Application of multi-objective evolutionary algorithms for the rehabilitation of storm sewer pipe networks

In recent decades, evolutionary optimisation algorithms have been used successfully for a wide variety of water resources engineering problems and their applications are still increasing. In this research work, a hybrid harmony search algorithm, ‘Non-dominated Sorting Harmony Search’ algorithm is developed and compared with two state-of-the-art multi-objective evolutionary algorithms – the non-dominated sorting genetic algorithm (NSGA)-II and multi-objective particle swarm optimisation (MOPSO) algorithms – for assigning optimal rehabilitation plans for sewer pipe networks. The algorithms considered were validated using some standard test functions reported in the literature and compared with each other in terms of several metrics. These algorithms were then linked to the SWMM-EPA hydraulic model and applied to a storm sewer pipe network case study in Seoul, South Korea, to obtain the best rehabilitation plans for pipe replacements. The results showed that the algorithms considered have different behaviours in solving the benchmark tests and rehabilitation problem. The proposed hybrid multi-objective harmony search algorithm provides better optimal solutions in terms of different metrics and clearly outperforms the other two algorithms for the rehabilitation of the storm sewer pipe networks.