长江科学院院报2024，Vol.41Issue(12)：9-14,6.DOI:10.11988/ckyyb.20230804
基于深度学习的三峡电站未来坝前最大最小水位预测
Predicting Maximum and Minimum Future Water Levels in front of Three Gorges Dam Using Deep Learning
摘要
Abstract
The maximum and minimum water levels are crucial constraints in the calculation of cascade reservoir op-erations and the economic operation of hydropower stations.Traditional iterative methods for multi-period predictions lack credibility due to error accumulation.This study employs a Long Short-Term Memory(LSTM)model which is effective in handling time series problems to predict the maximum and minimum water levels of the Three Gorges Reservoir over the next four days.Two LSTM-based deep learning models incorporating different characteristic varia-bles are developed,and a conventional forecast model based on the water balance framework is also constructed for comparison.Results demonstrate that the deep learning model,which considers the propagation law of water surface profiles in the Three Gorges Reservoir area,delivers accurate and stable predictions,achieving an absolute error of less than 40 cm for 99％of the predictions.关键词
水电站经济运行/水位预测/LSTM/深度学习/神经网络/三峡电站Key words
economic operation of hydropower station/water level prediction/LSTM/deep learning/neural network/Three Gorges hydropower station分类
建筑与水利引用本文复制引用
王永强,张森,谢帅,周涛..基于深度学习的三峡电站未来坝前最大最小水位预测[J].长江科学院院报,2024,41(12):9-14,6.基金项目
国家重点研发计划重点专项(2022YFC3202300) （2022YFC3202300）
国家自然科学基金面上项目(42271044) （42271044）
水利部重大科技项目(SKS-2022120) （SKS-2022120）
湖北省自然科学基金联合基金项目(2022CFD027) （2022CFD027）
中央级公益性科研院所基本科研业务费项目(CKSF2021486) （CKSF2021486）
中国长江电力股份有限公司资助项目(Z242302057) （Z242302057）
