Research on Forecasting Method of Urban Water Demand Based on Fuzzy Theory

Water demand forecasting is very important in urban water supply management. A large number of researches have been done on water demand forecasting methods. In order to meet the easy operation and high accuracy requirements, a new forecasting method based on fuzzy theory, adaptive neuro-fuzzy inference system (ANFIS), was presented. The parameters of this method are obtained by the original fuzzy rules from the samples and optimized according to the latest history data based on adaptive mix learning arithmetic. At the same time, this forecasting system input variables are embodied the information, such as factors of burthen increasing, periodicity, the load changeable trends and the weather etc. The system configuration is very simple and valid. Based on imitated example, the consequence predicting precision of this method can satisfy the engineering request.