基于双层经验模态分解和神经网络的城市短期需水量预测研究  

Research on short term water demand prediction of cities based on double layer empirical mode decomposition and neural networks

作　　者：韩冰 傅继晗 HAN Bing;FU Jihan(Zhejiang Tongji Vocational College of Science and Technology,Hang Zhou 311231,China)

机构地区：[1]浙江同济科技职业学院,浙江杭州311231

出　　处：《通信与信息技术》2024年第6期20-23,共4页Communication & Information Technology

基　　金：2023年度学校重大水利科技项目培育项目(项目编号:FRF23PY004)。

摘　　要：探讨了基于双层经验模态分解方法在城市短期需水量预测中的应用。针对城市需水量时间序列的非线性、非平稳特性,文章提出了一种结合双层经验模态分解法与最小二乘法和长短期记忆法两种神经网络相结合的混合方法,以提高预测的准确性和稳定性。实验结果表明,该方法能够提高城市短期需水量预测的精度和稳定性,具有较高的实用价值。为城市供水系统的优化调度提供有力支持。This article explores the application of the double-layer empirical mode decomposition method in short-term urban wa-ter demand forecasting.In response to the nonlinear and non-stationary characteristics of urban water demand time series,this article proposes a hybrid method that combines double-layer empirical mode decomposition with least squares and long short-term memory methods to improve the accuracy and stability of prediction.The experimental results show that this method can improve the accuracy and stability of short-term water demand prediction in cities,and has high practical value.It provide strong support for the optimization and scheduling of urban water supply systems.

关 键 词：需水量预测 双层经验模态分解 最小二乘法 长短期记忆法 

分 类 号：TP311.1[自动化与计算机技术—计算机软件与理论]