CN116933022A - Intelligent synchronous alignment preprocessing method and system for data of multi-source load equipment - Google Patents
Intelligent synchronous alignment preprocessing method and system for data of multi-source load equipment Download PDFInfo
- Publication number
- CN116933022A CN116933022A CN202311181371.XA CN202311181371A CN116933022A CN 116933022 A CN116933022 A CN 116933022A CN 202311181371 A CN202311181371 A CN 202311181371A CN 116933022 A CN116933022 A CN 116933022A
- Authority
- CN
- China
- Prior art keywords
- data
- sampling
- interpolation
- function
- source load
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 59
- 230000001360 synchronised effect Effects 0.000 title claims abstract description 50
- 238000007781 pre-processing Methods 0.000 title claims abstract description 33
- 238000005070 sampling Methods 0.000 claims abstract description 130
- 238000005259 measurement Methods 0.000 claims abstract description 77
- 238000012937 correction Methods 0.000 claims abstract description 49
- 238000012549 training Methods 0.000 claims abstract description 41
- 238000012545 processing Methods 0.000 claims abstract description 35
- 238000004364 calculation method Methods 0.000 claims abstract description 27
- 238000010606 normalization Methods 0.000 claims abstract description 22
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 14
- 239000013589 supplement Substances 0.000 claims abstract description 3
- 230000009469 supplementation Effects 0.000 claims description 18
- 238000010276 construction Methods 0.000 claims description 8
- 239000011159 matrix material Substances 0.000 claims description 8
- 238000004458 analytical method Methods 0.000 claims description 6
- 238000004422 calculation algorithm Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 6
- 101100391182 Dictyostelium discoideum forI gene Proteins 0.000 claims description 3
- 238000012850 discrimination method Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 6
- 230000006870 function Effects 0.000 description 75
- 238000012360 testing method Methods 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 4
- 238000009826 distribution Methods 0.000 description 3
- 238000013507 mapping Methods 0.000 description 3
- 238000012952 Resampling Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 239000000835 fiber Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 230000001902 propagating effect Effects 0.000 description 2
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 229910052802 copper Inorganic materials 0.000 description 1
- 239000010949 copper Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Chemical compound O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
- G06F18/15—Statistical pre-processing, e.g. techniques for normalisation or restoring missing data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/15—Correlation function computation including computation of convolution operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0475—Generative networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/094—Adversarial learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Business, Economics & Management (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Databases & Information Systems (AREA)
- Algebra (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Probability & Statistics with Applications (AREA)
- Economics (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Evolutionary Biology (AREA)
- Public Health (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Water Supply & Treatment (AREA)
- Operations Research (AREA)
- Computer Vision & Pattern Recognition (AREA)
Abstract
A multisource load device data intelligent synchronous alignment preprocessing method and system, the method includes: sampling measurement data of multi-source load equipment in a novel power system to obtain sampling data of the measurement data; establishing a cubic spline interpolation function, determining a correction amount in the function, and carrying out normalization processing on calculation parameters of the function; constructing and training a WGAN network based on the data characteristics of multi-source load equipment in a novel power system, and generating interpolation data to interpolate and supplement sampling data of measurement data; re-establishing a cubic spline interpolation function, and carrying out Crout decomposition and solving on the function to obtain an optimal correction; and synchronous interpolation processing is carried out on sampling data of the multi-source load equipment measurement data by utilizing a cubic spline interpolation function for determining the optimal correction amount, so that intelligent synchronous alignment preprocessing of the data is realized. The application obtains the synchronous alignment pretreatment effect of the measurement data of the novel power system multi-source load equipment with higher speed.
Description
Technical Field
The application belongs to the technical field of data of power data equipment, and relates to an intelligent synchronous alignment preprocessing method and system for data of multi-source load equipment.
Background
Compared with the traditional power grid, the novel power system has more diversified constituent elements, and along with the fact that type equipment such as distributed photovoltaic, electric vehicles and adjustable loads is connected into a regional power distribution network, the complexity of power equipment and circuit layout used by a main network and a distribution network is improved progressively, sampling periods of various measurement data are different, and the novel power system has the characteristics of multiple feature sets, multiple representations, multiple collection points, isomerism and the like.
In terms of basic data preprocessing, conventional methods generally enhance the correctness of state estimation by robust error-free calculation of erroneous data or by reducing the weights of erroneous data. However, for multi-source measurement heterogeneous data with different sampling periods such as distributed photovoltaics, electric vehicles and adjustable loads in a novel power system, the intelligent alignment preprocessing method aiming at equipment characteristics and space-time characteristics under a unified time scale is lacking, so that advanced application functions are prevented from being extended in an analysis range and calculation accuracy is improved, synchronous alignment preprocessing level of base number measurement data is required to be improved, and a high-quality data basis is provided for state estimation.
Disclosure of Invention
In order to solve the defects in the prior art, the application provides an intelligent synchronous alignment preprocessing method and system for multi-source load equipment data, which are used for analyzing measurement data with different sampling periods in a novel power system, carrying out normalization processing based on a cubic spline interpolation function and power system data characteristics, then designing a WGAN network structure to generate interpolation data which is more in line with actual conditions, providing more accurate calculation data for the interpolation function, and finally solving to obtain a sampling data sequence with synchronization error of 0 hedging so as to realize intelligent synchronous alignment of the multi-source load equipment data.
The application adopts the following technical scheme.
The intelligent synchronous alignment preprocessing method for the data of the multi-source load equipment comprises the following steps:
step 1, sampling measurement data of multi-source load equipment in a novel power system to obtain sampling data of the measurement data;
step 2, establishing a cubic spline interpolation function for sampling data of the measurement data, determining correction quantity in the function, and carrying out normalization processing on calculation parameters of the function;
step 3, constructing and training a Wasserstein generation countermeasure network WGAN based on the data characteristics of the multi-source load equipment in the novel power system, generating interpolation data by adopting the trained Wasserstein generation countermeasure network WGAN, and carrying out interpolation supplementation on sampling data of the measurement data;
step 4, reestablishing a cubic spline interpolation function by adopting the sample data after interpolation supplementation, and carrying out Kellow Crout decomposition and solving on the function to obtain the optimal correction quantity of the correction quantity determined in the step 2;
and 5, performing synchronous interpolation processing on sampling data of the multi-source load equipment measurement data by utilizing a cubic spline interpolation function for determining the optimal correction amount, so as to realize intelligent synchronous alignment preprocessing of the data.
Preferably, in step 1, the multi-source load device measurement data includes voltage, current, power, and switch state data of the distributed photovoltaic, the electric vehicle charging pile, and the adjustable load device.
Preferably, in step 2, sampling data of various measurement data of the multi-source load device in the novel power system is performed in time intervals [ T1, tn ]]In, establish sampling dataS i Is a cubic spline interpolation function of:
wherein ,i、Respectively sampling sequence numbers and sampling time;
interpolation function for cubic spline;
、/>sample data for i-1 and i;
、/>first derivatives for the i-1 and i-th sample data;
,/>is the sampling interval between the i-1 th and i-th sampled data points.
Preferably, in step 2, the data is sampledS i The cubic spline interpolation function of (2) is decomposed, and the correction amount in the interpolation function is determined, wherein the concrete process is as follows:
order theThen->Then willS i Is rewritten as:
，
，
，
，
，
wherein ,is only equal to the sampling interval t and +.>Correlation, by coefficient relation analysis of interpolation function, will +.>Further decomposed into:
S(T)=
wherein ,is a linear interpolation +.>Nonlinear part, ++> and />It cannot be directly obtained and is regarded as a correction amount.
Preferably, in step 2, according to the data characteristics of the power system, the calculation parameters in the interpolation function are normalized based on a cubic spline interpolation algorithm, and the specific process is as follows:
let the signal period of various load measurement data beT m The number of sampling points in each signal period is n, the sampling interval between two sampling pointsIs regarded as a constant of the size ofT m /nThe sampled data of each device is normalized on the basis:
sampling intervalRegarding as a standard quantity 1, if normalization processing is performed, the sampling time T is entirely extended by n +.T m The number of times of the number of times,then enlarge n as a whole 2 /T m 2 The interpolation interval is also followed by [T 1 ,T n ]Becomes [1, n ]]；
After normalization processing, the cubic spline interpolation function is changed into:
，
，
，
，
。
preferably, in step 3, the WGAN network includes a generator and a discriminator, and uses the historical measurement data of the load device as sample data, and samples the sample data in the sampling manner of step 1 (i.e. using the sampling frequency of step 1) to obtain the original dataPDownsampling the sample data with equal sampling interval to obtain downsampled data；
Raw dataPAnd downsampling dataForming a training set to train the WGAN network, determining the parameters of the WGAN network, and obtaining a trained WGAN network, wherein the specific training process comprises the following steps:
raw dataPAnd downsampling dataRespectively performing N-N cutting, inputting into a generator for training, and generating according to the original dataPAnd downsampled data->Generates and outputs a duplicate of the mapping relation of (2)Constructional data->，/> and />Common input discriminant for discriminant training with the final goal of +.> and />The smaller the error between them, the better.
Preferably, the loss function used by the generator in the training process is:
，
wherein ,in order for the training set to be a set of training,Mis a sampling matrix;
matrix arrayMIs an N matrix, wherein the ith row and the jth elementIndicating whether the data obtained by downsampling is the same as the data obtained by using the sampling mode of the step 1, if so, the element is 1, otherwise, the element is 0.
Preferably, in step 3, the sampled data of the measurement data obtained in step 1 is input into a trained WGAN network to generate corresponding interpolation data, and the sampled data of the measurement data is subjected to equidistant interpolation and supplementation to obtain the interpolated and supplemented sampled data.
Preferably, step 4 comprises:
step 41, dividing the [ T1, tn ] time interval into n parts, integrating the cubic spline interpolation function based on the sample data after interpolation supplement, and establishing the following equation at the sampling point and the interpolation point, namely, continuously equaling the equation of the first derivative and the second derivative of the reconstructed cubic spline interpolation function:
，
wherein ,, />,/>；
meanwhile, after normalization processing is carried out on the sampling data after interpolation, and />Constant 1/2;
step 42, calculating correction by using Crout decomposition and regression solution for the reestablished continuous equality equation of the first and second derivatives of the cubic spline interpolation function：
Crout decomposition is performed on the equation and and />For 1/2 carry-in calculation:
will beIs decomposed intoLU；
wherein ,Lin order to form a lower triangular array, the lower triangular array is provided with a plurality of triangular grooves,Uis an upper triangular array;
first calculateLIs recalculated in the first column of (2)UThen calculates the second column of L, and so on, resulting in:
，
，
，
，
to be used forIs the initial value, is subjected to continuous iterative computation +.> and />According to the iterative convergence discrimination method, when the error is、/>When all meet the requirement, the iteration is completed to obtain the optimal correction amount +.>, wherein />Is the last element of the lower triangular array and the upper triangular array.
The intelligent synchronous alignment preprocessing system for the data of the multi-source load equipment comprises the following components:
the data sampling module is used for sampling the measurement data of the multi-source load equipment in the novel power system to obtain sampling data of the measurement data;
the interpolation function construction module is used for establishing a cubic spline interpolation function for sampling data of the measurement data, determining correction quantity in the function and carrying out normalization processing on calculation parameters of the function;
the Wasserstein generation countermeasure network WGAN construction module is used for constructing and training the Wasserstein generation countermeasure network WGAN based on the multi-source load equipment data characteristics in the novel power system, generating interpolation data by adopting the trained Wasserstein generation countermeasure network WGAN, and carrying out interpolation supplementation on the sampling data of the measurement data;
the correction quantity solving module is used for reestablishing a cubic spline interpolation function by adopting the sample data after interpolation supplementation and carrying out Kellow Crout decomposition and solving on the function to obtain the optimal correction quantity of the correction quantity determined by the interpolation function constructing module;
and the preprocessing module is used for carrying out synchronous interpolation processing on the sampling data of the multi-source load equipment measurement data by utilizing a cubic spline interpolation function for determining the optimal correction amount, so as to realize intelligent synchronous alignment preprocessing of the data.
A terminal comprising a processor and a storage medium; the storage medium is used for storing instructions; the processor is configured to operate in accordance with the instructions to perform the steps of the method.
A computer readable storage medium having stored thereon a computer program which when executed by a processor realizes the steps of the method.
The application has the beneficial effects that compared with the prior art:
aiming at the condition that sampling periods of multi-source load equipment measurement data in a novel power system are not aligned, the normalization processing method based on the cubic spline interpolation calculation parameters is designed based on the integral characteristics of the sampling data and the electrical measurement characteristics of the power system equipment, and the interpolation calculation amount can be effectively reduced. Meanwhile, based on the characteristic of a cubic spline interpolation function, the method has higher sampling precision on the sampling signal with higher harmonic interference.
The application designs a novel intelligent generation method for measuring data interpolation of power system multi-source load equipment based on a Wasserstein generating countermeasure network WGAN deep learning network, which takes real measuring data and construction data as input, continuously corrects network parameters in the continuous game process of a generator and a discriminator to generate the most reasonable interpolation data, and improves the data sampling and synchronization precision of interpolation functions.
According to the application, an interpolation function is constructed based on original data and automatically generated data, the solving interpolation function is simplified into solving correction quantity, the calculated quantity is effectively reduced, the Crout decomposition and the back-generation solving are utilized, the calculation result closest to the convergence value is obtained by continuous iteration, the more accurate synchronous alignment pretreatment effect of the multi-source load equipment measurement data of the novel power system is obtained at a higher speed, the synchronous alignment pretreatment level of the basic number measurement data is improved, and a high-quality data basis is provided for state estimation.
Drawings
FIG. 1 is a flow chart of a method for intelligent synchronous alignment preprocessing of multi-source load equipment data;
FIG. 2 is a flow chart of the application Wasserstein generation of interpolated data against network WGAN generation;
FIG. 3 is a logic flow diagram of the measurement data synchronization process of the multi-source load device of the novel power system.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. The described embodiments of the application are only some, but not all, embodiments of the application. All other embodiments, which can be made by those skilled in the art without making any inventive effort, are within the scope of the present application.
As shown in fig. 1, embodiment 1 of the present application provides a method for intelligent synchronous alignment pretreatment of multi-source load device data, which aims at the situation that sampling periods of multi-source load device measurement data in a novel power system are not aligned, and starts from the integral characteristics of sampling data, performs calculation parameter normalization treatment based on a cubic spline interpolation algorithm and the measurement data characteristics of the novel power system device, then, in order to obtain a better interpolation effect, improves data interpolation precision, performs power device measurement data interpolation based on wasser tein to generate an countermeasure network (WGAN), and finally, performs intelligent synchronous alignment on distributed photovoltaic, electric vehicle charging facilities, adjustable load and other heterogeneous devices in the novel power system and space-time characteristics thereof, and provides a high quality data basis for feature extraction and analysis.
In a preferred but non-limiting embodiment of the present application, the intelligent synchronization alignment preprocessing method for multi-source load equipment data includes the following steps 1-5:
step 1, sampling measurement data of multi-source load equipment in a novel power system to obtain sampling data of the measurement data;
further preferably, the multi-source load device measurement data includes data such as voltage, current, power, and switch state of devices such as distributed photovoltaic, electric vehicle charging piles, adjustable loads, and the like.
Step 2, establishing a cubic spline interpolation function for sampling data of the measurement data, determining correction quantity in the function, and carrying out normalization processing on calculation parameters of the function;
step 2, analyzing sampling data of various multi-source load devices in a novel power system in a designated time interval, and establishing a cubic spline interpolation function; according to the data characteristics of the electric power system, carrying out normalization processing on calculation parameters in the interpolation function based on a cubic spline interpolation algorithm;
further preferably, the specific process of step 2 is as follows:
(1) Sampling data of various measurement data of multi-source load equipment in novel power system in time interval [T 1 ,T n ]In, establish sampling dataS i Is a cubic spline interpolation function of:
wherein ,i、Respectively is samplingSequence number and sampling time;
interpolation function for cubic spline;
、/>sample data for i-1 and i;
、/>first derivatives for the i-1 and i-th sample data;
,/>is the sampling interval between the i-1 th and i-th sampled data points.
(2) For sampling signalsS i The cubic spline interpolation function of (2) is decomposed to determine the correction amount in the interpolation function, and the method concretely comprises the following steps:
to simplify the interpolation functionExpression form, let->Then->ThenS i Can be rewritten as a cubic spline interpolation function
，
，
，
，
，
It can be seen that the light source is,is only equal to the sampling interval t and +.>Correlation, and by performing a coefficient relation analysis on the interpolation function +.>Further decomposed into
S(T)=
wherein ,is a linear interpolation +.>The nonlinear part can be regarded as a correction function. t and->Is of known quantity, but-> and />It cannot be directly found and is regarded as a correction amount. And determining the proper correction quantity to establish a proper cubic spline interpolation function.
(3) According to the data characteristics of the electric power system, the calculation parameters in the interpolation function are normalized based on a cubic spline interpolation algorithm, and the method specifically comprises the following steps:
according to the characteristic that the fluctuation of the equidistant sampling time period of various load equipment in the power system is small, the signal period of various load measurement data is set asT m The number of sampling points in each signal period is n, the sampling interval between two sampling pointsCan be regarded as a constant of the size ofT m /nThe sampled data of each device is normalized on the basis:
sampling intervalRegarding the standard quantity 1, if normalization processing is performed, the sampling time T is expanded by n +.T m Multiple of (I)>Then overall enlarge n 2 /T m 2 The interpolation interval is also followed by [T 1 ,T n ]Becomes [1, n ]]；
After normalization processing, the cubic spline interpolation function is changed into:
，
，
，
，
。
step 3, constructing and training a Wasserstein generation countermeasure network WGAN based on the data characteristics of the multi-source load equipment in the novel power system, generating interpolation data by adopting the trained Wasserstein generation countermeasure network WGAN, and carrying out interpolation supplementation on sampling data of the measurement data;
the step 3 establishes a WGAN network structure, and learns mapping between two probability distributions of downsampled data and original sampled data on the premise of not making corresponding assumptions on the data so as to improve the intelligence level and rationality of data interpolation.
Further preferably, the WGAN network includes a generator and a discriminator, and uses the historical measurement data of the load device as sample data, and samples the sample data by adopting the sampling mode (i.e. sampling frequency) of step 1 to obtain the original dataPDownsampling the sample data at equal sampling intervals to obtain downsampled data；
Raw dataPAnd downsampling dataForming a training set to train the WGAN network, determining the parameters of the WGAN network, and obtaining a trained WGAN network, wherein the specific training process comprises the following steps:
raw dataPAnd downsampling dataRespectively performing N-N cutting, inputting into a generator for training, and generating according to the original dataPAnd downsampled data->Generates and outputs reconstruction data/>，/> and />Common input discriminators for use in a discriminator network training with the ultimate goal of training +.> and />The smaller the error between them, the better.
The data are divided into a training set and a testing set, in order to enable the model obtained through training to be better applied to the testing data set, the same structure is designed for the training data set and the testing data set, after the training set is used for training in the step 3, the testing set is used for testing to determine the effect of the network, when the effect meets the requirement, the network parameters are determined, and the network can be directly used in the step 5.
As shown in fig. 2, the WGAN network includes two parts, namely a generator and a discriminator, and takes measurement data of a certain device for one month as sample data, and the sampling interval is set to be 10s. The data obtained by sampling the training set by using the method of step 1 is the original dataP，Downsampled data obtained by downsampling at a sampling interval of 10s isThe reconstruction data which is output by the corresponding mapping relation is +.>Will-> and />The input signals are input into the discriminator in common,for training of the arbiter network, the final goal of the training is to make +.> and />The smaller the error between them, the better.
During training, the generator cuts the measurement data of one month into n×n small squares as the input of the generator, and N can be set to 128, because the measurement data of one month has larger data size, so as to improve the training speed. Meanwhile, the loss function used in the training process of the generator model is as follows:
meanwhile, the loss function used in the training process of the generator model is as follows:
wherein ,in order for the training set to be a set of training,Mfor sampling matrices, matricesMIs an N matrix, wherein the j element of the i row is +.>Indicating whether the data obtained by downsampling is the same as the data obtained by using the sampling mode of the step 1, if so, the element is 1, otherwise, the element is 0.
Specific: m is downsampling once every 10s, if the downsampled data is the same as the data sampled by the method of step 1, the element is 1, otherwise, 0:
inputting the sampled data of the measured data obtained in the step 1 into a trained WGAN network to generate corresponding interpolation data, and carrying out equidistant interpolation supplementation on the sampled data of the measured data to obtain interpolated and supplemented sampled data (namely, the interval is 10sSample data), i.e. after multiple iterative training, WGAN network parameters are determined, which can be based on the input original sample data { of the multi-source load deviceP 1 ,P 2 ,…P m (where the data corresponds to the sampled data of the previous section)S i ) Corresponding device data { is generated ,/> ,…/>The generated data can be used as the interpolation of the equipment measurement data, and the interpolation supplementation of the original sampling data with the interval of 10s is carried out.
Step 4, reestablishing a cubic spline interpolation function by adopting the sample data after interpolation supplementation, and carrying out Kellow Crout decomposition and solving on the function to obtain the optimal correction quantity of the correction quantity determined in the step 2;
further preferably, in step 41, the [ T1, tn ] time interval is divided into n parts, and for the sample data after interpolation and supplementation, the following equations are established at the sampling point and the interpolation point, namely the equation that the first derivative and the second derivative of the reconstructed cubic spline interpolation function are continuously equal:
according to the basic formula of the cubic spline sampling function, it can be understood by those skilled in the art that according to the continuous requirement of a derivative of a curve of the interpolation function, resampling the sampling data with the interval of 10s obtained in the step 3, integrating the sampling function, and establishing n-2 equations (expressed by using a matrix form, namely, the lower equation) at the sampling point and the interpolation point, meanwhile, according to the characteristic that the power system equipment data has periodicity, establishing the following equations by utilizing the conclusion that the first derivative and the second derivative of the starting point and the ending point are equal:
，
wherein ,, />,/>；
meanwhile, after normalization processing is carried out on the resampled data, and />Constant 1/2; two-step calculation of correction amount +.>。
Step 42, crout decomposition is performed on the equation with continuous equality of the first and second derivatives of the cubic spline interpolation function (i.e., the equation above), and and />1/2, carry-in calculation:
will beIs decomposed intoLU；
wherein ,Lin order to form a lower triangular array, the lower triangular array is provided with a plurality of triangular grooves,Uis an upper triangular array; first calculateLIs recalculated in the first column of (2)UThen calculate the second column of L, and so on, to obtain
，
，
，
，
To be used forIs the initial value, is subjected to continuous iterative computation +.> and />According to the iterative convergence discrimination method, when the error is、/>Are all<When 0.5%, the iteration is completed to obtain the optimal correction amount +.>., wherein />Is the last element of the lower triangular array and the upper triangular array.
Step 5, synchronous interpolation processing is carried out on sampling data of the multi-source load equipment measurement data by utilizing a cubic spline interpolation function for determining the optimal correction amount, so that intelligent synchronous alignment pretreatment of the data is realized:
substituting the optimal correction calculation result back to the cubic spline interpolation function in step 2The synchronous processing of the sampling data can be completed. The sampling data of the measurement data of all the devices are subjected to synchronous interpolation processing of the functions, and then the sampling data of the whole period meets the sampling condition, and the synchronous error of the data of each device is 0, so that synchronous alignment processing is realized.
In summary, the implementation principle of the application is as follows: for the measurement data of various multi-source load devices in the novel power system, in order to realize the whole period sampling, as shown in fig. 3, the input signal is firstly sampled with a fixed sampling frequencySSampling to obtain a sampling original sequencef(s)Then, the original sequence is sampledf(s)On the basis of (1) using WGAN generation data to construct a new data sequence with a sampling interval of 10sF（s）Solving based on new data sequence to obtain optimal correctionS’Thereby obtaining a new sampling sequencef (s,s’)After interpolation processing, the measurement data of all the devices meet the sampling condition of the whole period, and the data synchronization error of each device is 0, thereby realizing synchronous alignment processing. The intelligent synchronous alignment of the distributed photovoltaic, electric automobile charging facilities, adjustable loads and other heterogeneous equipment and the space-time characteristics thereof in the novel power system can be realized by constructing the intelligent synchronous alignment pretreatment model of the data of the multi-source load equipment in the novel power system, and a high-quality data basis can be provided for feature extraction and analysis.
The embodiment 2 of the application provides an intelligent synchronous alignment preprocessing system for data of multi-source load equipment, which comprises the following steps:
the data sampling module is used for sampling the measurement data of the multi-source load equipment in the novel power system to obtain sampling data of the measurement data;
the interpolation function construction module is used for establishing a cubic spline interpolation function for sampling data of the measurement data, determining correction quantity in the function and carrying out normalization processing on calculation parameters of the function;
the Wasserstein generation countermeasure network WGAN construction module is used for constructing and training the Wasserstein generation countermeasure network WGAN based on the multi-source load equipment data characteristics in the novel power system, generating interpolation data by adopting the trained Wasserstein generation countermeasure network WGAN, and carrying out interpolation supplementation on the sampling data of the measurement data;
the correction quantity solving module is used for reestablishing a cubic spline interpolation function by adopting the sample data after interpolation supplementation and carrying out Kellow Crout decomposition and solving on the function to obtain the optimal correction quantity of the correction quantity determined by the interpolation function constructing module;
and the preprocessing module is used for carrying out synchronous interpolation processing on the sampling data of the multi-source load equipment measurement data by utilizing a cubic spline interpolation function for determining the optimal correction amount, so as to realize intelligent synchronous alignment preprocessing of the data.
In the implementation, the system can collect the measurement data of the multi-source load equipment in the novel power system;
storing measurement data of multi-source load equipment in a novel power system in a standardized way; classifying the measurement data of the multi-source load equipment in the novel power system and completing normalization processing; and establishing an interpolation function based on a cubic spline interpolation algorithm. And constructing the WGAN network, generating interpolation data, and filling the interpolation function. And according to the interpolation function, iteratively solving the correction amount in the calculation function, thereby obtaining a resampling sequence, eliminating the equipment data synchronization error, and realizing the synchronization alignment processing.
A terminal comprising a processor and a storage medium; the storage medium is used for storing instructions;
the processor is configured to operate in accordance with the instructions to perform the steps of the method.
A computer readable storage medium having stored thereon a computer program which when executed by a processor realizes the steps of the method.
The application has the beneficial effects that compared with the prior art:
aiming at the condition that sampling periods of multi-source load equipment measurement data in a novel power system are not aligned, the normalization processing method based on the cubic spline interpolation calculation parameters is designed based on the integral characteristics of the sampling data and the electrical measurement characteristics of the power system equipment, and the interpolation calculation amount can be effectively reduced. Meanwhile, based on the characteristic of a cubic spline interpolation function, the method has higher sampling precision on the sampling signal with higher harmonic interference.
The application designs a novel intelligent generating method for measuring data interpolation of power system multi-source load equipment based on a WGAN deep learning network, which takes real measuring data and construction data as input, continuously corrects network parameters in the continuous game process of a generator and a discriminator so as to generate the most reasonable interpolation data, and improves the data sampling and synchronization accuracy of interpolation functions.
According to the application, an interpolation function is constructed based on the original data and the automatically generated data, the solving interpolation function is simplified into solving correction quantity, the calculated quantity is effectively reduced, crout decomposition and recurrent solving are utilized, the calculation result closest to the convergence value is obtained continuously through iteration, the more accurate synchronous alignment pretreatment effect of the multi-source load equipment measurement data of the novel power system is obtained at a higher speed, the synchronous alignment pretreatment level of the base number measurement data is improved, and a high-quality data base is provided for state estimation.
The present disclosure may be a system, method, and/or computer program product. The computer program product may include a computer readable storage medium having computer readable program instructions embodied thereon for causing a processor to implement aspects of the present disclosure.
The computer readable storage medium may be a tangible device that can hold and store instructions for use by an instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: portable computer disks, hard disks, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static Random Access Memory (SRAM), portable compact disk read-only memory (CD-ROM), digital Versatile Disks (DVD), memory sticks, floppy disks, mechanical coding devices, punch cards or in-groove structures such as punch cards or grooves having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media, as used herein, are not to be construed as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., optical pulses through fiber optic cables), or electrical signals transmitted through wires.
The computer readable program instructions described herein may be downloaded from a computer readable storage medium to a respective computing/processing device or to an external computer or external storage device over a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmissions, wireless transmissions, routers, firewalls, switches, gateway computers and/or edge servers. The network interface card or network interface in each computing/processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium in the respective computing/processing device.
Computer program instructions for performing the operations of the present disclosure can be assembly instructions, instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, c++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer readable program instructions may be executed entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, aspects of the present disclosure are implemented by personalizing electronic circuitry, such as programmable logic circuitry, field Programmable Gate Arrays (FPGAs), or Programmable Logic Arrays (PLAs), with state information of computer readable program instructions, which can execute the computer readable program instructions.
Finally, it should be noted that the above embodiments are only for illustrating the technical solution of the present application and not for limiting the same, and although the present application has been described in detail with reference to the above embodiments, it should be understood by those skilled in the art that: modifications and equivalents may be made to the specific embodiments of the application without departing from the spirit and scope of the application, which is intended to be covered by the claims.
Claims (12)
1. The intelligent synchronous alignment preprocessing method for the data of the multi-source load equipment is characterized by comprising the following steps of:
step 1, sampling measurement data of multi-source load equipment in a novel power system to obtain sampling data of the measurement data;
step 2, establishing a cubic spline interpolation function for sampling data of the measurement data, determining correction quantity in the function, and carrying out normalization processing on calculation parameters of the function;
step 3, constructing and training a Wasserstein generation countermeasure network WGAN based on the data characteristics of the multi-source load equipment in the novel power system, generating interpolation data by adopting the trained Wasserstein generation countermeasure network WGAN, and carrying out interpolation supplementation on sampling data of the measurement data;
step 4, reestablishing a cubic spline interpolation function by adopting the sample data after interpolation supplementation, and carrying out Kellow Crout decomposition and solving on the function to obtain the optimal correction quantity of the correction quantity determined in the step 2;
and 5, performing synchronous interpolation processing on sampling data of the multi-source load equipment measurement data by utilizing a cubic spline interpolation function for determining the optimal correction amount, so as to realize intelligent synchronous alignment preprocessing of the data.
2. The intelligent synchronous alignment preprocessing method for multi-source load equipment data according to claim 1, wherein the method comprises the following steps:
in step 1, the multi-source load device measurement data includes voltage, current, power and switch state data of the distributed photovoltaic, the electric vehicle charging pile and the adjustable load device.
3. The intelligent synchronous alignment preprocessing method for multi-source load equipment data according to claim 1, wherein the method comprises the following steps:
in step 2, sampling data of various measurement data of multi-source load equipment in the novel power system is performed in time intervals [ T1, tn]In, establish sampling dataS i Is a cubic spline interpolation function of:
，
wherein ,i、Respectively sampling sequence numbers and sampling time;
interpolation function for cubic spline;
、/>sample data for i-1 and i;
、/>first derivatives for the i-1 and i-th sample data;
,/>is the sampling interval between the i-1 th and i-th sampled data points.
4. The intelligent synchronous alignment preprocessing method for multi-source load equipment data according to claim 3, wherein the method comprises the following steps:
in step 2, the data is sampledS i The cubic spline interpolation function of (2) is decomposed, and the correction amount in the interpolation function is determined, wherein the concrete process is as follows:
order theThen->Then willS i Is rewritten as:
，
，
，
，
，
wherein ,is only equal to the sampling interval t and +.>Correlation, by coefficient relation analysis of interpolation function, will +.>Further decomposed into:
S(T)=
wherein ,is a linear interpolation +.>Nonlinear part, ++> and />It cannot be directly obtained and is regarded as a correction amount.
5. The intelligent synchronous alignment preprocessing method for multi-source load equipment data according to claim 4, wherein the method comprises the following steps:
in step 2, according to the data characteristics of the electric power system, the calculation parameters in the interpolation function are normalized based on a cubic spline interpolation algorithm, and the specific process is as follows:
let the signal period of various load measurement data beT m The number of sampling points in each signal period is n, the sampling interval between two sampling pointsIs regarded as a constant of the size ofT m /nThe sampled data of each device is normalized on the basis:
sampling intervalRegarding as a standard quantity 1, if normalization processing is performed, the sampling time T is entirely extended by n +.T m Multiple of (I)>Then enlarge n as a whole 2 /T m 2 The interpolation interval is also followed by [T 1 ,T n ]Becomes [1, n ]]；
After normalization processing, the cubic spline interpolation function is changed into:
，
，
，
，
。
6. the intelligent synchronous alignment preprocessing method for multi-source load equipment data according to claim 1, wherein the method comprises the following steps:
in step 3, the WGAN network includes a generator and a discriminator, and uses the historical measurement data of the load device as sample data, and samples the sample data by adopting the sampling mode of step 1, that is, adopting the sampling frequency of step 1, to obtain the original dataPDownsampling the sample data with equal sampling interval to obtain downsampled data；
Raw dataPAnd downsampling dataForming a training set to train the WGAN network, determining the parameters of the WGAN network, and obtaining a trained WGAN network, wherein the specific training process comprises the following steps:
raw dataPAnd downsampling dataRespectively performing N-N cutting, inputting into a generator for training, and generating according to the original dataPAnd downsampled data->Generates and outputs reconstruction data +.>，/> and />Common input discriminant for discriminant training with the final goal of +.> and />The smaller the error between them, the better.
7. The intelligent synchronous alignment preprocessing method for multi-source load equipment data according to claim 6, wherein the method comprises the following steps:
the loss function used by the generator in the training process is:
，
wherein ,in order for the training set to be a set of training,Mis a sampling matrix;
matrix arrayMIs an N matrix, wherein the ith row and the jth elementIndicating whether the data obtained by downsampling is the same as the data obtained by using the sampling mode of the step 1, if so, the element is 1, otherwise, the element is 0.
8. The intelligent synchronous alignment preprocessing method for multi-source load equipment data according to claim 6, wherein the method comprises the following steps:
in step 3, the sampling data of the measurement data obtained in step 1 is input into a trained WGAN network to generate corresponding interpolation data, and the sampling data of the measurement data is subjected to equidistant interpolation supplementation to obtain the sampling data after interpolation supplementation.
9. The intelligent synchronous alignment preprocessing method for multi-source load equipment data in a novel power system according to claim 1, which is characterized by comprising the following steps:
step 4 comprises:
step 41, dividing the [ T1, tn ] time interval into n parts, integrating the cubic spline interpolation function based on the sample data after interpolation supplement, and establishing the following equation at the sampling point and the interpolation point, namely, continuously equaling the equation of the first derivative and the second derivative of the reconstructed cubic spline interpolation function:
,
wherein ,, />,/>；
meanwhile, after normalization processing is carried out on the sampling data after interpolation, and />Constant 1/2;
step 42, calculating correction by using Crout decomposition and regression solution for the reestablished continuous equality equation of the first and second derivatives of the cubic spline interpolation function：
Crout decomposition is performed on the equation and and />For 1/2 carry-in calculation:
will beIs decomposed intoLU；
wherein ,Lin order to form a lower triangular array, the lower triangular array is provided with a plurality of triangular grooves,Uis an upper triangular array;
first calculateLIs recalculated in the first column of (2)UThen calculates the second column of L, and so on, resulting in:
，
，
，
，
to be used forIs the initial value, is subjected to continuous iterative computation +.> and />According to the iterative convergence discrimination method, when the error is、/>When all meet the requirement, the iteration is completed to obtain the optimal correction amount +.>, wherein />Is the last element of the lower triangular array and the upper triangular array.
10. An intelligent synchronous alignment preprocessing system for multi-source load equipment data, which is used for realizing the method of any one of claims 1-9, and is characterized in that: the intelligent synchronous alignment preprocessing system comprises:
the data sampling module is used for sampling the measurement data of the multi-source load equipment in the novel power system to obtain sampling data of the measurement data;
the interpolation function construction module is used for establishing a cubic spline interpolation function for sampling data of the measurement data, determining correction quantity in the function and carrying out normalization processing on calculation parameters of the function;
the Wasserstein generation countermeasure network WGAN construction module is used for constructing and training the Wasserstein generation countermeasure network WGAN based on the multi-source load equipment data characteristics in the novel power system, generating interpolation data by adopting the trained Wasserstein generation countermeasure network WGAN, and carrying out interpolation supplementation on the sampling data of the measurement data;
the correction quantity solving module is used for reestablishing a cubic spline interpolation function by adopting the sample data after interpolation supplementation and carrying out Kellow Crout decomposition and solving on the function to obtain the optimal correction quantity of the correction quantity determined by the interpolation function constructing module;
and the preprocessing module is used for carrying out synchronous interpolation processing on the sampling data of the multi-source load equipment measurement data by utilizing a cubic spline interpolation function for determining the optimal correction amount, so as to realize intelligent synchronous alignment preprocessing of the data.
11. A terminal comprising a processor and a storage medium; the method is characterized in that:
the storage medium is used for storing instructions;
the processor being operative according to the instructions to perform the steps of the method according to any one of claims 1-9.
12. Computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the steps of the method according to any one of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311181371.XA CN116933022B (en) | 2023-09-14 | 2023-09-14 | Intelligent synchronous alignment preprocessing method and system for data of multi-source load equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311181371.XA CN116933022B (en) | 2023-09-14 | 2023-09-14 | Intelligent synchronous alignment preprocessing method and system for data of multi-source load equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116933022A true CN116933022A (en) | 2023-10-24 |
| CN116933022B CN116933022B (en) | 2024-01-23 |
Family
ID=88388168
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311181371.XA Active CN116933022B (en) | 2023-09-14 | 2023-09-14 | Intelligent synchronous alignment preprocessing method and system for data of multi-source load equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116933022B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101651363A (en) * | 2009-06-08 | 2010-02-17 | 国电南瑞科技股份有限公司 | Loss sampling data processing method based on third-order spline interpolation method |
| CN104502707A (en) * | 2015-01-06 | 2015-04-08 | 福州大学 | Synchronized phasor measurement method for electrical power system based on cubic spline interpolation |
| US20160305848A1 (en) * | 2015-04-15 | 2016-10-20 | The Boeing Company | Methods and devices for adaptive autonomous polynomial interpolation of time series data |
| CN106530131A (en) * | 2016-11-17 | 2017-03-22 | 南京南瑞继保电气有限公司 | Dynamic real-time recording monitoring method |
| US20170102725A1 (en) * | 2015-10-07 | 2017-04-13 | University Of Utah Research Foundation | Systems and methods for power system management |
| CN109144987A (en) * | 2018-08-03 | 2019-01-04 | 天津相和电气科技有限公司 | Electric system based on deep learning measures missing values method for reconstructing and its application |
| CN115345297A (en) * | 2022-08-12 | 2022-11-15 | 国网山东省电力公司聊城供电公司 | Platform area sample generation method and system based on generation countermeasure network |
| CN115688982A (en) * | 2022-10-11 | 2023-02-03 | 华能江苏综合能源服务有限公司 | Building photovoltaic data completion method based on WGAN and whale optimization algorithm |
-
2023
- 2023-09-14 CN CN202311181371.XA patent/CN116933022B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101651363A (en) * | 2009-06-08 | 2010-02-17 | 国电南瑞科技股份有限公司 | Loss sampling data processing method based on third-order spline interpolation method |
| CN104502707A (en) * | 2015-01-06 | 2015-04-08 | 福州大学 | Synchronized phasor measurement method for electrical power system based on cubic spline interpolation |
| US20160305848A1 (en) * | 2015-04-15 | 2016-10-20 | The Boeing Company | Methods and devices for adaptive autonomous polynomial interpolation of time series data |
| US20170102725A1 (en) * | 2015-10-07 | 2017-04-13 | University Of Utah Research Foundation | Systems and methods for power system management |
| CN106530131A (en) * | 2016-11-17 | 2017-03-22 | 南京南瑞继保电气有限公司 | Dynamic real-time recording monitoring method |
| CN109144987A (en) * | 2018-08-03 | 2019-01-04 | 天津相和电气科技有限公司 | Electric system based on deep learning measures missing values method for reconstructing and its application |
| CN115345297A (en) * | 2022-08-12 | 2022-11-15 | 国网山东省电力公司聊城供电公司 | Platform area sample generation method and system based on generation countermeasure network |
| CN115688982A (en) * | 2022-10-11 | 2023-02-03 | 华能江苏综合能源服务有限公司 | Building photovoltaic data completion method based on WGAN and whale optimization algorithm |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116933022B (en) | 2024-01-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110806541B (en) | AD-BAS-based lithium battery model parameter identification method | |
| CN113269314B (en) | New energy power generation scene data migration method based on generation countermeasure network | |
| CN113777552A (en) | Method and system for predicting metering error of capacitive voltage transformer | |
| CN114330935B (en) | New energy power prediction method and system based on multiple combination strategies integrated learning | |
| CN113569201B (en) | Geomagnetic Ap index forecasting method and device and electronic equipment | |
| CN115660233A (en) | Photovoltaic power prediction method and device, electronic equipment and storage medium | |
| CN116992779A (en) | Simulation method and system of photovoltaic energy storage system based on digital twin model | |
| CN116933022B (en) | Intelligent synchronous alignment preprocessing method and system for data of multi-source load equipment | |
| CN116722545B (en) | Photovoltaic power generation prediction method based on multi-source data and related equipment | |
| CN111967652A (en) | Double-layer cooperative real-time correction photovoltaic prediction method | |
| CN115713044B (en) | Method and device for analyzing residual life of electromechanical equipment under multi-condition switching | |
| CN116707331A (en) | Inverter output voltage high-precision adjusting method and system based on model prediction | |
| CN110969238A (en) | Method and device for calibrating electricity consumption data | |
| CN107918920B (en) | Output correlation analysis method for multiple photovoltaic power stations | |
| CN116050250A (en) | Power grid digital twin model modeling method and device based on hybrid driving model | |
| CN115619449A (en) | Deep learning model-based fertilizer price prediction method, device and storage medium | |
| CN114819264A (en) | Photovoltaic power station irradiance ultra-short term prediction method based on space-time dependence and storage medium | |
| CN114168657A (en) | Method, system, equipment and medium for detecting wind power abnormal data in real time | |
| CN112685900B (en) | Power load simulation method for representing impact load power characteristics | |
| CN110930172A (en) | Neural network-based cross-country market joint marginal price prediction method and system | |
| CN113554106B (en) | Collaborative completion method for power missing data | |
| CN114971058B (en) | Photovoltaic forecasting method based on depth attention network and clear sky radiation priori fusion | |
| CN112766076B (en) | Ultra-short-term prediction method, system, equipment and storage medium for power load | |
| CN115860249A (en) | Distributed photovoltaic power generation power prediction method, device, equipment and medium | |
| Zhao et al. | Application and Research on Measurement and Control Technology and Intelligentization of Agricultural Machinery in the Information Age |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |