Risk aware optimization of water sensor placement

This paper addresses the identification of optimal "sensing spots", within a network for monitoring the spread of "effects"triggered by "events". Many real-world problems fit into this general framework: we focused on the early detection of contamination events in Water Distribution Networks (WDN). We model the sensor placement as a bi-objective optimization problem, aiming at minimizing the mean and standard deviation of detection time over a set of different simulated contamination events and solved using NSGA-II. A problem-specific data structure is proposed enabling a deeper analysis of empirical convergence of the population.