Frequency domain resonance enhancement and stochastic differential driven chirplet prediction method

Abstract

The present application relates to the technical field of power system, especially provide a kind of based on frequency domain resonance enhancement and stochastic differential drive frequency modulation sequence prediction method.The method includes constructing frequency domain mapping and resonance enhancement filter;Frequency domain enhancement and inverse transformation are carried out;Dynamic smoothing is carried out by constructing stochastic differential equation SDE;SDE is discretized, and the final optimized sequence is obtained;The frequency modulation sequence is predicted, and the predicted sequence is obtained, which improves the accurate prediction of power grid frequency modulation sequence and improves the stability of power grid frequency.

Description

Technical Field

[0001] This invention relates to the field of power system technology, and in particular to a frequency modulation sequence prediction method based on frequency domain resonance enhancement and stochastic differential drive. Background Technology

[0002] Against the backdrop of the accelerated construction of new power systems, the high proportion of renewable energy connected to the grid has led to increasingly complex grid frequency fluctuation characteristics, placing higher demands on frequency regulation capabilities. Hybrid energy storage systems, due to their millisecond-level response speed and flexible power support capabilities, have become key equipment for improving grid frequency stability. Their core control logic relies on the accurate prediction of the grid frequency regulation command sequence; the prediction accuracy directly affects the optimization of the energy storage unit's charging and discharging strategies, lifetime management, and overall frequency regulation performance. However, the grid frequency regulation sequence is essentially a time-domain mapping of the grid's unbalanced power, and is simultaneously affected by multiple factors such as unit start-up and shutdown, load abrupt changes, and the intermittent output of renewable energy, exhibiting strong non-stationarity, nonlinearity, and high noise characteristics. These sequences often contain multiple time-scale characteristics: including slow trend components determined by system inertia, as well as instantaneous spikes caused by random disturbances. Traditional time series prediction models struggle to directly and effectively extract generalizable regularities from the raw data.

[0003] Existing prediction techniques typically rely on direct processing of the original sequence, facing fundamental bottlenecks. First, while conventional preprocessing methods such as Kalman filtering or moving averages can smooth noise, they have significant drawbacks: using fixed parameters and linear assumptions, while filtering out high-frequency noise, they inevitably weaken the burst components and short-time frequency domain features carrying crucial dynamic information in the sequence, leading to feature degradation of the input signal for the prediction model. Second, while methods based on frequency domain wavelet transforms can extract multi-scale features, the selection of their decomposition modes is highly dependent on prior knowledge, and the reconstruction prediction of different mode components suffers from phase lag and energy leakage problems, making it difficult to guarantee temporal consistency. A deeper problem lies in the fact that existing methods generally treat denoising and feature extraction as two independent stages, failing to construct the preprocessing process from the perspective of system dynamic evolution. This results in processed sequences with improved statistical properties but ambiguous physical meaning, making it difficult for the prediction model to establish a reliable causal relationship between input and output. Summary of the Invention

[0004] In view of this, the present invention provides a frequency modulation sequence prediction method based on frequency domain resonance enhancement and stochastic differential driving, which can improve the accuracy of power grid frequency modulation sequence prediction and enhance the stability of power grid frequency.

[0005] In a first aspect, the present invention provides a frequency modulation sequence prediction method based on frequency domain resonance enhancement and stochastic differential driving, the method comprising:

[0006] Step 1: Construct a frequency domain mapping and resonance enhancement filter;

[0007] Step 2: Based on Step 1, perform frequency domain enhancement and inverse transform;

[0008] Step 3: Based on Step 2, construct the stochastic differential equation SDE for dynamic smoothing;

[0009] Step 4: Using the method from step 3, discretize the SDE to obtain the final optimized sequence;

[0010] Step 5: Based on step 4, predict the frequency modulation sequence to obtain the predicted sequence.

[0011] Optionally, step 1 includes:

[0012] First, the original frequency modulation sequence The frequency domain signal expression after mapping to the frequency domain via Fast Fourier Transform (FFT) is as follows:

[0013] ;

[0014] in, ; For the complex components in the frequency domain i It is the imaginary unit.

[0015] Optionally, step 1 further includes:

[0016] Constructing a resonant enhancement filter Its bandwidth and peak position are related to the characteristic frequencies of the sequence. The relevant expression for the resonant enhancement filter is:

[0017] ;

[0018] in, For the first k The angular frequency corresponding to each frequency point ; Bandwidth parameters ; =2 and =0.5 are the gain and offset constants, respectively, used to control the magnitude of the enhancement.

[0019] Optionally, step 2 includes:

[0020] frequency domain signal With resonant enhancement filter Multiply to obtain the enhanced frequency domain signal. Then, it is mapped back to the time domain using the inverse Fourier transform (IFFT), and its expression is:

[0021] ;

[0022] ;

[0023] in, This is the intermediate sequence after frequency domain resonance enhancement.

[0024] Optionally, step 3 includes:

[0025] The enhanced intermediate sequence Treating the external force acting on a virtual Brownian particle, we construct a variant of the Ornstein-Uhlenbeck (OU) process for it, and use its steady-state solution as the final output; we define the stochastic differential equation SDE, whose expression is:

[0026] ;

[0027] in, The optimized sequence; The long-term mean of the time-varying value is set as follows: That is, the enhanced sequence; The mean regression rate parameter, =0.5, used for control Towards The speed of regression; For volatility parameters, ; For the virtual Wiener process increment.

[0028] Optionally, step 4 includes:

[0029] The SDE is discretized and solved using the Euler-Maruyama method to obtain the final optimized sequence, which is expressed as follows:

[0030] .

[0031] Optionally, step 5 includes:

[0032] The original frequency modulation sequence Transform into ,right The prediction formula is as follows:

[0033] ;

[0034] in, =1, Let them be independent and identically distributed standard normal random variables, i.e. ~N(0,1); , avg This represents the mean;

[0035] .

[0036] Optionally, it includes: to The prediction formula is as follows:

[0037] ;

[0038] in, ;

[0039] ;

[0040] By analogy, the prediction can be made. ; Q To predict the length of the sequence, Q Less than , Indicates rounding down.

[0041] In a second aspect, embodiments of the present invention provide a computer-readable storage medium comprising a stored program, wherein, when the program is executed, it controls the device on which the computer-readable storage medium is located to execute the frequency modulation sequence prediction method based on frequency domain resonance enhancement and stochastic differential driving in the first aspect or any possible implementation thereof.

[0042] Thirdly, embodiments of the present invention provide an electronic device, including: one or more processors; a memory; and one or more computer programs, wherein the one or more computer programs are stored in the memory, and the one or more computer programs include instructions that, when executed by the device, cause the device to perform the frequency modulation sequence prediction method based on frequency domain resonance enhancement and stochastic differential driving in the first aspect or any possible implementation of the first aspect.

[0043] The technical solution provided by this invention includes constructing a frequency domain mapping and resonance enhancement filter; performing frequency domain enhancement and inverse transformation; constructing a stochastic differential equation (SDE) for dynamic smoothing; discretizing the SDE to obtain the final optimized sequence; and predicting the frequency modulation sequence to obtain the predicted sequence. This method improves the accuracy of predicting the power grid frequency modulation sequence and enhances the stability of the power grid frequency. Attached Figure Description

[0044] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0045] Figure 1 A flowchart illustrating the frequency modulation sequence prediction method based on frequency domain resonance enhancement and stochastic differential driving provided in an embodiment of the present invention;

[0046] Figure 2 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0047] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0048] It should be understood that the described embodiments are merely some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0049] The terminology used in the embodiments of this invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. The singular forms “a,” “the,” and “the” used in the embodiments of this invention are also intended to include the plural forms unless the context clearly indicates otherwise.

[0050] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0051] Depending on the context, the word "if" as used here can be interpreted as "when," "when," "in response to determination," or "in response to detection." Similarly, depending on the context, the phrase "if determination" or "if detection (of the stated condition or event)" can be interpreted as "when determination," "in response to determination," "when detection (of the stated condition or event)," or "in response to detection (of the stated condition or event)."

[0052] Figure 1 The flowchart of the frequency modulation sequence prediction method based on frequency domain resonance enhancement and stochastic differential driving provided in the embodiments of the present invention is as follows: Figure 1 As shown, the method includes:

[0053] Step 1: Construct frequency domain mapping and resonance enhancement filter.

[0054] In this embodiment of the invention, step 1 includes:

[0055] First, the original frequency modulation sequence The frequency domain signal expression after mapping to the frequency domain via Fast Fourier Transform (FFT) is as follows:

[0056] ;

[0057] in, ; For the complex components in the frequency domain i It is the imaginary unit.

[0058] In this embodiment of the invention, the original frequency modulation sequence is... Mapping from the time domain to the frequency domain identifies the frequency components in the sequence, providing a foundation for subsequent frequency domain enhancement.

[0059] In this embodiment of the invention, step 1 further includes:

[0060] Constructing a resonant enhancement filter The filter's gain peaks near a specific frequency, and its bandwidth and peak location are related to the sequence's characteristic frequency (system core frequency). The relevant expression for the resonant enhancement filter is:

[0061] ;

[0062] in, For the first k The angular frequency corresponding to each frequency point ; (Select the frequency point with the strongest spectral energy); bandwidth parameters (Narrow bandwidth to enhance selectivity); =2 and =0.5 are the gain and offset constants, respectively, used to control the magnitude of the enhancement.

[0063] In this embodiment of the invention, the resonant enhancement filter exhibits a fourth-power steep drop characteristic; =2 can amplify the target frequency band, offset constant This can prevent the gain from dropping to zero in the low-frequency band. =0.5 preserves the basic signal. The fourth-power design ensures the target frequency band... Internal gain close + External decay to This significantly improves the signal-to-noise ratio in key frequency bands.

[0064] Step 2: Based on Step 1, perform frequency domain enhancement and inverse transformation.

[0065] In this embodiment of the invention, step 2 includes:

[0066] frequency domain signal With resonant enhancement filter Multiply to obtain the enhanced frequency domain signal. Then, it is mapped back to the time domain using the inverse Fourier transform (IFFT), and its expression is:

[0067] ;

[0068] ;

[0069] in, This is the intermediate sequence after frequency domain resonance enhancement.

[0070] In this embodiment of the invention, the enhanced frequency domain signal is reconstructed into a time domain sequence. While preserving the physical essence, it amplifies the key features.

[0071] Step 3: Based on Step 2, construct the stochastic differential equation SDE for dynamic smoothing.

[0072] In this embodiment of the invention, step 3 includes:

[0073] The enhanced intermediate sequence Treating the external force acting on a virtual Brownian motion particle, we construct a variant of the Ornstein-Uhlenbeck (OU) process for it, and use its steady-state solution as the final output; we define the stochastic differential equation SDE, whose expression is:

[0074] ;

[0075] in, The optimized sequence (continuous form); The long-term mean of the time-varying value is set as follows: That is, the enhanced sequence; The mean regression rate parameter, =0.5, used for control Towards The speed of regression ( The larger, The faster the tracking ); For volatility parameters, Volatility is correlated with the standard deviation of the original sequence; For the virtual Wiener process (Brownian motion) increment.

[0076] In this embodiment of the invention, the physical meaning of the SDE is as follows: As a virtual smooth frequency modulation power, it is subject to a boost signal to the current signal. The regressive force, simultaneously subjected to a random perturbation, will result in a solution that is a smoother sequence that fluctuates around the amplifying signal, i.e. In enhancing signal Nearby fluctuations, Balancing tracking ability and smoothness Retain reasonable random disturbances.

[0077] Step 4: Using the method from step 3, discretize the SDE to obtain the final optimized sequence.

[0078] In this embodiment of the invention, step 4 includes:

[0079] The SDE is discretized and solved using the Euler-Maruyama method to obtain the final optimized sequence, which is expressed as follows:

[0080] .

[0081] Step 5: Based on step 4, predict the frequency modulation sequence to obtain the predicted sequence.

[0082] In this embodiment of the invention, step 5 includes:

[0083] The original frequency modulation sequence Transform into ,right The prediction formula is as follows:

[0084] ;

[0085] in, =1, Let them be independent and identically distributed standard normal random variables, i.e. ~N(0,1); (Dynamically updated historical average) avg This represents the mean;

[0086] .

[0087] In this embodiment of the invention, it includes: [the following is a list of components / specifications] The prediction formula is as follows:

[0088] ;

[0089] in, This ensures that the mean is corrected in real time.

[0090] ;

[0091] By analogy, the prediction can be made. ; Q To predict the length of the sequence, Q Less than , Indicates rounding down.

[0092] In this embodiment of the invention, dynamic To enable predictions to continuously adapt to sequence changes, The historical values ​​of the decay items are weighted to highlight recent trends.

[0093] In a frequency modulation system, the original frequency modulation sequence The subscript indicates the number of samples, with one sample taken per second. N ≥300; The core of this invention is to treat the original frequency-modulated sequence as an observation of a virtual physical system (such as a frequency-modulated energy field), map it to the frequency domain, and design a resonance enhancement filter to amplify a specific frequency band containing key prediction information. Subsequently, a stochastic differential equation (SDE) is introduced to simulate the system dynamics, and finally the SDE is discretized and solved to obtain the optimized sequence, thus obtaining a smoother and more regular sequence.

[0094] In this embodiment of the invention, simulated data verification is performed:

[0095] Input data: Assume the original frequency modulation sequence =[0.1,0.5,-0.2,0.7,-0.4] N =5, Target Prediction X 6;

[0096] First, frequency domain enhancement is performed:

[0097] Obtained through Fast Fourier Transform (FFT) :

[0098] =[0.7,-0.25+0.4i,-0.1,-0.25-0.4i];

[0099] calculate :|| If ||=[0.7,0.47,0.1,0.47], then argmax|| ||=1, = / 5;

[0100] Constructing a resonant enhancement filter ( =2, =0.5):

[0101] =[2.5,1.8,0.5,1.8]( (where the gain is maximum).

[0102] Inverse transformation yields =[0.12,0.52,-0.18,0.68,-0.37].

[0103] Secondly, SDE dynamic smoothing:

[0104] parameter: =0.5, =0.1×std( ) = 0.05;

[0105] initialization , =0.12;

[0106] recursion :

[0107] ,Pick =0.3, then ≈0.14;

[0108] The final optimized sequence =[0.12,0.14,-0.05,0.41,-0.12].

[0109] Finally, prediction :

[0110] = avg ( =0.1;

[0111] ;

[0112] Predicted value .

[0113] The technical solution provided by this invention includes constructing a frequency domain mapping and resonance enhancement filter; performing frequency domain enhancement and inverse transformation; constructing a stochastic differential equation (SDE) for dynamic smoothing; discretizing the SDE to obtain the final optimized sequence; and predicting the frequency modulation sequence to obtain the predicted sequence. This method improves the accuracy of predicting the power grid frequency modulation sequence and enhances the stability of the power grid frequency.

[0114] The various steps in the embodiments of the present invention can be performed by an electronic device. This electronic device includes, but is not limited to, tablet computers, portable PCs, and desktop computers.

[0115] This invention provides a computer-readable storage medium including a stored program, wherein, when the program is running, it controls the electronic device containing the computer-readable storage medium to execute the above-described embodiment of the frequency modulation sequence prediction method based on frequency domain resonance enhancement and stochastic differential driving.

[0116] Figure 2 A schematic diagram of an electronic device provided in an embodiment of the present invention, such as... Figure 2 As shown, the electronic device 21 includes a processor 211, a memory 212, and a computer program 213 stored in the memory 212 and executable on the processor 211. When the computer program 213 is executed by the processor 211, it implements the frequency modulation sequence prediction method based on frequency domain resonance enhancement and random differential driving in the embodiment. To avoid repetition, it will not be described in detail here.

[0117] Electronic device 21 includes, but is not limited to, processor 211 and memory 212. Those skilled in the art will understand that... Figure 2 This is merely an example of electronic device 21 and does not constitute a limitation on electronic device 21. It may include more or fewer components than shown, or combine certain components, or different components. For example, electronic device may also include input / output devices, network access devices, buses, etc.

[0118] The processor 211 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0119] The memory 212 can be an internal storage unit of the electronic device 21, such as a hard disk or RAM of the electronic device 21. The memory 212 can also be an external storage device of the electronic device 21, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, or FlashCard equipped on the electronic device 21. Furthermore, the memory 212 can include both internal and external storage units of the electronic device 21. The memory 212 is used to store computer programs and other programs and data required by network devices. The memory 212 can also be used to temporarily store data that has been output or will be output.

[0120] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0121] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for predicting frequency-modulated sequence based on frequency domain resonance enhancement and stochastic differential drive, characterized in that, The method comprises: Step 1, constructing a frequency domain mapping and resonance enhancement filter; Step 2, according to step 1, performing frequency domain enhancement and inverse transformation; Step 3, based on step 2, constructing a stochastic differential equation (SDE) for dynamic smoothing; Step 4, using step 3, discretizing the SDE to obtain a final optimized sequence; Step 5, according to step 4, predicting the frequency modulation sequence to obtain a predicted sequence; The step 1 comprises: First, the original frequency modulation sequence The frequency domain signal expression of the frequency domain transform is: ； wherein ; is a complex component in the frequency domain, i is the imaginary unit; The step 1 further comprises: Constructing a resonance-enhanced filter whose bandwidth and peak position are related to the characteristic frequency of the sequence The expression for the resonance-enhanced filter is ； wherein, is the angular frequency corresponding to the k th frequency bin, ; ; the bandwidth parameter ; = 2 and = 0.5 are gain and offset constants, respectively, for controlling the amplitude of the enhancement; The step 3 comprises: The enhanced intermediate sequence Considering the external force as a virtual Brownian motion particle, a variant of the Ornstein-Uhlenbeck (OU) process is constructed, and its steady-state solution is used as the final output. A stochastic differential equation (SDE) is defined, and its expression is as follows: ； where, is the optimized sequence; is the time-varying long-term mean, set to is the enhanced sequence; is the mean reversion rate parameter, = 0.5, used to control the speed of reversion; is the volatility parameter, ; is the virtual Wiener process increment; The step 4 comprises: The Euler-Maruyama method is used to discretize and solve the SDE to obtain the final optimized sequence, and the expression is: ； The step 5 comprises: The original frequency modulation sequence is converted into , a prediction is made, the prediction formula of which is: ​ ； wherein = 1, are independent and identically distributed standard normal random variables, i.e. ~ N(0, 1); , avg denotes the mean; 。 2. The method of claim 1, wherein, The step 2 comprises: The frequency domain signal is multiplied with a resonance enhancement filter to obtain an enhanced frequency domain signal which is mapped back to the time domain by an inverse Fourier transform IFFT, which is expressed as ； ； wherein is the intermediate sequence after frequency domain resonance enhancement.

3. The method of claim 1, wherein, Including: To Prediction is made with the following formula: ； wherein ; ； By analogy, it is predicted that ; Q To predict the length of the sequence, Q Less than , Indicates rounding.

4. A computer-readable storage medium, characterized in that, The computer readable storage medium comprises a stored program, wherein the program controls the device where the computer readable storage medium is located to execute the frequency modulation sequence prediction method based on frequency domain resonance enhancement and stochastic differential drive according to any one of claims 1-3 when the program is running.

5. An electronic device, comprising: Including: One or more processors; Memory; And one or more computer programs, wherein the one or more computer programs are stored in the memory, and the one or more computer programs comprise instructions which, when executed by the device, cause the device to execute the frequency modulation sequence prediction method based on frequency domain resonance enhancement and stochastic differential drive according to any one of claims 1-3.

Images