Title :
Prediction of Urban Short-Term Water Consumption in Zhengzhou City
Author :
Liu, Jianhua ; Zhang, Rui ; Wang, Lailing
Author_Institution :
North China Univ. of Water Conservancy & Electr. Power, Zhengzhou, China
Abstract :
For supplying optimal scheduling of Zhengzhou city with short-term water consumption data, this paper builds three types of forecasting model according to moving arithmetic mean method, regression analysis method and BP neural network. As a result, forecasting result is obtained by water supply data and meteorological data. The study shows that three different methods all can meet the need of urban water supply project in the prediction of hourly water consumption. Regression analysis and BP neural network can obtain better forecasting result and can gracefully satisfy the request of urban water supply scheduling. If water consumption measured in 15-minute unit, the forecasting result of BP neural network is better, this can meet the urban water supply request better.
Keywords :
backpropagation; forecasting theory; moving average processes; neural nets; regression analysis; scheduling; water supply; BP neural network; backpropagation; forecasting model; meteorological data; moving arithmetic mean method; optimal scheduling; regression analysis; urban short term water consumption; urban water supply scheduling; Cities and towns; Economic forecasting; Meteorology; Neural networks; Optimal scheduling; Predictive models; Regression analysis; Time series analysis; Water conservation; Weather forecasting; neural network; regression analysis; urban water supply system; water consumption forecast;
Conference_Titel :
Intelligent Computation Technology and Automation (ICICTA), 2010 International Conference on
Conference_Location :
Changsha
Print_ISBN :
978-1-4244-7279-6
Electronic_ISBN :
978-1-4244-7280-2
DOI :
10.1109/ICICTA.2010.535