplarily, let the subsequence IMF of VMD decomposition i = [1, 2, 3, 4,..., 9], and the subsequence IMF of CEEMDAN decomposition j 、 = [10, 11, 12, 13,..., 18];

[0089] Randomly determine Q = 5, then the result of the first exchange is IMF i = [10, 11, 12, 13, 14, 6, 7, 8, 9], IMF j 、 = [1, 2, 3, 4, 5, 15, 16, 17, 18];

[0090] Calculate the experimental group errors W1, W1 、 and the corresponding error average value for this time.

[0091] The result of the second exchange is IMF i = [1, 11, 12, 13, 14, 15, 7, 8, 9], IMF j 、 = [10, 2, 3, 4, 5, 6, 16, 17, 18];

[0092] Calculate the experimental group errors and the corresponding error average value for this time.

[0093] And so on, exhausting all possibilities;

[0094] It should be noted that for each pair of matching subsequences, when the length Q of the exchange sequence segment is determined, a segment of length Q is selected at different starting positions in the subsequence for the exchange operation. After each exchange operation of selecting segments at different starting positions, calculate the corresponding error average value, and take the exchange with the smallest error average value as the final result of the sequence segment exchange.

[0095] It should be noted that for the matched subsequences, sequence segment exchange is performed so that the subsequences generated by different decomposition methods can learn from each other's advantageous information, further optimizing the feature expression of the subsequences, reducing the errors caused by the limitations of a single decomposition method, and providing high-quality data input for the subsequent prediction process.

[0096] In this embodiment, in step S4 above, the subsequence after sequence segment exchange is predicted through a GRU network, and the correction of the prediction result includes:

[0097] All the subsequences after sequence segment exchange, that is, DNA segment exchange, are respectively put into the GRU network for prediction, and the prediction result sequences of the obtained prediction groups are C1, C2, C3,..., C K and C1 、 , C2 、 , C3 、 ,..., C K 、 .

[0098] Suppose the prediction result of a certain sequence after DNA exchange is C r = [X N+1 , X N+2 , X N+3 ,..., X N+i ,..., X N+0.1N , and the corresponding result is corrected to:

[0099] , where is the length of the DNA segment corresponding to this sequence.

[0100] The final prediction result of the energy storage frequency modulation instruction is expressed as 0.5(C1 + C2 + C3 +... + C K + C1 、 + C2 、 + C3 、 +... + C K 、 ).

[0101] It should be noted that when using the GRU network to predict the subsequence after sequence segment exchange, the GRU network, as an advanced recurrent neural network, has a powerful ability to process time series data and can capture the complex dynamic change laws in the frequency modulation instruction sequence; in the correction link of the prediction result, the characteristics of the subsequence and the influence of the exchange operation are fully considered to further eliminate the possible errors and make the prediction result more accurately approximate the actual energy storage frequency modulation instruction situation.

[0102] Embodiment 3. The above is a schematic solution of the complementary energy storage frequency modulation command prediction method of this embodiment. It should be noted that the technical solution of the complementary energy storage frequency modulation command prediction system belongs to the same concept as the technical solution of the above complementary energy storage frequency modulation command prediction method. For the details not described in detail in the technical solution of the complementary energy storage frequency modulation command prediction system in this embodiment, reference can be made to the description of the technical solution of the above complementary energy storage frequency modulation command prediction method.

[0103] This embodiment also provides a system based on the complementary energy storage frequency modulation command prediction method, including:

[0104] An initial decomposition module, configured to perform VMD decomposition and CEEMDAN decomposition on the frequency modulation command to be predicted, and respectively obtain a first subsequence set and a second subsequence set;

[0105] A matching judgment module, configured to perform sequence interspersing based on the first subsequence set and the second subsequence set, and perform a first judgment;

[0106] The sequence interspersing based on the first subsequence set and the second subsequence set includes:

[0107] Let a certain subsequence in the first subsequence set, that is, a certain subsequence obtained by VMD decomposition, be IMF i =[X i1 , X i2 , X i3 ,..., X ii ,..., X iN , and let the experimental group error of this sequence be W i ;

[0108] Let a certain subsequence in the second subsequence set, that is, a certain subsequence obtained by CEEMDAN decomposition, be IMF j 、 =[X j1 、 , X j2 、 , X j3 、 ,..., X ji 、 ,..., X jN 、 , and let the experimental group error of this sequence be W j 、 ;

[0109] Intersperse the two subsequences, expressed as [X i1 , X j1 、 , X i2 , X j2 、, X i3 , X j3 、 ,..., X ii , X ji 、 ,..., X iN , X jN 、 , the experimental group error generated is W ij , W ij = (W i + W j 、 ) / 2;

[0110] The first judgment described above includes:

[0111] Judge the experimental group error generated by the two subsequences with sequence interspersing. If and

[0112] , it is considered that the two subsequences with sequence interspersing match each other, where avg() represents taking the average value;

[0113] The segment exchange module is used to perform sequence segment exchange on all matching subsequences based on the result of the first judgment; for non-matching subsequences, no sequence segment exchange operation is performed; the so-called matching means that the complete subsequences match each other;

[0114] Performing sequence segment exchange on all matching subsequences based on the result of the first judgment includes:

[0115] Let any pair of matching subsequences be: the subsequence IMF of VMD decomposition i = [X i1 , X i2 , X i3 ,..., X ii ,..., X iN and the subsequence IMF of CEEMDAN decomposition j 、 = [X j1 、 , X j2 、 , X j3 、 ,..., X ji 、 ,..., X jN 、 , perform sequence segment exchange of length Q on this pair of subsequences;

[0116] Performing sequence segment exchange of length Q includes:

[0117] The random range of the length of Q is expressed as:

[0118] , where N is the length of the subsequence for sequence segment exchange, and [ ] represents rounding down;

[0119] Based on the result of the first judgment, the sequence segment exchange for all mutually matching subsequences further includes:

[0120] For each pair of mutually matching subsequences, when determining the length Q of the exchange sequence segment, select segments with a length of Q at different starting positions in the subsequence for the exchange operation; after each exchange operation of selecting segments at different starting positions, calculate the corresponding average error, and take the exchange with the smallest average error as the final result of the sequence segment exchange;

[0121] The prediction module is used to input all subsequences that have undergone the sequence segment exchange operation into the GRU network for prediction, and correct the prediction result to obtain the final prediction result of the energy storage frequency modulation command.

[0122] This embodiment also provides a computing device, applicable to the case of the energy storage frequency modulation command prediction method with complementary advantages, including:

[0123] A memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the energy storage frequency modulation command prediction method with complementary advantages as proposed in the above embodiment.

[0124] This embodiment also provides a storage medium, on which a computer program is stored, and when the program is executed by the processor, it implements the energy storage frequency modulation command prediction method with complementary advantages as proposed in the above embodiment.

[0125] The storage medium proposed in this embodiment and the energy storage frequency modulation command prediction method with complementary advantages proposed in the above embodiment belong to the same inventive concept. The technical details not described in detail in this embodiment can be referred to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0126] Embodiment 4, referring to Tables 1-2, is an embodiment of the present invention, which provides an energy storage frequency modulation command prediction method with complementary advantages. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through simulation experiments.

[0127] The present invention respectively uses the method of the present invention, the prediction method of VMD-GRU, and the prediction method of CEEMDAN-GRU to predict the frequency modulation sequence, and the results are as follows.

[0128] Table 1 Comparison of evaluation indexes

[0129]

[0130] Table 2 Four evaluation indexes

[0131]

[0132] Among them, N represents the sample size, and respectively represent the actual value and the predicted value at time n.

[0133] It can be seen that when predicting the frequency modulation sequence, the complementary energy storage frequency modulation command prediction method proposed by the present invention is significantly better than the prediction methods of VMD - GRU and CEEMDAN - GRU in all evaluation indexes. Specifically, in terms of the indexes of MAE (Mean Absolute Error), SSE (Sum of Squares within Groups or Residual Sum of Squares), RMSE (Root Mean Square Error) and MAPE (Mean of Absolute Errors), the values obtained by the method of the present invention are much lower than those of the other two comparative methods. This fully shows that the method of the present invention can greatly reduce the prediction error, significantly improve the accuracy and reliability of the prediction, more accurately approximate the actual frequency modulation command situation, thereby providing a more accurate and effective basis for the frequency modulation control of the power system, and further improving the benefits of power plants and the stability of the power system, which strongly verifies that the method of the present invention has obvious advantages and good application effects.

[0134] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

Claims

1. A method for predicting energy storage frequency modulation instructions with complementary advantages, characterized in that: include: Perform VMD decomposition and CEEMDAN decomposition on the frequency modulation instructions to be predicted to obtain a first subsequence set and a second subsequence set respectively; Interleave the sequence based on the first subsequence set and the second subsequence set, and make a first judgment; The performing sequence interleaving based on the first subsequence set and the second subsequence set comprises: Suppose a subsequence in the first subsequence set, that is, a subsequence decomposed by VMD, is IMF i =[X i1 ,X i2 ,X i3 ,...,X ii ,...,X iN ], let the experimental group error of the sequence be W i ; Suppose a subsequence in the second subsequence set, that is, a subsequence IMF decomposed by CEEMDAN j 、 =[X j1 、 ,X j2 、 ,X j3 、 ,...,X ji 、 ,...,X jN 、 ], let the experimental group error of the sequence be W j 、 ; Interleave the two subsequences, expressed as [X i1 ,X j1 、 ,X i2 ,X j2 、 , X i3 ,X j3 、 ,...,X ii ,X ji 、 ,...,X iN ,X jN 、 ], the experimental group error generated is W ij , W ij =(W i +W j 、 ) / 2; The first determination comprises: The test group error generated by the two subsequences interlaced with each other is judged. and , then the two subsequences interlaced are considered to match each other, where avg() means taking the average value; Based on the result of the first judgment, sequence fragments are exchanged for all mutually matching subsequences; for unmatched subsequences, no sequence fragment exchange operation is performed; the mutual matching refers to the mutual matching of complete subsequences; The step of performing sequence segment exchange on all mutually matching subsequences based on the result of the first judgment includes: Suppose any pair of matching subsequences is: VMD decomposed subsequence IMF i =[X i1 ,X i2 ,X i3 ,...,X ii ,...,X iN ] and CEEMDAN decomposition of subsequence IMF j 、 =[X j1 、 ,X j2 、 ,X j3 、 ,...,X ji 、 ,...,X jN 、 ], exchange the sequence fragments of length Q for this pair of subsequences; The step of exchanging sequence segments having a length of Q comprises: The random range of the length of Q is expressed as: , where N is the length of the subsequence to be exchanged, and [ ] means rounding down; The step of performing sequence segment exchange on all mutually matching subsequences based on the result of the first judgment further includes: For each pair of mutually matching subsequences, when the length Q of the exchange sequence fragment is determined, fragments of length Q are selected from different starting positions in the subsequence for exchange operation; after each exchange operation of selecting fragments at different starting positions, the corresponding average error is calculated, and the exchange with the smallest average error is taken as the final result of sequence fragment exchange; All subsequences that have undergone sequence segment exchange operations are input into the GRU network for prediction, and the prediction results are corrected to obtain the final energy storage frequency modulation instruction prediction results.

2. A method for predicting energy storage frequency modulation instructions with complementary advantages as claimed in claim 1, characterized in that: The step of inputting all subsequences that have undergone the sequence segment exchange operation into the GRU network for prediction and correcting the prediction results includes: The subsequences after sequence fragment exchange are predicted through the GRU network, and the prediction result sequence of the obtained prediction group is assumed to be C1, C2, C3, ..., C K and C1 、 , C2 、 ,C3 、 ,...,C K 、 .

3. A method for predicting energy storage frequency modulation instructions with complementary advantages as claimed in claim 2, characterized in that: The step of inputting all subsequences that have undergone the sequence segment exchange operation into the GRU network for prediction and correcting the prediction results also includes: Suppose the prediction result of a sequence after sequence segment exchange is: C r =[X N+1 ,X N+2 ,X N+3 ,...,X N+i ,...,X N+0.1N ]; Correct the corresponding results to: ,in, It is the length of the DNA fragment when the corresponding sequence undergoes fragment exchange.

4. A method for predicting energy storage frequency modulation instructions with complementary advantages as claimed in claim 3, characterized in that: The step of inputting all subsequences that have undergone the sequence segment exchange operation into the GRU network for prediction and correcting the prediction results also includes: The final energy storage frequency modulation command prediction result is expressed as 0.5 (C1+C2+C3+...+C K +C1 、 +C2 、 +C3 、 +...+C K 、 ).

5. A complementary energy storage frequency modulation instruction prediction system, using any method as claimed in claim 1 to claim 4, characterized in that: include: An initial decomposition module, used for performing VMD decomposition and CEEMDAN decomposition on the frequency modulation instruction to be predicted, to obtain a first subsequence set and a second subsequence set respectively; A matching judgment module, used for performing sequence interleaving based on the first subsequence set and the second subsequence set, and performing a first judgment; The performing sequence interleaving based on the first subsequence set and the second subsequence set comprises: Suppose a subsequence in the first subsequence set, that is, a subsequence decomposed by VMD, is IMF i =[X i1 ,X i2 ,X i3 ,...,X ii ,...,X iN ], let the experimental group error of the sequence be W i ; Suppose a subsequence in the second subsequence set, that is, a subsequence IMF decomposed by CEEMDAN j 、 =[X j1 、 ,X j2 、 ,X j3 、 ,...,X ji 、 ,...,X jN 、 ], let the experimental group error of the sequence be W j 、 ; Interleave the two subsequences, expressed as [X i1 ,X j1 、 ,X i2 ,X j2 、 , X i3 ,X j3 、 ,...,X ii ,X ji 、 ,...,X iN ,X jN 、 ], the experimental group error generated is W ij , W ij =(W i +W j 、 ) / 2; The first determination comprises: The test group error generated by the two subsequences interlaced with each other is judged. and , then the two subsequences interlaced are considered to match each other, where avg() means taking the average value; A fragment exchange module, used for performing sequence fragment exchange on all mutually matching subsequences based on the result of the first judgment; for unmatched subsequences, no sequence fragment exchange operation is performed; the mutual matching refers to the mutual matching of complete subsequences; The step of performing sequence segment exchange on all mutually matching subsequences based on the result of the first judgment includes: Suppose any pair of matching subsequences is: VMD decomposed subsequence IMF i =[X i1 ,X i2 ,X i3 ,...,X ii ,...,X iN ] and CEEMDAN decomposition of subsequence IMF j 、 =[X j1 、 ,X j2 、 ,X j3 、 ,...,X ji 、 ,...,X jN 、 ], exchange the sequence fragments of length Q for this pair of subsequences; The step of exchanging sequence segments having a length of Q comprises: The random range of the length of Q is expressed as: , where N is the length of the subsequence to be exchanged, and [ ] means rounding down; The step of performing sequence segment exchange on all mutually matching subsequences based on the result of the first judgment further includes: For each pair of mutually matching subsequences, when the length Q of the exchange sequence fragment is determined, fragments of length Q are selected from different starting positions in the subsequence for exchange operation; after each exchange operation of selecting fragments at different starting positions, the corresponding average error is calculated, and the exchange with the smallest average error is taken as the final result of sequence fragment exchange; The prediction module is used to input all subsequences that have undergone sequence segment exchange operations into the GRU network for prediction, and to correct the prediction results to obtain the final energy storage frequency modulation instruction prediction results.

6. A computing device comprising: Memory and processor; The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions. When the computer executable instructions are executed by the processor, the steps of the method described in any one of claims 1 to 4 are implemented.

7. A computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions, when executed by a processor, implement the steps of the method according to any one of claims 1 to 4.

Images