Prediction method of wind power output based on a Bayes-LSTM network

被引：0

作者：

Chen F. ^{[1
]}

Yu Y. ^{[1
]}

Xu J. ^{[1
]}

Yang J. ^{[1
]}

Chen K. ^{[1
]}

Zhang T. ^{[2
]}

Guo L. ^{[3
]}

Zheng Z. ^{[3
]}

Hu P. ^{[3
]}

机构：

[1] State Grid Hubei Electric Power Company Limited Economic Research Institute, Wuhan

[2] State Grid Shijiazhuang Power Supply Company, Shijiazhuang

[3] School of Electrical Engineering and Automation, Wuhan University, Wuhan

来源：

Dianli Xitong Baohu yu Kongzhi/Power System Protection and Control | 2023年 / 51卷 / 06期

基金：

中国国家自然科学基金;

关键词：

Bayes optimization; deep learning; feature extraction; wind power output prediction;

D O I：

10.19783/j.cnki.pspc.220817

中图分类号：

学科分类号：

摘要：

To improve the prediction accuracy of wind power output, a model using a long- and short-term memory (LSTM) artificial neural network based on Bayesian optimization is proposed. First, empirical mode decomposition is used to decompose an historical output series of wind power, and eight statistical features are extracted from each component and the original data respectively. In this way a prediction feature set is formed together with the output values at the first six moments of prediction. Then, a least absolute shrinkage and selection operator (LASSO) algorithm is used to extract the feature subset with statistical significance from the prediction feature set as the input to the prediction model. Finally, an optimization method of an LSTM network based on Bayesian super-parameters optimization is proposed to improve prediction accuracy. The historical data of wind power output in a city in Hubei Province are selected for a prediction experiment. The results show that, compared with a BP neural network, support vector machine (SVM), radial basis function (RBF) network, general regression neural networks (GRNN) network and other prediction models, the proposed model has higher accuracy and the feature extraction method is more reasonable. © 2023 Power System Protection and Control Press. All rights reserved.

引用

页码：170 / 178

页数：8

共 27 条

[1] SUN Rong, LI Qiang, LUO Haifeng, Et al., Wind power forecasting based on error correction using adaptive moving smoothing and time convolution network, Journal of Global Energy Interconnection, 5, 1, pp. 11-22, (2022)
[2] JIA Rui, YANG Guohua, ZHENG Haofeng, Et al., Combined wind power prediction method based on CNN-LSTM&GRU with adaptive weights, Electric Power, 55, 5, pp. 47-56, (2022)
[3] ZHANG Binqiao, GE Suye, LI Cheng, Markov Chain wind speed prediction model based on Copula function, Smart Power, 49, 11, pp. 24-30, (2021)
[4] SU Jiantao, ZHENG Shuting, YAN Gangui, Et al., Research on day-ahead forecast of wind power based on FCM-equivalent wind speed model, Power System and Clean Energy, 38, 2, pp. 110-120, (2022)
[5] YANG Hong, YAN Yujie, WANG Yu, Applicability of Beta distribution on wind power forecast error modeling, Electrical Measurement & Instrumentation, 57, 11, pp. 37-41, (2020)
[6] ZHONG Yashan, FU Cong, QIAN Feng, Et al., Economic dispatch model of an integrated energy system considering generalized energy storage and conditional value at risk, Power System Protection and Control, 50, 9, pp. 54-63, (2022)
[7] ZHAO Fulin, YU Xiaoling, DU Shijia, Et al., Assessment on flexibility of a power grid with large-scale wind farm integration considering demand response, Power System Protection and Control, 49, 1, pp. 42-51, (2021)
[8] DING Teng, FENG Donghan, LIN Xiaofan, Et al., Ultra-short-term wind speed forecasting based on improved ARIMA-GARCH model, Power System Technology, 41, 6, pp. 1808-1814, (2017)
[9] CAO Junbo, ZHOU Renjun, DENG Xuehua, Et al., wind power forecast considering differential times of optimal ARIMA model, Proceedings of the CSU-EPSA, 31, 1, pp. 105-111, (2019)
[10] LIU Fang, WANG Zhen, LIU Ruidi, Et al., Short-term forecasting method of wind power generation based on BP neural network with combined loss function, Journal of Zhejiang University (Engineering Science), 55, 3, pp. 594-600, (2021)

← 1 2 3 →