A TOOLSET FOR CONSTRUCTION OF HYBRID INTELLIGENT FORECASTING SYSTEMS - APPLICATION FOR WATER DEMAND PREDICTION

This paper presents the intelligent Forecasters Construction Set (IFCS ) which is a toolset for constructing forecasting applications. The to olset supports the intelligent techniques of fuzzy logic, artificial n eural networks, knowledge-based and case-based reasoning. The develope r can construct a forecasting application using rules, procedures and flow diagrams, which are organized into a hierarchy of workspaces. The modularity of the IFCS allows subsequent addition of other modules of intelligent techniques. The IFCS was used for developing a water dema nd forecasting system based on real-world data obtained from the City of Regina's water distribution system and Environment Canada. A utilit y demand prediction system developed with the IFCS system is useful fo r optimizing operation costs of water plants. Some water plants need t o pay a flat rate for electricity, which is set depending on peak kilo watt demand. Hence, if the peak kilowatt demand can be reduced, the op erating costs of the plant can be lessened (Jamieson RA et al. America n Water Works Association Journal 1993;85:48-55). An energy management system needs a good estimate of future customer demand in order to fi nd the optimal pumping schedules that can minimize the peak kilowatt d emand. Since the IFCS supports developing multiple predictor models, m odeling of data can be expedited. The benefits of using multiple modul es of artificial neural networks for demand prediction are presented. The results from this approach are compared with a linear regression a nd a case-based reasoning program. The performance comparisons among t he forecasters will be discussed. (C) 1998 Elsevier Science Ltd. All r ights reserved.