基于改进GRU的城市供水管网流量预测研究  

Research on Flow Forecasting Methods for Urban Water Supply Network Based on Improved GRU

作　　者：夏巍 汪石 梁祥莹 XIA Wei;WANG Shi;LIANG Xiangying(School of Electronic and Information Engineering,Anhui Jianzhu University,Hefei 230601,China)

机构地区：[1]安徽建筑大学电子与信息工程学院,安徽合肥230601

出　　处：《安徽建筑大学学报》2023年第2期51-54,共4页Journal of Anhui Jianzhu University

基　　金：国家科技重大专项课题项目(2014ZX074055-003-03);安徽省高校省级自然科学研究项目(KJ2019JD15)。

摘　　要：城市供水管网随着城市规模的扩大和人口的增加等因素的变化而越来越复杂,供水管网的流量预测在管网的优化调度工作中发挥了有效作用。本文通过分析某城市供水管网系统的多个监测节点的流量数据,以类似局部加权线性回归的方法优化GRU算法,构建了基于多监测节点的流量预测模型,提高了模型的泛化能力。利用该市供水管网监测平台采集的监测节点流量数据进行验证,实验的结果表明,基于改进的GRU流量预测模型有着较好的预测精度。The urban water supply network is becoming more complex as the city's size and population growing.Flow forecasting plays a role in water supply network optimization.With flow data of city water supply system,this research constructs a flow prediction model based on multiple monitoring nodes by analyzing the flow data of different nodes in a city water supply system,and increasing the Gated Recurrent Unit(GRU)algorithm’s generalization using an approach comparable to local weighted linear regression.Using another node’s flow data of the system for validation,and the results show that the improved GRU flow prediction model has better accuracy.

关 键 词：供水管网 流量预测 GRU算法 局部加权线性回归 

分 类 号：TU990.3[建筑科学—市政工程]