Renewable energy fluctuation identification method based on parameter adaptive revolving door algorithm

Abstract

The invention provides a renewable energy fluctuation identification method based on a parameter adaptive revolving door algorithm. The renewable energy fluctuation identification method comprises the following steps: acquiring a renewable energy power prediction data set, a time sequence set and an initial door width; taking out the prediction data and the corresponding time sequence in sequence, performing slope calculation in combination with the initial door width, if the obtained slope of the upper spiral door is smaller than the slope of the lower spiral door, returning to perform slope calculation again until the slope of the upper spiral door is greater than or equal to the slope of the lower spiral door, and retaining the data point at the current moment; if the average percentage absolute error of the fluctuation section corresponding to the data point at the current moment to the data point at the previous moment is greater than an average percentage absolute error threshold value, updating the initial gate width, and returning to perform slope and average percentage absolute error calculation again; keeping the data point at the previous moment until the current average percentage absolute error is less than or equal to the average percentage absolute error threshold value; and extracting fluctuation characteristics of each fluctuation section. According to the method, the volatility identification precision is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of renewable energy fluctuation identification, and in particular to a renewable energy fluctuation identification method based on a parameter-adaptive revolving door algorithm. Background Art

[0002] In the context of the Global Energy Internet, renewable energy has experienced unprecedented development. However, renewable energy is characterized by randomness and volatility, and predicting its volatility is crucial for optimizing the dispatch and operational control of power systems.

[0003] Currently, indirect forecasting is the mainstream method for renewable energy volatility prediction. It identifies volatility based on renewable energy power forecasts to obtain volatility prediction results. Some researchers use statistical characteristic indicators to characterize renewable energy fluctuations, such as slope, mean, standard deviation, maximum, minimum, and volatility. However, these methods provide a vague description of renewable energy volatility and fail to fully reflect the fluctuation characteristics of a specific time period. To address these issues, some researchers segment renewable energy output forecast series and then extract the fluctuation characteristics of each segment to identify renewable energy volatility. Commonly used methods include filtering, sliding window methods, extreme point extraction, and revolving door algorithms. The segmentation effect of these traditional methods is not ideal. Current renewable energy volatility identification methods have several issues. For example, the extreme point extraction method performs well in low-frequency bands but poorly in high-frequency bands. The sliding window method's identification performance is significantly affected by parameter selection. Inappropriate window size selection can result in large errors, and this method cannot accurately characterize time periods with less drastic power fluctuations. The revolving door algorithm can also suffer from inaccurate identification due to improper parameter selection.

[0004] Therefore, the identification methods in the prior art have poor accuracy in identifying volatility. Summary of the Invention

[0005] In view of this, the present invention provides a renewable energy volatility identification method based on a parameter-adaptive revolving door algorithm to solve the above problem.

[0006] The present invention provides a method for identifying renewable energy volatility based on a parameter-adaptive revolving door algorithm, comprising: step one, obtaining a renewable energy power prediction data set and a corresponding time series set; step two, determining an initial gate width for identifying renewable energy volatility through a beetle swarm optimization algorithm; step three, sequentially taking out a prediction data set and a corresponding time series from the data set and the corresponding time series set, and performing slope calculation in combination with the initial gate width to obtain an upper spiral gate slope and a lower spiral gate slope respectively; step four, comparing the upper spiral gate slope and the lower spiral gate slope, and if the upper spiral gate slope is smaller than the lower spiral gate slope, returning to step Step 3: Recalculate the slope until the slope of the upper spiral gate is greater than or equal to the slope of the lower spiral gate, and retain the data point at the current moment; Step 5: Calculate the average percentage absolute error of the fluctuation segment from the data point at the current moment to the data point at the previous moment. If the average percentage absolute error is greater than the average percentage absolute error threshold, update the initial gate width, return to step 3, recalculate the slope and average percentage absolute error until the current average percentage absolute error is less than or equal to the average percentage absolute error threshold, and retain the data point at the previous moment; Step 6: There is a fluctuation segment between every two retained data points, and the fluctuation characteristics of each fluctuation segment are extracted.

[0007] In another implementation of the present invention, the upper spiral gate slope and the lower spiral gate slope are expressed as:

[0008] K′ 1new =max(K1,K 1new ),K' 2new =min(K2,K 2new )

[0009] Among them, K 1new , K 2new is the initial value of the slope of the lower revolving door, K1 and K2 represent the slopes of the upper and lower revolving doors in the time series T respectively.

[0010] In another implementation of the present invention, the mean percentage absolute error calculation formula is:

[0011]

[0012] Among them, S m 、S n are the power values ​​restored proportionally after compression and the original power values ​​during the same period of time; m is the time interval from the last storage point to the detection point.

[0013] In another implementation of the present invention, the fluctuation characteristics include fluctuation amplitude, fluctuation rate, fluctuation direction, and duration.

[0014] In another implementation of the present invention, the fluctuation amplitude ΔP is expressed as:

[0015] ΔP=|P(t n )-P(t m )|

[0016] Where, P(t n ) is t n Renewable energy output at the moment; P(t m ) is t m Renewable energy output at the moment, meeting t n >t m .

[0017] In another implementation of the present invention, the fluctuation rate is expressed as:

[0018]

[0019] In another implementation of the present invention, the fluctuation direction is expressed as:

[0020]

[0021] Another aspect of the present invention provides a renewable energy volatility identification system based on a parameter-adaptive revolving door algorithm, comprising: a data acquisition module for acquiring a renewable energy power prediction data set and a corresponding time series set; a data processing module for determining an initial gate width for renewable energy volatility identification through a beetle swarm optimization algorithm; a data calculation module for sequentially taking out a prediction data and a corresponding time series from the data set and the corresponding time series set, and performing slope calculation in combination with the initial gate width to obtain an upper spiral gate slope and a lower spiral gate slope respectively; a first judgment module for comparing the upper spiral gate slope with the lower spiral gate slope, and returning the upper spiral gate slope if the upper spiral gate slope is smaller than the lower spiral gate slope. Return to the data calculation module to recalculate the slope until the slope of the upper spiral gate is greater than or equal to the slope of the lower spiral gate, and retain the data point at the current moment; a second judgment module: used to calculate the average percentage absolute error of the fluctuation segment from the data point at the current moment to the data point at the previous moment, if the average percentage absolute error is greater than the average percentage absolute error threshold, then update the initial gate width, return to the data calculation module to recalculate the slope and average percentage absolute error, until the current average percentage absolute error is less than or equal to the average percentage absolute error threshold, and retain the data point at the previous moment; a result output module: used to extract the fluctuation characteristics of each fluctuation segment as a fluctuation segment between every two retained data points.

[0022] Another aspect of the present invention provides 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 computer program, the steps of a renewable energy volatility identification method based on a parameter-adaptive revolving door algorithm as described in any one of the above items are implemented.

[0023] Another aspect of the present invention provides a computer storage medium, characterized in that a computer program is stored on the computer storage medium, and when the computer program is executed by a processor, the steps of the renewable energy volatility identification method based on the parameter adaptive revolving door algorithm as described in any one of the above are implemented.

[0024] The renewable energy volatility identification method based on the parameter adaptive revolving door algorithm of the present invention adopts the beetle swarm optimization algorithm to optimize the renewable energy output data to be identified, obtains the initial gate width of the revolving door algorithm, and then adaptively expands and contracts the initial gate width based on the relative error to obtain fluctuation segments with different fluctuation characteristics, thereby improving the accuracy of fluctuation identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the embodiments or the description of the prior art. By reading the detailed description of the embodiments below, the advantages and benefits of the solutions will become clear to those skilled in the art. The drawings are only for the purpose of illustrating preferred embodiments and are not to be considered as limiting the present invention. In the drawings:

[0026] Figure 1 The figure is a flow chart of a method for identifying renewable energy volatility based on a parameter-adaptive revolving door algorithm according to an embodiment of the present invention.

[0027] Figure 2 Schematic diagram of a renewable energy volatility identification algorithm according to an embodiment of the present invention. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the technical solutions in the embodiments of the present invention, the technical solutions in the embodiments of the present invention will be clearly and detailedly described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by those skilled in the art based on the embodiments in the embodiments of the present invention should fall within the scope of protection of the embodiments of the present invention.

[0029] Figure 1 A flow chart of a renewable energy volatility identification method based on a parameter-adaptive revolving door algorithm provided by an embodiment of the present invention is shown in FIG. Figure 1 As shown, this embodiment mainly includes:

[0030] S101: Obtain a renewable energy power prediction data set and a corresponding time series set.

[0031] S102. Determine an initial threshold width for identifying renewable energy volatility using a swarm optimization algorithm.

[0032] S103 , sequentially extracting a predicted data and a corresponding time series from the data set and the corresponding time series, and performing slope calculation in combination with the initial gate width to obtain an upper spiral gate slope and a lower spiral gate slope, respectively.

[0033] S104. Compare the slope of the upper spiral gate with the slope of the lower spiral gate. If the slope of the upper spiral gate is less than the slope of the lower spiral gate, return to S103 and recalculate the slope until the slope of the upper spiral gate is greater than or equal to the slope of the lower spiral gate, and retain the data point at the current moment.

[0034] S105. Calculate the average percentage absolute error of the fluctuation segment from the data point at the current moment to the data point at the previous moment. If the average percentage absolute error is greater than the average percentage absolute error threshold, update the initial gate width, return to S103, and recalculate the slope and average percentage absolute error until the current average percentage absolute error is less than or equal to the average percentage absolute error threshold, and retain the data point at the previous moment.

[0035] S106. The area between every two retained data points is a fluctuation segment, and the fluctuation characteristics of each fluctuation segment are extracted.

[0036] The renewable energy volatility identification method based on the parameter adaptive revolving door algorithm of the present invention adopts the beetle swarm optimization algorithm to optimize the renewable energy output data to be identified, obtains the initial gate width of the revolving door algorithm, and then adaptively expands and contracts the initial gate width based on the relative error to obtain fluctuation segments with different fluctuation characteristics, thereby improving the accuracy of fluctuation identification.

[0037] In another implementation of the present invention, the upper spiral gate slope and the lower spiral gate slope are expressed as:

[0038] K′ 1new =max(K1,K 1new ),K' 2new =min(K2,K 2new )

[0039] Among them, K 1new , K 2new is the initial value of the slope of the lower revolving door, K1 and K2 represent the slopes of the upper and lower revolving doors in the time series T respectively.

[0040] For example, let P = {p1, p2, p3, ..., p i ,...,p n} is the renewable energy power forecast data, T={t1,t2,t3,...,t i ,...,t n} is the time series corresponding to the power prediction data, K 1new is the initial value of the upper revolving door slope, K 2new is the initial value of the slope of the lower revolving door, and ΔE is the tolerance coefficient of the SDA algorithm, that is, the door width.

[0041] The main process of the revolving door algorithm is as follows:

[0042] (1) Initialize the slopes of the upper and lower revolving doors respectively. The formulas are as follows:

[0043]

[0044] (2) In the time series T, the slopes of the upper and lower revolving doors are calculated respectively. The formula is as follows:

[0045]

[0046] (3) Update the slope K1' of the upper revolving door respectively new and the slope K' of the lower revolving door 2new , the formula is as follows:

[0047] K′ 1new =max(K1,K 1new ),K' 2new =min(K2,K 2new ) (3)

[0048] (4) Compare the upper revolving door slope K1' new and the slope K' of the lower revolving door 2new , determine the data to be stored, if K′ is satisfied 1new ≥K' 2new , then store the tth i-1 The point at time i=i+1 is returned to step (1); otherwise, the revolving door will continue to compress the data and return to step (2).

[0049] In another implementation of the present invention, a highly efficient intelligent optimization algorithm, beetle swarm optimization (BSO), is employed to comprehensively optimize the data to be identified, obtaining an optimal gate width that serves as the initial gate width for identifying renewable energy volatility. The gate width of the revolving door algorithm is the position of each beetle in the BSO algorithm, and the global optimal solution is achieved through continuous iterative updates.

[0050] The main process of the BSO algorithm is as follows:

[0051] (1) Initialize the position, speed and search direction of the longicorn:

[0052]

[0053]

[0054] Where: and are the location of the k-th longicorn beetle and the s-th variable of the search speed, respectively; S and K are the search space dimension and the number of longicorn beetles, respectively; u ps 、l ps 、u vs and l vs are the upper and lower bounds of the sth variable position and search speed respectively.

[0055] (2) Calculate the inertia weight coefficient:

[0056]

[0057] Where: ω n is the inertia weight coefficient of the nth iteration; ω max and ω min are the maximum and minimum values ​​of the inertia coefficient respectively; n is the current iteration number; N is the total iteration number.

[0058] (3) Calculate the search step size and search distance:

[0059]

[0060] Where: is the step size of the nth iteration; is the step attenuation coefficient, which is generally taken as 0.8; μ0 is the initial step length; is the search distance of the nth iteration; c1 is the adjustment factor.

[0061] (4) Calculation of the left and right positions of the longicorn herd:

[0062]

[0063] Where: and is the left and right whisker positions of the k-th longicorn beetle at the n-th iteration; is the centroid position of the k-th longicorn beetle at the n-th iteration.

[0064] (5) Calculate the moving position increment:

[0065]

[0066] Where: is the moving position increment of the n+1th iteration; sign is the sign function; f is the fitness function, and its calculation formula needs to be set according to the application scenario.

[0067] (6) Speed ​​update:

[0068]

[0069] Where: c2 and c3 are two positive constant coefficients; r1 and r2 are two random numbers with a value range of [0, 1]; and are individual extreme values ​​and global extreme values.

[0070] (7) Longicorn location update:

[0071]

[0072] Where: λ is a positive constant.

[0073] (8) Global optimal solution update:

[0074] Calculate the fitness function of each beetle's position and assign the beetle position x corresponding to the best fitness function to best as the global optimal solution for the nth iteration.

[0075] During the optimization process, the compression error and compression ratio are used to construct the optimization fitness function:

[0076]

[0077] Where: f is the fitness function for optimization; α1 and α2 are coefficients; f MSE is the compression error; f c is the compression ratio; P(t) is the actual output at time t, MW; P f (t) is the power at time t after linear interpolation of two adjacent feature data points, MW; N1 is the total number of samples; N2 is the number of compressed data.

[0078] The present invention innovatively introduces the BSO algorithm as a pre-optimization module, and automatically searches for the optimal initial gate width parameters of the revolving door algorithm through a swarm intelligent search mechanism (inertia weight mechanism + double-whisker detection mechanism), thereby solving the subjectivity of parameter selection of the traditional revolving door algorithm, improving the accuracy of volatility identification, and adapting to new energy output data with different volatility characteristics.

[0079] In another implementation of the present invention, the mean percentage absolute error calculation formula is:

[0080]

[0081] Among them, S m 、S n are the power values ​​restored proportionally after compression and the original power values ​​during the same period of time; m is the time interval from the last storage point to the detection point.

[0082] Specifically, after determining the initial door width, the initial door width is scaled according to the data to be identified, and the data points that meet the conditions are retained. There is a fluctuation segment between the two points to achieve parameter adaptation of the revolving door algorithm (different fluctuation segments correspond to different door widths).

[0083] like Figure 2 As shown, the specific steps of the algorithm are as follows:

[0084] (1) Calculate the upper revolving door slope K′ using equations (1 to 3) 1new and the slope K' of the lower revolving door 2new ;

[0085] (2) Comparison of K′ 1new and K' 2new , determine the data to be stored, if the data point at time t satisfies K′ 1new ≥K' 2new , then store the data point at the current moment and go to step (3); otherwise: i=i+1, go to step (1).

[0086] (3) Calculate the average percentage absolute error C of the fluctuation segment from the last retained data point to time t-1 E :

[0087]

[0088] Where: S m 、S n are the power values ​​restored proportionally after compression and the original power values ​​during the same period of time; m is the time interval from the last storage point to the detection point.

[0089] If C E ≤C E,th , then store the data point at time t-1 and return to step (1) to reinitialize the slope of the up and down revolving door; if C E >C E,th When , it is processed according to formula (15), and then returns to the last saved data point, that is, i = i last , go to step (1).

[0090] ε1=ε0-Δε (15)

[0091] Where: ε0 is the set initial gating parameter value; Δε is the single gating parameter adjustment amount; ε1 is the gating parameter value after adaptive reduction.

[0092] (4) If after traversing all the data, K′ is always satisfied 1new <K' 2new , then keep the first and last data points and calculate C E , if C E >C E,th , process according to formula (15), return to the first data point, and go to step (1).

[0093] (5) There is a fluctuation segment between every two retained data points, and the fluctuation characteristics of each fluctuation segment are extracted.

[0094] The present invention establishes a dual error control system and designs a dynamic door width contraction algorithm. The BSO algorithm is used to optimize the initial door width of the revolving door algorithm at the global level, and a sliding window is used to verify the CE value (based on the percentage mean of the linear interpolation error) in real time locally. When the compression error of the local fluctuation segment exceeds the standard, the system automatically contracts the door width in micro-steps until the accuracy requirements are met.

[0095] In another implementation of the present invention, the fluctuation characteristics include fluctuation amplitude, fluctuation rate, fluctuation direction, and duration.

[0096] In another implementation of the present invention, the fluctuation amplitude ΔP is defined as the change in renewable energy power over a period of time, expressed as:

[0097] ΔP=|P(t n )-P(t m )| (16)

[0098] Where, P(t n ) is t n Renewable energy output at the moment; P(t m ) is t m Renewable energy output at the moment, meeting t n >t m .

[0099] In another implementation of the present invention, the fluctuation rate σ is defined as the fluctuation amount of renewable energy power per unit time, which is expressed as:

[0100]

[0101] In another implementation of the present invention, a method for determining the fluctuation direction of renewable energy is as follows:

[0102]

[0103] In another implementation of the present invention, the duration, i.e., the difference between the end time and the start time of the fluctuation segment, is expressed as:

[0104] Δt=t n -t m (19)

[0105] The identification method of the present invention can dynamically adjust the parameters of the identification algorithm according to the fluctuation of renewable energy output data, reduce the error caused by improper parameter selection, and effectively control the identification accuracy within a given range, which can better adapt to the problem of renewable energy volatility identification.

[0106] Another aspect of the present invention provides a renewable energy volatility identification system based on a parameter-adaptive revolving door algorithm, comprising:

[0107] Data acquisition module: used to obtain renewable energy power prediction data sets and corresponding time series sets.

[0108] Data processing module: used to determine the initial gate width for renewable energy volatility identification through the beetle swarm optimization algorithm.

[0109] Data calculation module: used to sequentially extract a prediction data and a corresponding time series from the data set and the corresponding time series set, and perform slope calculation in combination with the initial gate width to obtain the upper spiral gate slope and the lower spiral gate slope respectively.

[0110] The first judgment module is used to compare the slope of the upper spiral gate and the slope of the lower spiral gate. If the slope of the upper spiral gate is less than the slope of the lower spiral gate, the module returns to the data calculation module to recalculate the slope until the slope of the upper spiral gate is greater than or equal to the slope of the lower spiral gate, and the data point at the current moment is retained.

[0111] The second judgment module is used to calculate the average percentage absolute error of the fluctuation segment from the data point at the current moment to the data point at the previous moment. If the average percentage absolute error is greater than the average percentage absolute error threshold, the initial gate width is updated, and the data calculation module is returned to recalculate the slope and the average percentage absolute error until the current average percentage absolute error is less than or equal to the average percentage absolute error threshold, and the data point at the previous moment is retained.

[0112] Result output module: It is used to extract the fluctuation characteristics of each fluctuation segment, with a fluctuation segment between every two retained data points.

[0113] The renewable energy volatility identification system based on the parameter adaptive revolving door algorithm of the present invention adopts the beetle swarm optimization algorithm to optimize the renewable energy output data to be identified, obtains the initial gate width of the revolving door algorithm, and then adaptively expands and contracts the initial gate width based on the relative error to obtain fluctuation segments with different fluctuation characteristics, thereby improving the accuracy of volatility identification.

[0114] In another aspect of the present invention, an electronic device includes a processor, a memory, a communication bus, and a communication interface.

[0115] in:

[0116] The processor, memory and communication interface communicate with each other through a communication bus.

[0117] Communication interface, used to communicate with other electronic devices or servers.

[0118] The processor is configured to execute a program, and specifically may execute the steps of any one of the methods for identifying renewable energy volatility based on a parameter-adaptive revolving door algorithm in the above-mentioned embodiments.

[0119] Specifically, the program may include program codes including computer operation instructions.

[0120] The processor may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application. The one or more processors included in the smart device may be processors of the same type, such as one or more CPUs; or different types of processors, such as one or more CPUs and one or more ASICs.

[0121] Memory is used to store programs. The memory may include high-speed RAM memory, and may also include non-volatile memory (non-volatile memory), such as at least one disk storage.

[0122] The program can be specifically configured to cause a processor to execute the steps of any of the methods for identifying renewable energy fluctuations based on a parameter-adaptive revolving door algorithm described in the embodiments. The specific implementation of each step in the program can be found in the corresponding descriptions of the steps and units executed in any of the aforementioned methods for identifying renewable energy fluctuations based on a parameter-adaptive revolving door algorithm, and is not further described here. Those skilled in the art will clearly understand that, for ease and brevity of description, the specific operating processes of the devices and modules described above can be referenced to the corresponding process descriptions in the aforementioned method embodiments.

[0123] The exemplary embodiments of the present application further provide a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute the methods of the various embodiments of the present application.

[0124] The method according to the embodiment of the present invention described above can be implemented in hardware, firmware, or as software or computer code that can be stored in a recording medium (such as a CD ROM, RAM, floppy disk, hard disk or magneto-optical disk), or as computer code that is originally stored in a remote recording medium or a non-temporary machine-readable medium downloaded via a network and will be stored in a local recording medium, so that the method described herein can be stored in such software processing on a recording medium using a general-purpose computer, a dedicated processor or programmable or dedicated hardware (such as an ASIC or FPGA). It can be understood that a computer, a processor, a microprocessor controller or programmable hardware includes a storage component (e.g., RAM, ROM, flash memory, etc.) that can store or receive software or computer code, and when the software or computer code is accessed and executed by a computer, a processor or hardware, the method described herein is implemented. In addition, when a general-purpose computer accesses the code for implementing the method shown here, the execution of the code converts the general-purpose computer into a dedicated computer for executing the method shown here.

[0125] Thus far, specific embodiments of the present invention have been described. Other embodiments are within the scope of the appended claims. In some cases, the actions recited in the claims can be performed in a different order and still achieve the desired results. Additionally, the processes depicted in the accompanying drawings do not necessarily require the specific order shown, or sequential order, to achieve the desired results.

[0126] It should be noted that all directional indications in the embodiments of the present invention (such as up, down, left, right, back, etc.) are only used to explain the relative position relationship between the components in a certain specific order (as shown in the accompanying drawings). If the specific order changes, the directional indication will also change accordingly.

[0127] In the description of the present invention, the terms "first" and "second" are used solely to facilitate description of different components or names and should not be construed as indicating or implying a sequential relationship, relative importance, or implicitly specifying the quantity of the technical features being described. Therefore, features specified as "first" or "second" may explicitly or implicitly include at least one of such features.

[0128] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0129] It should be noted that although the specific embodiments of the present invention are described in detail in conjunction with the accompanying drawings, this should not be construed as limiting the scope of protection of the present invention. Within the scope described by the claims, various modifications and variations that can be made by those skilled in the art without creative effort still fall within the scope of protection of the present invention.

[0130] The examples of the embodiments of the present invention are intended to briefly illustrate the technical features of the embodiments of the present invention so that those skilled in the art can intuitively understand the technical features of the embodiments of the present invention, and are not intended to improperly limit the embodiments of the present invention.

[0131] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for identifying renewable energy volatility based on a parameter-adaptive revolving door algorithm, characterized in that: include: Step 1: Obtain the renewable energy power prediction dataset and the corresponding time series set; Step 2: Determine the initial threshold width for renewable energy volatility identification through the beetle swarm optimization algorithm; Step 3: From the data set and the corresponding time series set, sequentially extract a predicted data and the corresponding time series, and calculate the slope in combination with the initial gate width to obtain the upper spiral gate slope and the lower spiral gate slope respectively; Step 4: Compare the slope of the upper spiral gate with the slope of the lower spiral gate. If the slope of the upper spiral gate is less than the slope of the lower spiral gate, return to step 3 and recalculate the slope until the slope of the upper spiral gate is greater than or equal to the slope of the lower spiral gate, and retain the data point at the current moment; Step 5: Calculate the average percentage absolute error of the fluctuation segment from the current data point to the previous data point at the corresponding time. If the average percentage absolute error is greater than the average percentage absolute error threshold, update the initial gate width and return to step 3 to recalculate the slope and average percentage absolute error until the current average percentage absolute error is less than or equal to the average percentage absolute error threshold. Then retain the data point at the previous time. Step 6: There is a fluctuation segment between every two retained data points, and the fluctuation characteristics of each fluctuation segment are extracted.

2. The method according to claim 1, characterized in that The upper spiral gate slope and the lower spiral gate slope are expressed as: K' 1new =max(K1,K 1new ),K' 2new =min(K2,K 2new ) Among them, K 1new , K 2new is the initial value of the slope of the lower revolving door, K1 and K2 represent the slopes of the upper and lower revolving doors in the time series T respectively.

3. The method according to claim 1, characterized in that The mean percentage absolute error is calculated as follows: Among them, S m 、S n are the power values ​​restored proportionally after compression and the original power values ​​during the same period of time; m is the time interval from the last storage point to the detection point.

4. The method according to claim 1, wherein The fluctuation characteristics include fluctuation amplitude, fluctuation rate, fluctuation direction, and duration.

5. The method according to claim 4, characterized in that The fluctuation amplitude ΔP is expressed as: ΔP=|P(t n )-P(t m )| Where, P(t n ) is t n Renewable energy output at the moment; P(t m ) is t m Renewable energy output at the moment, meeting t n >t m .

6. The method according to claim 5, characterized in that The fluctuation rate is expressed as:

7. The method according to claim 5, characterized in that The fluctuation direction is expressed as:

8. A renewable energy volatility identification system based on parameter adaptive revolving door algorithm, characterized in that: include: Data acquisition module: used to obtain renewable energy power prediction data sets and corresponding time series sets; Data processing module: used to determine the initial gate width for renewable energy volatility identification through the beetle swarm optimization algorithm; Data calculation module: used to sequentially extract a predicted data and a corresponding time series from the data set and the corresponding time series set, and perform slope calculation in combination with the initial gate width to obtain the upper spiral gate slope and the lower spiral gate slope respectively; A first judgment module is used to compare the slope of the upper spiral gate with the slope of the lower spiral gate. If the slope of the upper spiral gate is less than the slope of the lower spiral gate, the module returns to the data calculation module to recalculate the slope until the slope of the upper spiral gate is greater than or equal to the slope of the lower spiral gate, and the data point at the current moment is retained; The second judgment module is used to calculate the average percentage absolute error of the fluctuation segment between the data point at the current moment and the data point at the previous moment. If the average percentage absolute error is greater than the average percentage absolute error threshold, the initial gate width is updated, and the data calculation module is returned to recalculate the slope and the average percentage absolute error until the current average percentage absolute error is less than or equal to the average percentage absolute error threshold, and the data point at the previous moment is retained. Result output module: It is used to extract the fluctuation characteristics of each fluctuation segment, with a fluctuation segment between every two retained data points.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of a renewable energy volatility identification method based on a parameter-adaptive revolving door algorithm as described in any one of claims 1 to 7 are implemented.

10. A computer storage medium, characterized in that The computer storage medium stores a computer program, which, when executed by a processor, implements the steps of the renewable energy volatility identification method based on a parameter-adaptive revolving door algorithm according to any one of claims 1 to 7.

Images