陕西科技大学学报2024，Vol.42Issue(1)：177-185,9.
基于VMD-BiLSTM-WOA的短期风电功率预测
Short-term wind power prediction based on VMD-BiLSTM-WOA
摘要
Abstract
Wind power generation is of great significance to solve the problem of global energy shortage,and accurate prediction of wind power power is helpful to the reasonable dispatc-hing of wind power grid connection and the reliable operation of power grid.In this paper,a hybrid deep learning model based on variational mode decomposition(VMD),bidirectional long short-term memory network(BiLSTM)and whale optimization algorithm(WOA)is proposed for short-term wind power prediction.First,VMD decomposes the original wind power into multiple sub-modes,effectively reducing the series volatility.Then one BiLSTM model is established for each sub-mode,and WOA is used to optimize the parameters in BiL-STM to improve the efficiency and prediction performance of the hybrid model.Finally,the results of each sub-model are superimposed to obtain the final prediction results.In the ex-periment,different comparison models are established to illustrate the effectiveness and supe-riority of the improved strategy.The results show that the hybrid model proposed in this pa-per has higher prediction accuracy in wind power prediction.关键词
风电功率/变分模态分解/双向长短期记忆网络/鲸鱼优化/长短期记忆网络Key words
wind power/variational mode decomposition/bidirectional long short-term mem-ory network/whale optimization/long short-term memory network分类
信息技术与安全科学引用本文复制引用
史加荣,王双馨..基于VMD-BiLSTM-WOA的短期风电功率预测[J].陕西科技大学学报,2024,42(1):177-185,9.基金项目
国家重点研发计划项目(2018YFB1502902) （2018YFB1502902）
陕西省科技厅自然科学基金项目(2021JM-378,2021JQ-493) （2021JM-378,2021JQ-493）
