CN116565865B - Wind power prediction method based on deep error feedback learning - Google Patents

Wind power prediction method based on deep error feedback learning Download PDF

Info

Publication number
CN116565865B
CN116565865B CN202310843436.6A CN202310843436A CN116565865B CN 116565865 B CN116565865 B CN 116565865B CN 202310843436 A CN202310843436 A CN 202310843436A CN 116565865 B CN116565865 B CN 116565865B
Authority
CN
China
Prior art keywords
wind power
prediction
model
prediction error
weather forecast
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.)
Active
Application number
CN202310843436.6A
Other languages
Chinese (zh)
Other versions
CN116565865A (en
Inventor
胡宇晗
朱利鹏
李佳勇
帅智康
曾杨
郑李梦千
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hunan University
Original Assignee
Hunan University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Hunan University filed Critical Hunan University
Priority to CN202310843436.6A priority Critical patent/CN116565865B/en
Publication of CN116565865A publication Critical patent/CN116565865A/en
Application granted granted Critical
Publication of CN116565865B publication Critical patent/CN116565865B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H02J3/004—Generation forecast, e.g. methods or systems for forecasting future energy generation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • 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
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
    • 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"
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
    • H02J3/381—Dispersed generators
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
    • H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
    • H02J2300/20—The dispersed energy generation being of renewable origin
    • H02J2300/28—The renewable source being wind energy

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Human Resources & Organizations (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Economics (AREA)
  • Power Engineering (AREA)
  • Marketing (AREA)
  • General Health & Medical Sciences (AREA)
  • Tourism & Hospitality (AREA)
  • Health & Medical Sciences (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Game Theory and Decision Science (AREA)
  • General Business, Economics & Management (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Development Economics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The application provides a wind power prediction method based on depth error feedback learning, which comprises the following steps of S1, constructing a prediction error estimation model based on XGBoost, wherein the prediction error estimation model takes weather forecast data as input and prediction error as output; s2, constructing a wind power secondary prediction model based on double-layer LSTM, wherein the wind power secondary prediction model takes weather forecast data as main input, prediction error as feedback input and wind power predicted value as output; and step S3, sending the current weather forecast data into a prediction error estimation model to obtain a future prediction error, and sending the current weather forecast data and the future prediction error into the wind power secondary prediction model together to obtain a final wind power predicted value. The method can effectively improve the prediction precision of the wind power plant, reduce the uncertainty of the output of the wind power plant and facilitate the improvement of the utilization efficiency of wind resources.

Description

Wind power prediction method based on deep error feedback learning
Technical Field
The application relates to the technical field of wind power prediction, in particular to a wind power prediction method based on deep error feedback learning.
Background
Wind energy has the advantages of wide distribution range, cleanness, reproducibility and the like. However, due to the outstanding intermittence, volatility and uncertainty of wind power generation, large scale grid connection thereof presents serious challenges for safe and reliable operation of the power system. If the wind power can be predicted efficiently and reliably, the uncertainty of the output of the wind power can be effectively reduced, and important support and guarantee are provided for the safe and stable operation of the system after large-scale wind power access.
The existing prediction method is difficult to accurately describe the relation between wind power plant meteorological data and the output power of a station, so that a prediction error inevitably exists in a wind power prediction result, and if the hidden useful information in the error can be fully excavated and learned, the wind power prediction precision is expected to be further improved. However, existing methods all attempt to improve prediction accuracy by directly improving the prediction model itself, and the potential value of prediction errors for improving prediction performance is not mined, and the prediction result faces a bottleneck that cannot be further improved.
Disclosure of Invention
The application aims to provide a wind power prediction method based on deep error feedback learning so as to improve the prediction accuracy of wind power.
In order to solve the technical problems, the application adopts the following technical methods: a wind power prediction method based on deep error feedback learning comprises the following steps:
step S1, constructing a prediction error estimation model based on XGBoost, wherein weather forecast data is taken as input and a prediction error is taken as output;
s2, constructing a wind power secondary prediction model based on double-layer LSTM, wherein the wind power secondary prediction model takes weather forecast data as main input, prediction error as feedback input and wind power predicted value as output;
and step S3, sending the current weather forecast data into the prediction error estimation model to obtain a future prediction error, and sending the current weather forecast data and the future prediction error into the wind power secondary prediction model together to obtain a final wind power predicted value.
Further, the construction of the prediction error estimation model includes the following steps:
s11, collecting weather forecast data and wind power of a history of a prediction target wind power plant, and calculating a prediction error of the history;
s12, constructing a prediction error estimation model based on XGBoost, wherein the prediction error estimation model takes weather forecast data as input and prediction error as output;
s13, setting initial parameters of a prediction error estimation model, training the prediction error estimation model by using historical weather forecast data and historical prediction errors, and continuously optimizing the model parameters based on grid search until the model converges.
Further, the process of calculating the prediction error of the history in step S11 is as follows:
1) Collecting weather forecast data of a forecast target wind farm historyAnd wind power->；
2) Will be、/>Normalizing to obtain->、/>；
3) Constructing a preliminary prediction model based on double-layer LSTM and taking weather forecast data as input and wind power data as output, setting initial parameters of the preliminary prediction model, and utilizing、/>Training the preliminary prediction model by the data, and continuously optimizing the model parameters based on grid search until the model converges;
4) Will beSending the wind power prediction model into a trained preliminary prediction model to obtain wind power prediction of wind power plant historyValue->；
5) The method of 4)Performing inverse normalization to obtain->；
6) Based on that obtained in 5)And 1) collected->Calculating the prediction error of the history +.>The following formula:
(1)
7) The method obtained in 6) is carried outNormalizing to obtain->。
Further, in step S13, initial parameters of the prediction error estimation model are set and usedAnd->Training the prediction error estimation model, and continuously optimizing the model parameters based on grid search until the model converges.
Still further, the preliminary prediction model comprises an input layer, two LSTM layers, a full connection layer and an output layer; the wind power secondary prediction model comprises two input layers, two LSTM layers, a full connection layer and an output layer.
Further, the wind power secondary prediction model is constructed by the following steps:
s21, constructing a wind power secondary prediction model based on double-layer LSTM, wherein the wind power secondary prediction model takes weather forecast data as main input, prediction error as feedback input and wind power predicted value as output;
s22, setting initial parameters of a wind power secondary prediction model, and utilizing、/>、/>Training a wind power secondary prediction model, wherein the wind power secondary prediction model is used for training>Vector +.>Will->And->Form a combination vector->Then input into the full connection layer, output +.>；
And S23, continuously optimizing parameters of the wind power secondary prediction model based on grid search until the model converges.
Further, the step S3 includes:
s31, collecting current weather forecast of a target wind power plantNewspaper data；
S32, willNormalizing to obtain->；
S33, willSending the prediction error into a trained prediction error estimation model to obtain future prediction error +.>；
S34, will、/>Sending the wind power into a trained wind power secondary prediction model to obtain a prediction result +.>；
S35, willPerforming inverse normalization to obtain final wind power predicted value +.>。
Preferably, the weather forecast data includes wind speed, wind direction, air temperature and air pressure.
Compared with the traditional wind power prediction method, the wind power prediction method based on the depth error feedback learning provided by the application extracts historical error information in a preliminary prediction stage, estimates future prediction errors based on XGBoost (eXtreme Gradient Boosting extreme gradient lifting algorithm), and applies the future prediction errors to secondary wind power prediction, so that hidden useful information in the prediction errors is fully excavated and utilized, the prediction accuracy of wind power is improved, the uncertainty of wind power plant output is reduced, and the utilization efficiency of wind resources is improved.
Drawings
FIG. 1 is a flow chart of a wind power prediction method based on depth error feedback learning according to the present application;
FIG. 2 is a frame diagram of a wind power prediction method based on depth error feedback learning according to the present application;
FIG. 3 is a block diagram of a preliminary predictive model in accordance with the present application;
FIG. 4 is a structural diagram of a wind power secondary prediction model in the application.
Detailed Description
The application will be further described with reference to examples and drawings, to which reference is made, but which are not intended to limit the scope of the application.
In wind power prediction, the prediction result inevitably has errors, and if the hidden useful information in the errors can be fully mined and learned, the wind power prediction precision is expected to be further improved. The method takes the method as a starting point, extracts historical error information in a preliminary prediction stage, estimates future prediction errors based on XGBoost (eXtreme Gradient Boosting extreme gradient lifting algorithm), and acts the future prediction errors on wind power secondary prediction to fully learn the errors so as to improve the overall prediction performance.
As shown in fig. 1 and fig. 2, a wind power prediction method based on deep error feedback learning mainly includes the following three steps of constructing a preliminary prediction model, a prediction error estimation model, a wind power secondary prediction model and predicting future wind power.
Step S1
S11, collecting weather forecast data and wind power of a history of a prediction target wind power plant, and calculating a prediction error of the history.
1) Acquisition predictionWeather forecast data for target wind farm historyAnd wind power->。
2) Will be、/>Normalizing to obtain->、/>。
3) A preliminary prediction model based on double-layer LSTM and taking weather forecast data as input and wind power data as output is constructed, and as shown in figure 3, the preliminary prediction model consists of an input layer, two LSTM layers, a full connection layer and an output layer. Setting initial parameters of the preliminary prediction model, and utilizing、/>And training the preliminary prediction model by the data, and continuously optimizing the model parameters based on grid search until the model converges.
4) As shown in fig. 3, willSending the wind power into a trained preliminary prediction model to obtain preliminary predicted wind power, wherein the preliminary predicted wind power is also a wind power predicted value +.>。
5) The method of 4)Performing inverse normalization to obtain->。
6) Based on that obtained in 5)And 1) collected->Calculating the prediction error of the history +.>The following formula:
(1)
7) The method obtained in 6) is carried outNormalizing to obtain->。
S12, constructing a prediction error estimation model based on XGBoost, wherein the prediction error estimation model takes weather forecast data as input and prediction error as output.
S13, setting initial parameters of a prediction error estimation model, and utilizingAnd->Training the prediction error estimation model, and continuously optimizing the model parameters based on grid search until the model converges.
Step S2
S21, constructing a wind power secondary prediction model based on double-layer LSTM, wherein the wind power secondary prediction model is composed of two input layers, two LSTM layers, a full connection layer and an output layer, and the weather forecast data is used as main input, the prediction error is used as feedback input and the wind power predicted value is used as output.
S22, setting initial parameters of a wind power secondary prediction model, and utilizing、/>、/>Training of the power quadratic prediction model, as shown in FIG. 4,/for training>Vector +.>Will->And->Form a combination vector->Then input into the full connection layer, output +.>。
And S23, continuously optimizing parameters of the wind power secondary prediction model based on grid search until the model converges.
Step S3
S31, collecting current weather forecast data of a prediction target wind power plant。
S32, willNormalizing to obtain->。
S33, willSending the prediction error into a trained prediction error estimation model to obtain future prediction error +.>。
S34, will、/>Sending the wind power into a trained wind power secondary prediction model to obtain secondary predicted wind power which is also a prediction result +.>。
S35, willPerforming inverse normalization to obtain final wind power predicted value +.>。
Preferably, the weather forecast data includes characteristic information such as wind speed, wind direction, air temperature, air pressure, etc.
In order to verify the effectiveness and accuracy of the wind power prediction method based on the depth error feedback learning, two indexes of absolute average error (MAE) and Root Mean Square Error (RMSE) can be adopted to evaluate the method, and the method is specifically:
a) Predicted value of wind power in step S35Predicted by a wind power secondary prediction model, and calculated +.>MAE and of (2)RMSE value.
b) Obtained in step S32Sending the wind power into a trained preliminary prediction model, and predicting the wind power by adopting the preliminary prediction model to obtain a prediction result +.>Will->After inverse normalization, MAE and RMSE values were calculated.
c) Comparing the MAE and RMSE values obtained in a) and b), if the MAE and RMSE values obtained in a) are smaller than the MAE and RMSE values obtained in b), the fact that error information is introduced into a prediction model can effectively improve prediction accuracy is indicated, otherwise, the prediction accuracy cannot be improved. In addition, the smaller the values of MAE and RMSE, the higher the prediction accuracy of the model.
The foregoing embodiments are preferred embodiments of the present application, and in addition, the present application may be implemented in other ways, and any obvious substitution is within the scope of the present application without departing from the concept of the present application.
In order to facilitate understanding of the improvements of the present application over the prior art, some of the figures and descriptions of the present application have been simplified and some other elements have been omitted for clarity, as will be appreciated by those of ordinary skill in the art.

Claims (3)

1. The wind power prediction method based on the deep error feedback learning is characterized by comprising the following steps of:
step S1, constructing a prediction error estimation model based on XGBoost, wherein weather forecast data is taken as input and a prediction error is taken as output;
the constructing of the prediction error estimation model comprises the following steps:
s11, collecting weather forecast data and wind power of a history of a prediction target wind power plant, and calculating a prediction error of the history;
1) Collecting weather forecast data of a forecast target wind farm historyAnd wind power->；
2) Will be、/>Normalizing to obtain->、/>；
3) Constructing a preliminary prediction model based on double-layer LSTM and taking weather forecast data as input and wind power data as output, wherein the preliminary prediction model comprises an input layer, two LSTM layers, a full-connection layer and an output layer, setting initial parameters of the preliminary prediction model, and utilizing、/>Training the preliminary prediction model by the data, and continuously optimizing the model parameters based on grid search until the model converges;
4) Will beSending the wind power prediction value into a trained preliminary prediction model to obtain a wind power prediction value of wind power plant history +.>；
5) The method of 4)Performing inverse normalization to obtain->；
6) Based on that obtained in 5)And 1) collected->Calculating the prediction error of the history +.>The following formula:
(1)
7) The method obtained in 6) is carried outNormalizing to obtain->；
S12, constructing a prediction error estimation model based on XGBoost, wherein the prediction error estimation model takes weather forecast data as input and prediction error as output;
s13, setting initial parameters of a prediction error estimation model, and utilizingAnd->Training a prediction error estimation model, continuously optimizing the model parameters based on grid search,until the model converges;
s2, constructing a wind power secondary prediction model based on double-layer LSTM, wherein the wind power secondary prediction model takes weather forecast data as main input, prediction error as feedback input and wind power predicted value as output;
the building of the wind power secondary prediction model comprises the following steps:
s21, constructing a wind power secondary prediction model based on double-layer LSTM, wherein the wind power secondary prediction model takes weather forecast data as main input, prediction error as feedback input and wind power predicted value as output, and the wind power secondary prediction model comprises two input layers, two LSTM layers, a full connection layer and an output layer;
s22, setting initial parameters of a wind power secondary prediction model, and utilizing、/>、/>Training a wind power secondary prediction model, wherein the wind power secondary prediction model is used for training>Vector +.>Will->And->Form a combination vector->Then input into the full connection layer, output +.>；
S23, continuously optimizing parameters of a wind power secondary prediction model based on grid search until the model converges;
and step S3, sending the current weather forecast data into the prediction error estimation model to obtain a future prediction error, and sending the current weather forecast data and the future prediction error into the wind power secondary prediction model together to obtain a final wind power predicted value.
2. The wind power prediction method based on depth error feedback learning according to claim 1, wherein: the step S3 includes:
s31, collecting current weather forecast data of a prediction target wind power plant；
S32, willNormalizing to obtain->；
S33, willSending the prediction error into a trained prediction error estimation model to obtain future prediction error +.>；
S34, will、/>Sending the wind power into a trained wind power secondary prediction model to obtain a prediction result +.>；
S35, willPerforming inverse normalization to obtain final wind power predicted value +.>。
3. The wind power prediction method based on depth error feedback learning according to claim 2, wherein: the weather forecast data comprises wind speed, wind direction, air temperature and air pressure.
CN202310843436.6A 2023-07-11 2023-07-11 Wind power prediction method based on deep error feedback learning Active CN116565865B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310843436.6A CN116565865B (en) 2023-07-11 2023-07-11 Wind power prediction method based on deep error feedback learning

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310843436.6A CN116565865B (en) 2023-07-11 2023-07-11 Wind power prediction method based on deep error feedback learning

Publications (2)

Publication Number Publication Date
CN116565865A CN116565865A (en) 2023-08-08
CN116565865B true CN116565865B (en) 2023-09-26

Family

ID=87486532

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310843436.6A Active CN116565865B (en) 2023-07-11 2023-07-11 Wind power prediction method based on deep error feedback learning

Country Status (1)

Country Link
CN (1) CN116565865B (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107704966A (en) * 2017-10-17 2018-02-16 华南理工大学 A kind of Energy Load forecasting system and method based on weather big data
CN111815033A (en) * 2020-06-19 2020-10-23 上海电力大学 Offshore wind power prediction method based on RCNN and meteorological time sequence characteristics
CN112348292A (en) * 2021-01-07 2021-02-09 中国电力科学研究院有限公司 Short-term wind power prediction method and system based on deep learning network
CN114330915A (en) * 2021-12-31 2022-04-12 青海大学 Short-term wind power combination model prediction method
CN115238980A (en) * 2022-07-13 2022-10-25 湖南大学 Micro-grid transient power angle trajectory prediction method based on attention mechanism and space-time diagram convolutional neural network
CN116307287A (en) * 2023-05-19 2023-06-23 国网信息通信产业集团有限公司 Prediction method, system and prediction terminal for effective period of photovoltaic power generation

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107704966A (en) * 2017-10-17 2018-02-16 华南理工大学 A kind of Energy Load forecasting system and method based on weather big data
CN111815033A (en) * 2020-06-19 2020-10-23 上海电力大学 Offshore wind power prediction method based on RCNN and meteorological time sequence characteristics
CN112348292A (en) * 2021-01-07 2021-02-09 中国电力科学研究院有限公司 Short-term wind power prediction method and system based on deep learning network
CN114330915A (en) * 2021-12-31 2022-04-12 青海大学 Short-term wind power combination model prediction method
CN115238980A (en) * 2022-07-13 2022-10-25 湖南大学 Micro-grid transient power angle trajectory prediction method based on attention mechanism and space-time diagram convolutional neural network
CN116307287A (en) * 2023-05-19 2023-06-23 国网信息通信产业集团有限公司 Prediction method, system and prediction terminal for effective period of photovoltaic power generation

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
偏差修正算法的风电短期功率预测;张瀚超 等;《新型工业化》;第9卷(第2期);1-9 *

Also Published As

Publication number Publication date
CN116565865A (en) 2023-08-08

Similar Documents

Publication Publication Date Title
CN102479347B (en) Method and system for forecasting short-term wind speed of wind farm based on data driving
CN104021427A (en) Method for predicting daily generating capacity of grid-connected photovoltaic power station based on factor analysis
CN103942736B (en) A kind of wind power plant multimachine equivalent modeling method
CN110866633A (en) Micro-grid ultra-short term load prediction method based on SVR support vector regression
Li et al. A short-term photovoltaic power generation forecast method based on LSTM
Xu et al. Short-term wind power forecasting based on Elman neural network with particle swarm optimization
CN113991711A (en) Capacity configuration method for energy storage system of photovoltaic power station
CN116565865B (en) Wind power prediction method based on deep error feedback learning
CN117454939A (en) Wind power prediction method for optimizing BP neural network based on NSABO-Gold algorithm
CN111242371B (en) Photovoltaic power generation short-term prediction correction method based on non-iterative multi-model
CN116187508A (en) Wind turbine generator system fault prediction method integrating knowledge graph and deep learning
CN116128211A (en) Wind-light-water combined short-term optimization scheduling method based on wind-light uncertainty prediction scene
CN115526671A (en) New energy power station site selection method based on improved analytic hierarchy process
CN113780661A (en) Wind power ultra-short-term power prediction method aiming at sudden change wind speed
CN112734073A (en) Photovoltaic power generation short-term prediction method based on long and short-term memory network
He et al. Fault Causes Identification of Transmission Lines Based on Weighted Naive Bayes Classification Algorithm Combined with Complex Algorithm
CN116842855B (en) Distributed photovoltaic power distribution network output prediction method and device, electronic equipment and medium
CN111798034B (en) Wind power prediction system and prediction method based on wind flow field space-time image learning
CN113780643A (en) Photovoltaic power station short-term output prediction method based on case reasoning
CN116896116B (en) Solar grid-connected regulation and control method and system based on artificial intelligence
CN116822370B (en) Ultra-short-term output prediction method for wind power cluster under data driving
Cheng et al. Establishing The Photovoltaic Output Model With PIC-LS-SVM Based on Curve Characteristic Index Dimensionality Reduction
CN109800919B (en) Regional wind farm overall active power prediction method and device
Chen et al. Electric power forecasting based on logistic regression and gradient boost regression tree
Tong et al. An Iterative Dynamic Ensemble Weighting Approach for Ultra-short-term Wind Power Prediction

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