LSTM-based Prediction of Short-term Water Level for Three Gorges and Gezhouba Cascade Powerplants

Water level prediction for the Three Gorges-Gezhouba cascade hydropower stations is crucial for their safe and stable operation and overall benefits. Nevertheless, due to the combined effects of multiple factors, such as the complex transformation between dynamic and static storage-capacity calculat...

Full description

Saved in:
Bibliographic Details
Main Author: WANG Tao, XU Yang, CAO Hui, LIU Ya-xin, MA Hao-yu, ZHANG Zheng, XIE Shuai, CHANG Xin-yu
Format: Article
Language:zho
Published: Editorial Office of Journal of Changjiang River Scientific Research Institute 2025-04-01
Series:长江科学院院报
Subjects:
Online Access:http://ckyyb.crsri.cn/fileup/1001-5485/PDF/1001-5485(2025)04-0080-07.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849331331577675776
author WANG Tao, XU Yang, CAO Hui, LIU Ya-xin, MA Hao-yu, ZHANG Zheng, XIE Shuai, CHANG Xin-yu
author_facet WANG Tao, XU Yang, CAO Hui, LIU Ya-xin, MA Hao-yu, ZHANG Zheng, XIE Shuai, CHANG Xin-yu
author_sort WANG Tao, XU Yang, CAO Hui, LIU Ya-xin, MA Hao-yu, ZHANG Zheng, XIE Shuai, CHANG Xin-yu
collection DOAJ
description Water level prediction for the Three Gorges-Gezhouba cascade hydropower stations is crucial for their safe and stable operation and overall benefits. Nevertheless, due to the combined effects of multiple factors, such as the complex transformation between dynamic and static storage-capacity calculations and the unsteady flow downstream of the stations, traditional methods struggle to accurately predict short-term water levels. When the stations perform peak-shaving and frequency-regulation tasks under complex operating conditions, there is a risk of violating scheduling regulations and opening the gates, which may lead to engineering safety hazards and economic losses. In this study, we employed the Long Short-Term Memory (LSTM) deep-learning method to develop an ultra-short-term water-level prediction model for the Three Gorges-Gezhouba Hydropower Stations. We utilized water-level, inflow, and output data to forecast the ultra-short-term water-level processes of the stations. Subsequently, we analyzed the prediction accuracy of the model using data from peak-shaving scenarios. The results show that the model exhibits high overall accuracy, stability, and adaptability, and maintains stable prediction accuracy under different peak-shaving conditions. However, the prediction results tend to be homogenized at extreme water levels. The average error of 24-hour water-level prediction for the upstream of the Three Gorges and Gezhouba is less than 0.05 m. These findings can offer technical support for the refined scheduling of cascade hydropower stations.
format Article
id doaj-art-431114b7d25a46b4bf2fc13d7d958f2c
institution Kabale University
issn 1001-5485
language zho
publishDate 2025-04-01
publisher Editorial Office of Journal of Changjiang River Scientific Research Institute
record_format Article
series 长江科学院院报
spelling doaj-art-431114b7d25a46b4bf2fc13d7d958f2c2025-08-20T03:46:38ZzhoEditorial Office of Journal of Changjiang River Scientific Research Institute长江科学院院报1001-54852025-04-01424808610.11988/ckyyb.20240008LSTM-based Prediction of Short-term Water Level for Three Gorges and Gezhouba Cascade PowerplantsWANG Tao, XU Yang, CAO Hui, LIU Ya-xin, MA Hao-yu, ZHANG Zheng, XIE Shuai, CHANG Xin-yu01 Hubei Provincial Key Laboratory of Smart Yangtze River and Hydropower Science,China Yangtze Power;Co.,Ltd.,Yichang 443000,China;2 Cascade Dispatching Communication Center for the Three Gorges Project,China Yangtze Power Co., Ltd., Yichang 443000,China;3 Water Resources Department, Changjiang RiverScientific Research Institute, Wuhan 430000,China;4 School of Civil and Hydraulic Engineering, HuazhongUniversity of Science and Technology, Wuhan 430000,ChinaWater level prediction for the Three Gorges-Gezhouba cascade hydropower stations is crucial for their safe and stable operation and overall benefits. Nevertheless, due to the combined effects of multiple factors, such as the complex transformation between dynamic and static storage-capacity calculations and the unsteady flow downstream of the stations, traditional methods struggle to accurately predict short-term water levels. When the stations perform peak-shaving and frequency-regulation tasks under complex operating conditions, there is a risk of violating scheduling regulations and opening the gates, which may lead to engineering safety hazards and economic losses. In this study, we employed the Long Short-Term Memory (LSTM) deep-learning method to develop an ultra-short-term water-level prediction model for the Three Gorges-Gezhouba Hydropower Stations. We utilized water-level, inflow, and output data to forecast the ultra-short-term water-level processes of the stations. Subsequently, we analyzed the prediction accuracy of the model using data from peak-shaving scenarios. The results show that the model exhibits high overall accuracy, stability, and adaptability, and maintains stable prediction accuracy under different peak-shaving conditions. However, the prediction results tend to be homogenized at extreme water levels. The average error of 24-hour water-level prediction for the upstream of the Three Gorges and Gezhouba is less than 0.05 m. These findings can offer technical support for the refined scheduling of cascade hydropower stations.http://ckyyb.crsri.cn/fileup/1001-5485/PDF/1001-5485(2025)04-0080-07.pdfwater level prediction|cascade powerplant|lstm|three gorges powerplant|gezhouba powerplant|error analysis
spellingShingle WANG Tao, XU Yang, CAO Hui, LIU Ya-xin, MA Hao-yu, ZHANG Zheng, XIE Shuai, CHANG Xin-yu
LSTM-based Prediction of Short-term Water Level for Three Gorges and Gezhouba Cascade Powerplants
长江科学院院报
water level prediction|cascade powerplant|lstm|three gorges powerplant|gezhouba powerplant|error analysis
title LSTM-based Prediction of Short-term Water Level for Three Gorges and Gezhouba Cascade Powerplants
title_full LSTM-based Prediction of Short-term Water Level for Three Gorges and Gezhouba Cascade Powerplants
title_fullStr LSTM-based Prediction of Short-term Water Level for Three Gorges and Gezhouba Cascade Powerplants
title_full_unstemmed LSTM-based Prediction of Short-term Water Level for Three Gorges and Gezhouba Cascade Powerplants
title_short LSTM-based Prediction of Short-term Water Level for Three Gorges and Gezhouba Cascade Powerplants
title_sort lstm based prediction of short term water level for three gorges and gezhouba cascade powerplants
topic water level prediction|cascade powerplant|lstm|three gorges powerplant|gezhouba powerplant|error analysis
url http://ckyyb.crsri.cn/fileup/1001-5485/PDF/1001-5485(2025)04-0080-07.pdf
work_keys_str_mv AT wangtaoxuyangcaohuiliuyaxinmahaoyuzhangzhengxieshuaichangxinyu lstmbasedpredictionofshorttermwaterlevelforthreegorgesandgezhoubacascadepowerplants