Opposition-Based Multiple-Objective Differential Evolution to Solve the Time–Cost–Environment Impact Trade-Off Problem in Construction Projects

Abstract

Current competitive conditions in the construction market require that construction companies satisfy customer needs using increasingly tight project budgets. The key indicators of success currently used on most construction projects include meeting project duration, cost, and quality targets. Project decision makers seldom consider customer expectations related to project-related environmental impact. Quantitative assessments of project-related emissions should be conducted during the project-planning phase. Trade-off optimization among project duration (time), project cost, and project environmental impact is necessary to enhance the overall construction project benefit. This paper develops a novel optimization algorithm, the opposition-based multiple-objective differential evolution (OMODE), to solve the time–cost–environmental impact tradeoff (TCET) problem. This novel algorithm uses an opposition-based learning technique for population initialization and for generation jumping. Opposition numbers are used to improve the exploration and convergence performance of the optimization process. A numerical case study of tunnel construction demonstrates the ability of OMODE-generated nondominated solutions to assist project managers in selecting a plan to optimize TCET, an operation that is otherwise difficult and time-consuming. Comparisons with the nondominated sorting genetic algorithm (NSGA-II), multiple-objective particle swarm optimization (MOPSO), and multiple-objective differential evolution (MODE) verify the efficiency and effectiveness of the proposed algorithm.