Adaptive Multipopulation Evolutionary Algorithm for Contamination Source Identification in Water Distribution Systems

Real-time monitoring of drinking water in a water distribution system (WDS) can effectively warn of and reduce safety risks. One of the challenges is to identify the contamination source through these observed data due to the real-time, nonuniqueness, and large-scale characteristics. To address the real-time and nonuniqueness challenges, we propose an adaptive multipopulation evolutionary optimization algorithm to determine the real-time characteristics of contamination sources, where each population aims to locate and track a different global optimum. The algorithm adaptively adjusts the number of populations using a feedback learning mechanism. To effectively locate an optimal solution for a population, a coevolutionary strategy is used to identify the location and the injection profile separately. Experimental results from three WDS networks show that the proposed algorithm is competitive in comparison with three other state-of-the-art evolutionary algorithms.