| Comparative study of multi-objective evolutionary algorithms for hydraulic rehabilitation of urban drainage networks |
|---|
|
학술지명 Talor & Francis
저자 노준우,J. Yaz,김중훈
발표일 2017-05-01
|
|
Multi-Objective Evolutionary Algorithms (MOEAs) are flexible and powerful tools for solving a wide varietyof non-linear and non-convex problems in water resources engineering contexts. In this work, two wellknownMOEAs, the Strength Pareto Evolutionary Algorithm (SPEA2) and Non-dominated Sorting GeneticAlgorithm (NSGA2), and two additional MOEAs that are extended versions of harmony search (HS) anddifferential evolution (DE), are linked to the Environmental Protection Agency’s Storm Water ManagementModel (SWMM-EPA), which is a hydraulic model used to determine the best pipe replacements in a set ofsewer pipe networks to decrease urban flooding overflows. The performance of the algorithms is comparedfor several comparative metrics. The results show that the algorithms exhibit different behaviours in solvingthe hydraulic rehabilitation problem. In particular, the multi-objective version of the HS algorithm providesbetter optimal solutions and clearly outperforms the other algorithms for this type of nondeterministicpolynomial-time hard (NP-hard) problem. |