Evolutionary Algorithm for Selecting Wastewater System Configuration

This study proposes a new methodology for selecting a near-optimal configuration of wastewater system components considering the uncertainty in water consumption and population spatial distribution. The proposed methodology is composed of two stages: (1)lay out local sewer networks at the minimum possible cost as a tree graph, and (2)lay out the wastewater system, including the number, location, capacity, and service area of the planned treatment facilities for collecting, treating, and reusing municipal wastewater with minimum life-cycle costs and greenhouse gas emissions. The second stage uses a multiobjective genetic algorithm (NSGA-II) and Monte Carlo simulation, and a breadth-first search algorithm. The proposed methodology was applied to a sewer network in Sahab City, Jordan. The behavior of the proposed approach was statistically evaluated under positive and negative population growth rate scenarios, and the resulting behavior of the proposed algorithm was compared with the results of a current state-of-art planning algorithm that does not consider the change in population spatial distribution throughout the analysis period. The results show that the proposed algorithm outperforms the existing planning model by achieving statistically significant improvement in the life-cycle costs and greenhouse gas emissions at the end of the planning period.