Time Series Analysis and Forecasting pp 329-340
Forecasting Daily Water Demand Using Fuzzy Cognitive Maps
- Cite this paper as:
- Salmeron J.L., Froelich W., Papageorgiou E.I. (2016) Forecasting Daily Water Demand Using Fuzzy Cognitive Maps. In: Rojas I., Pomares H. (eds) Time Series Analysis and Forecasting. Contributions to Statistics. Springer, Cham
In this chapter, we describe the design of a multi-regressive forecasting model based on fuzzy cognitive maps (FCMs). Growing window approach and 1-day ahead forecasting are assumed. The proposed model is retrained every day as more data become available. To improve forecasting accuracy, mean daily temperature and precipitation are applied as additional explanatory variables. The designed model is trained and tested using data gathered from a water distribution system. Comparative experiments provide evidence for the superiority of the proposed approach over the selected state-of-the-art competitive methods.