Water demand prediction optimization method in Shenzhen based on the zero-sum game model and rolling revisions

Xin Liu; Xuefeng Sang; Jiaxuan ChangYang ZhengYuping Han

首页> 外文期刊>Water policy >Water demand prediction optimization method in Shenzhen based on the zero-sum game model and rolling revisions

【24h】

Water demand prediction optimization method in Shenzhen based on the zero-sum game model and rolling revisions

机译：Water demand prediction optimization method in Shenzhen based on the zero-sum game model and rolling revisions

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相关主题

摘要

In this study, a deep learning model based on zero-sum game (ZSG) was proposed for accurate water demand prediction. Theensemble learning was introduced to enhance the generalization ability of models, and the sliding average was designed tosolve the non-stationarity problem of time series. To solve the problem that the deep learning model could not predictwater supply fluctuations caused by emergencies, a hypothesis testing method combining Student’s t-test and discrete wavelettransform was proposed to generate the envelope interval of the predicted values to carry out rolling revisions. The researchmethods were applied to Shenzhen, a megacity with extremely short water resources. The research results showed that theregular bidirectional models were superior to the unidirectional model, and the ZSG-based bidirectional models were superiorto the regular bidirectional models. The bidirectional propagation was conducive to improving the generalization ability of themodel, and ZSG could better guide the model to find the optimal solution. The fluctuations in water supply were mainly causedby the floating population, but the fluctuation was still within the envelope interval of the predicted values. The predicted valuesafter rolling revisions were very close to the measured values.

著录项

来源
《Water policy》 |2021年第6期|1506-1529|共24页
作者
Xin Liu; Xuefeng Sang; Jiaxuan ChangYang ZhengYuping Han;
展开▼
作者单位

China Institute of Water Resources and Hydropower Research, Beijing 100038, China;

North China University of Water Resources and Electric Power, Zhengzhou 450046, China;

North China University of Water Resources and Electric Power, Zhengzhou 450046, China, China Institute of Water Resources and Hydropower Research, Beijing 100038, China;

展开▼
收录信息
原文格式 PDF
正文语种英语
中图分类水文科学（水界物理学）;
关键词
Deep learning; Discrete wavelet transform; Ensemble learning; Envelope interval; Rolling revisions; Zero-sum game;

Water demand prediction optimization method in Shenzhen based on the zero-sum game model and rolling revisions

摘要

著录项

相关主题

期刊订阅