基于BP神经网络的城市时用水量分时段预测模型

来源期刊:中南大学学报(自然科学版)2012年第8期

论文作者:向平 张蒙 张智 张南

文章页码:3320 - 3324

关键词:时用水量;BP神经网络;分时段用水量模型;影响因子

Key words:hourly water consumption; BP neural network; period-divided water consumption model; impact factors

摘    要:针对目前时用水量预测模型中对时用水量影响因素分析研究较少的问题,通过分析各种时用水量影响因素与时用水量之间的相关性,筛选出时用水量的主要影响因子;通过分类将1 d划分为3个时段,建立分时段用水量模型。采用BP神经网络预测,精度指标采用平均绝对百分比误差(MAPE)表示。实例分析结果表明:模型预测MAPE均在5%以内,预测精度较高,满足供水系统优化调度的要求,为城市时用水量预测提供一种简单可行的思路和方法。

Abstract: At present there are scant studies on the impact factors of hourly water demand in the water demand prediction. This work investigated the main impact factors for the water consumption in different hours through the analysis on the correlation between the different impact factors and the hourly water consumption. The period-divided prediction model was established on the basis of three divided periods of one day. And BP neural network was used to predict. Precision index was indicated with MAPE value. Case analysis results show that for the established period-divided water consumption prediction model, MAPE values are all within 5%, which indicates a high prediction accuracy, and the water supply system optimization scheduling requirements can be met, providing a simple and feasible approach and method for the urban hourly water consumption prediction.

相关论文

  • 暂无!

相关知识点

  • 暂无!

有色金属在线官网  |   会议  |   在线投稿  |   购买纸书  |   科技图书馆

中南大学出版社 技术支持 版权声明   电话:0731-88830515 88830516   传真:0731-88710482   Email:administrator@cnnmol.com

互联网出版许可证:(署)网出证(京)字第342号   京ICP备17050991号-6      京公网安备11010802042557号