Applying knowledge discovery to predict water-supply consumption

Optimizing the control of operations in a municipal water distribution system can reduce electricity costs and realize other economic benefits. However, optimal control requires the ability to precisely predict short-term water demand so that minimum-cost pumping schedules can be prepared. One of the objectives of our project to develop an intelligent system for monitoring and controlling municipal water-supply systems is to ensure optimal control and reduce energy costs. Hence, prediction of water demand is essential. We present an application of a rough-set approach for the automated discovery of rules from a set of data samples for daily water-demand predictions. The database contains 306 training samples, covering information on seven environmental and sociological factors and their corresponding daily volume of distribution flow. The rough-set method generates prediction rules from the observed data, using statistical information that is inherent in the data to handle incomplete and ambiguous training samples. Experimental results indicate that this method provides more precise information than is available through knowledge acquisition from human experts