电力科技与环保2024，Vol.40Issue(4)：380-387,8.DOI:10.19944/j.eptep.1674-8069.2024.04.006
基于双向LSTM-Attention模型的火电厂负荷预测研究
Research on load prediction of thermal power plants based on BiLSTM-Attention model
摘要
Abstract
Accurate prediction of load can guide thermal power plants to formulate power generation plans and scheduling arrangements,which is conducive to their reduction of energy costs and pollution emissions,and is of great significance to the economy and environmental protection of power plants. Therefore,a load forecasting method of thermal power plant based on BiLSTM-Attention is proposed in this paper. Firstly,the key characteristic variables are screened by Pearson coefficient. Secondly,BiLSTM was used to extract the long-term dependence relationship and short-term change characteristics among key variables,and finally,the Attention mechanism was integrated to further highlight the key timing information,so as to achieve accurate load prediction. A 600 MW supercritical unit in service was used for validation. Compared to LSTM,BiLSTM,LSTM-Attention,the results of BiLSTM-Attention show that the coefficient of determination R2,root mean square error SRMSE and mean absolute error SMAE are optimal,they are 0.9566、16.3159、13.5043,which can more accurately capture the trend of rapid load fluctuation,it can take the accurate prediction of load for thermal power plants.关键词
火电厂/负荷预测/双向LSTM模型/Attention机制/能源管理Key words
thermal power plant/load prediction/BiLSTM model/Attention mechanism/energy management分类
能源科技引用本文复制引用
陈恩帅,茅大钧,陈思勤,魏立志..基于双向LSTM-Attention模型的火电厂负荷预测研究[J].电力科技与环保,2024,40(4):380-387,8.基金项目
国家自然科学基金项目(62373241) （62373241）
中国华能集团有限公司2022年度科技项目(HNKJ22-HF22) （HNKJ22-HF22）
