CN114065610A - Wind power prediction method for optimizing kernel limit learning machine based on sparrow search algorithm - Google Patents
Wind power prediction method for optimizing kernel limit learning machine based on sparrow search algorithm Download PDFInfo
- Publication number
- CN114065610A CN114065610A CN202111247254.XA CN202111247254A CN114065610A CN 114065610 A CN114065610 A CN 114065610A CN 202111247254 A CN202111247254 A CN 202111247254A CN 114065610 A CN114065610 A CN 114065610A
- Authority
- CN
- China
- Prior art keywords
- wind power
- learning machine
- kernel
- search algorithm
- limit learning
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 241000287127 Passeridae Species 0.000 title claims abstract description 38
- 238000010845 search algorithm Methods 0.000 title claims abstract description 31
- 238000012545 processing Methods 0.000 claims abstract description 7
- 230000006870 function Effects 0.000 claims description 22
- 238000012549 training Methods 0.000 claims description 19
- 239000011159 matrix material Substances 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 10
- 230000002159 abnormal effect Effects 0.000 claims description 9
- 230000004913 activation Effects 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 5
- 238000012847 principal component analysis method Methods 0.000 claims description 4
- 238000005457 optimization Methods 0.000 abstract description 15
- 238000004458 analytical method Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 238000010248 power generation Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E40/00—Technologies for an efficient electrical power generation, transmission or distribution
- Y02E40/70—Smart grids as climate change mitigation technology in the energy generation sector
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Development Economics (AREA)
- Mathematical Physics (AREA)
- Game Theory and Decision Science (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- Molecular Biology (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a wind power prediction method for optimizing a kernel-limit learning machine based on a sparrow search algorithm, which specifically comprises the following steps: step 1, determining a dominant influence factor influencing wind power; step 2, processing the dominant influence factor determined in the step 1 by using a Thompson tau-quartile method; and 3, constructing a sparrow search algorithm optimization kernel extreme learning machine prediction model, and predicting the wind power through the model. The method solves the problems that the wind power prediction precision is low and the prediction performance is greatly influenced by self parameters at present.
Description
Technical Field
The invention belongs to the technical field of wind power prediction, and relates to a wind power prediction method for optimizing a kernel limit learning machine based on a sparrow search algorithm.
Background
With the increasingly prominent energy and environmental problems, wind energy becomes a focus of renewable energy development as pollution-free and sustainable clean energy, the domestic wind power generation level also keeps steadily increasing, and the wind power generation amount in 2018 reaches 3660 hundred million kilowatts and accounts for 5.2% of the total power generation amount. The wind power prediction has important guiding significance on power grid dispatching. The improvement of the wind power prediction algorithm and the improvement of the wind power prediction precision are particularly important in the process.
At present, the wind power prediction method mainly comprises the following traditional prediction methods: time series method, regression analysis method, etc., novel prediction method: neural network algorithms, support vector machines, extreme learning machines, genetic algorithms, and the like. The predictive performance of the current intelligent algorithm models is greatly influenced by self parameters, the parameter optimizing capability is insufficient, the local searching capability is poor, the local optimal solution is easy to fall into, and the prediction precision is not high.
In order to improve the wind power prediction precision, a sparrow search algorithm optimized kernel limit learning machine prediction model is constructed, an intelligent optimization algorithm is combined with a limit learning machine model, and the sparrow search algorithm is used for automatically optimizing the regularization coefficient and kernel function parameters of the kernel limit learning machine, so that the wind power prediction precision and the convergence speed are improved.
Disclosure of Invention
The invention aims to provide a wind power prediction method for optimizing a kernel limit learning machine based on a sparrow search algorithm, which solves the problems that the wind power prediction precision is low and the prediction performance is greatly influenced by self parameters at present.
The technical scheme adopted by the invention is that the wind power prediction method for optimizing the kernel limit learning machine based on the sparrow search algorithm specifically comprises the following steps:
step 1, determining a dominant influence factor influencing wind power;
step 2, carrying out abnormal value processing on the dominant influence factor determined in the step 1 by using a Thompson tau-quartile method to obtain a processed sample set;
and 3, constructing a prediction model of the sparrow search algorithm optimized kernel-extreme learning machine, and training through the sample set obtained in the step 2 so as to predict the wind power.
The invention is also characterized in that:
the specific process of the step 1 is as follows: collecting wind power data and multi-dimensional meteorological data from a wind power plant, wherein the multi-dimensional meteorological data comprises: wind speed, wind direction, humidity, cabin temperature, blade temperature; and determining wind power dominant influence factors as wind speed and wind direction respectively by a principal component analysis method.
The specific process of the step 2 is as follows: and (3) carrying out sectional identification on the wind speed and wind direction data obtained in the step (1) by using a Thompson tau-quartile method, eliminating abnormal data points which are caused by recording errors, measuring instrument errors or equipment shutdown and have extremely non-corresponding power and wind speed, and carrying out normalization processing on the residual data to convert the residual data into standard values so as to obtain a cleaned sample set.
The specific process of the step 3 is as follows:
step 3.1, determining training parameters of the kernel limit learning machine;
step 3.2, taking wind speed and wind direction as input of the nuclear limit learning machine, taking wind power as output, substituting the wind speed and wind power into the cleaned sample set obtained in the step 2, dividing the sample set into training samples and prediction samples, and automatically searching for training parameters in the nuclear limit learning machine by using a sparrow search algorithm;
and 3.3, using the trained training parameters in a nuclear extreme learning machine, and substituting the trained training parameters into the cleaned sample set obtained in the step 2 to predict the wind power and obtain the predicted power.
In step 3.1, the training parameters of the extreme learning machine are respectively as follows: an activation function, a kernel function matrix, and a regularization coefficient.
And 3.2, automatically searching parameters of the regularization coefficient and the kernel function matrix in the kernel limit learning machine by using a sparrow search algorithm through the regularization coefficient and the kernel function matrix.
The invention has the following beneficial effects:
1. the method has the advantages that the problem of relevance of various meteorological data and power fluctuation is considered, the wind power is predicted by introducing relevant meteorological factors after principal component analysis is carried out, and the multi-dimensional meteorological factors are beneficial to improving prediction accuracy.
2. Abnormal data are removed by using Thompson tau-quartile, and the influence of the abnormal data on a prediction result is reduced.
3. And the reconstruction of the total data after the abnormal values are removed is finished by using a four-point interpolation method, so that the influence of data shortage on a prediction result is reduced.
4. The prediction model based on the sparrow search algorithm optimization kernel limit learning machine is constructed, the generalization capability is strong, the optimization algorithm convergence speed is high, and the prediction precision is high.
5. The predicted root mean square error is below 80 kW.
Drawings
FIG. 1 is a flow chart of a wind power prediction method for optimizing a kernel-limit learning machine based on a sparrow search algorithm according to the invention;
FIG. 2 is an SSA-KELM power prediction diagram in the wind power prediction method for optimizing the kernel limit learning machine based on the sparrow search algorithm;
FIG. 3 is a PSO-KELM power prediction diagram in the wind power prediction method for optimizing the kernel limit learning machine based on the sparrow search algorithm.
Detailed Description
The present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.
The invention discloses a wind power prediction method for optimizing a kernel-limit learning machine based on a sparrow search algorithm, which comprises the following steps of: 1. selecting a dominant influence factor by using a principal component analysis method; 2. removing historical power abnormal data by using a Thompson tau-quartile method; 3. preprocessing data, and performing data normalization; 4. inputting the cleaned data to train a sparrow search algorithm to optimize a kernel-limit learning machine model for prediction; 5. data inverse normalization processing, 6, predicting the power of the multi-period sequence, drawing an image, and calculating a root mean square error; 7. and comparing the real predicted values to perform error evaluation analysis on the predicted results.
The method specifically comprises the following steps:
step 1, wind speed, wind direction, humidity, cabin temperature and blade temperature of certain domestic wind power plant wind power data and multidimensional meteorological data are collected, wind speed and wind direction are determined as wind power dominant influence factors through a principal component analysis method, the wind speed and the wind direction respectively account for 53.9234% and 27.7168% of the total proportion, and 53.9234% + 27.7168% > 80%, and therefore the wind speed and the wind direction of the first two principal components are reserved.
And 2, carrying out sectional identification on the wind speed and wind direction data obtained in the first step by using a Thompson tau-quartile method, and removing abnormal data points which are extremely inconsistent with the wind speed and cause power due to recording errors, measuring instrument errors or equipment shutdown. And the data are normalized and converted into standard values, so that the influence on the accuracy of a prediction result due to different magnitude value ranges of the wind speed data and the wind direction data is prevented.
And 3, constructing a sparrow search algorithm optimized kernel-extreme learning machine prediction model (ssa-kelm) and finishing parameter initialization setting. Before training, the kernel-limit learning machine needs to determine three parameters, namely an activation function, a kernel function matrix and a regularization coefficient. The sig activation function (with the highest fitness with the group of data) is selected from the activation functions of the kernel-limit learning machine, the regularization coefficient and the kernel function matrix automatically search the parameters of the kernel function matrix and the regularization coefficient in the kernel-limit learning machine by using a sparrow search algorithm, and the population number, the maximum iteration number, the number of optimization parameters, the risk ratio and the upper and lower limit limits of the sparrow optimization algorithm need to be determined. The population number, the maximum iteration number and the risk ratio can be freely selected (wherein the larger the parameter of the maximum iteration number and the population number is, the longer the time is, and the higher the training precision is in general), for example, the number of the selected population is 60, the maximum iteration number is 30, the number of the optimization parameters is 2, the risk ratio is 0.3, the upper limit is 1000, and the lower limit is 0.1. Substituting two optimization parameters generated in a sparrow optimization algorithm into a regularization coefficient and a kernel function matrix, then taking wind speed and wind direction as the input of a kernel limit learning machine, taking wind power as the output of the kernel limit learning machine, substituting the wind power into a sample set cleaned in the second step, taking 4600 groups of data as training samples, and taking 65 groups of data as prediction samples. Wind power prediction is carried out, the root mean square error of the predicted power and the actual power is obtained, the RMSE (root mean square error) of the predicted power and the actual power is taken as the minimum to be the best fitness (fit) in a sparrow optimization algorithm, and the best kernel function matrix and the regularization coefficient are selected in an iteration mode. And the model is trained in the automatic parameter searching process of the sparrow optimization algorithm, and finally the initial value setting and model training of the overall prediction model are completed.
And 4, performing inverse normalization processing on the predicted power and actual power samples obtained by final training, converting standard values in the training process into normal power data, correspondingly listing the predicted power and the actual power into a table one by one, and making a comparison graph so as to facilitate observation and analysis. The root mean square error between the predicted value and the actual value is calculated, the error analysis and evaluation are carried out on the result, the deficiency of the model is found through the analysis on the root mean square error, the accuracy degree of individual power point prediction and whether the trend between the overall predicted value and the actual value is matched with the factors according to the wind speed and the wind direction, and a new improvement direction is provided. Meanwhile, the prediction accuracy of the model is judged according to the factors, wherein the factors are mainly root mean square errors, so that the adaptation degree of the model to the problems is judged.
For the kernel-limit learning machine, a power sample and a wind speed and a wind direction corresponding to the power sample need to be input for prediction, and an activation function, a kernel function matrix and a regularization coefficient need to be selected. In the selection of the kernel function matrix and the regularization coefficient, manual selection is time-consuming and labor-consuming, the obtained result is not accurate enough, and the defect can be made up by combining a sparrow optimization algorithm to carry out intelligent selection.
The invention focuses on introducing multidimensional meteorological data and adopts a Thompson tau-quartile method to process historical abnormal data. A prediction model based on a sparrow search algorithm optimization kernel extreme learning machine is built to predict wind power, and a regularization coefficient and kernel function parameters of the kernel extreme learning machine are automatically optimized through the sparrow search algorithm. And therefore, wind power prediction is carried out by using the optimal regularization coefficient and the kernel function parameter.
FIG. 2 is a comparison result of a predicted value and an actual value of wind power of a kernel-based extreme learning machine optimized based on a sparrow algorithm search method, FIG. 2 is an SSA-KELM power prediction graph, and the root mean square error of the wind power prediction of the kernel-based extreme learning machine optimized based on the sparrow algorithm is 60.1556 kW. The prediction effect of the extreme learning machine is greatly influenced by parameter selection, the stability and the prediction precision of a prediction algorithm are improved by the prediction method, the prediction speed is high, the generalization capability is strong, and the optimization effect is good. Has good expansibility.
Compared with the kernel limit learning machine optimized by the same type of particle swarm, the algorithm has the advantages of progressiveness, the training prediction samples with the same parameters are set, and the same upper and lower search limits, the same population quantity and the maximum iteration times are set. The root mean square error predicted by the particle swarm optimization kernel extreme learning machine is 133.6366kw, and a comparison graph of a predicted value and a true value is shown in fig. 3 (fig. 3 is a PSO-KELM power prediction graph): obviously, the predicted value of the SSA-KELM is closer to the true value, and the prediction effect is more accurate. In addition, the prediction system can be applied to the aspect of wind power prediction, and the prediction method is also applicable to the fields of stock prediction, house price prediction, weather prediction and the like.
Claims (6)
1. The wind power prediction method for optimizing the kernel limit learning machine based on the sparrow search algorithm is characterized by comprising the following steps of: the method specifically comprises the following steps:
step 1, determining a dominant influence factor influencing wind power;
step 2, processing the dominant influence factor determined in the step 1 by using a Thompson tau-quartile method to obtain a processed sample set;
and 3, constructing a prediction model of the sparrow search algorithm optimized kernel-extreme learning machine, and training through the sample set obtained in the step 2 so as to predict the wind power.
2. The wind power prediction method based on the sparrow search algorithm optimized kernel-limit learning machine of claim 1, characterized in that: the specific process of the step 1 is as follows: collecting wind power data and multi-dimensional meteorological data from a wind power plant, wherein the multi-dimensional meteorological data comprises: wind speed, wind direction, humidity, cabin temperature, blade temperature; and determining wind power dominant influence factors as wind speed and wind direction respectively by a principal component analysis method.
3. The wind power prediction method based on the sparrow search algorithm optimized kernel-limit learning machine of claim 2, characterized in that: the specific process of the step 2 is as follows: and (3) carrying out sectional identification on the wind speed and wind direction data obtained in the step (1) by using a Thompson tau-quartile method, eliminating abnormal data points which are caused by recording errors, measuring instrument errors or equipment shutdown and have extremely non-corresponding power and wind speed, and carrying out normalization processing on the residual data to convert the residual data into standard values so as to obtain a cleaned sample set.
4. The wind power prediction method based on the sparrow search algorithm optimized kernel-limit learning machine of claim 3, characterized in that: the specific process of the step 3 is as follows:
step 3.1, determining training parameters of the kernel limit learning machine;
3.2, automatically searching the training parameters in the kernel limit learning machine by using a sparrow search algorithm;
and 3.3, taking the wind speed and the wind direction as the input of the nuclear limit learning machine, taking the wind power as the output, substituting the wind power into the cleaned sample set obtained in the step 2, dividing the sample set into a training sample and a prediction sample, and predicting the wind power to obtain the predicted power.
5. The wind power prediction method based on the sparrow search algorithm optimized kernel-limit learning machine of claim 4, characterized in that: in the step 3.1, the training parameters of the kernel limit learning machine are respectively as follows: an activation function, a kernel function matrix, and a regularization coefficient.
6. The wind power prediction method based on the sparrow search algorithm optimized kernel-limit learning machine of claim 5, characterized in that: in the step 3.2, the regularization coefficients and the kernel function matrix automatically search parameters for the kernel function matrix and the regularization coefficients in the kernel limit learning machine by using a sparrow search algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111247254.XA CN114065610A (en) | 2021-10-26 | 2021-10-26 | Wind power prediction method for optimizing kernel limit learning machine based on sparrow search algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111247254.XA CN114065610A (en) | 2021-10-26 | 2021-10-26 | Wind power prediction method for optimizing kernel limit learning machine based on sparrow search algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114065610A true CN114065610A (en) | 2022-02-18 |
Family
ID=80235498
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111247254.XA Pending CN114065610A (en) | 2021-10-26 | 2021-10-26 | Wind power prediction method for optimizing kernel limit learning machine based on sparrow search algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114065610A (en) |
-
2021
- 2021-10-26 CN CN202111247254.XA patent/CN114065610A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106779223B (en) | Photovoltaic system power generation real-time prediction method and device | |
| CN111369070B (en) | Multimode fusion photovoltaic power prediction method based on envelope clustering | |
| CN107944622A (en) | Wind power forecasting method based on continuous time cluster | |
| CN112182720B (en) | Building energy consumption model evaluation method based on building energy management application scene | |
| CN110601250B (en) | Method for evaluating stability of static voltage of access point based on new energy power station | |
| CN113837464A (en) | Load prediction method of cogeneration boiler based on CNN-LSTM-Attention | |
| CN110991737A (en) | Ultra-short-term wind power prediction method based on deep belief network | |
| CN113869616A (en) | Self-adaptive residential user load prediction method | |
| CN112651576A (en) | Long-term wind power prediction method and device | |
| CN112330045A (en) | Power transmission network line loss evaluation and reduction method based on K-medoids clustering analysis method | |
| CN115545333A (en) | Method for predicting load curve of multi-load daily-type power distribution network | |
| CN109388863B (en) | ARIMA model-based distributed photovoltaic output power prediction method | |
| CN110991747A (en) | Short-term load prediction method considering wind power plant power | |
| CN114240003A (en) | New energy output prediction method, system, storage medium and equipment | |
| CN116826745B (en) | Layered and partitioned short-term load prediction method and system in power system background | |
| CN114298132A (en) | Wind power prediction method and device and electronic equipment | |
| CN112132344A (en) | Short-term wind power prediction method based on similar day and FRS-SVM | |
| CN112836876A (en) | Power distribution network line load prediction method based on deep learning | |
| CN116317937A (en) | Distributed photovoltaic power station operation fault diagnosis method | |
| CN114065610A (en) | Wind power prediction method for optimizing kernel limit learning machine based on sparrow search algorithm | |
| CN115764870A (en) | Multivariable photovoltaic power generation power prediction method and device based on automatic machine learning | |
| CN113554203B (en) | Wind power prediction method and device based on high-dimensional meshing and LightGBM | |
| CN112801388B (en) | Power load prediction method and system based on nonlinear time series algorithm | |
| CN113705887A (en) | Data-driven photovoltaic power generation power prediction method and system | |
| CN117669391B (en) | Short-term photovoltaic power prediction method based on deep learning |
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 |