Fuzzy clustering chaotic-based differential evolution for resource leveling in construction projects

Abstract

Project scheduling is an important part of project planning in many management companies. Resource leveling problem describes the process of reducing the fluctuations in resource usage over the project duration. The goal of resource leveling is to minimize the incremental demands that cause fluctuations of resources, and thus avoid undesirable cyclic hiring and firing during project execution. In this research, a novel optimization model, named as Fuzzy Clustering Chaotic-based Differential Evolution for solving Resource leveling (FCDE-RL), is introduced. Fuzzy Clustering Chaotic-based Differential Evolution (FCDE) is developed by integrating original Differential Evolution with fuzzy c-means clustering and chaotic techniques to tackle complex optimization problems. Chaotic was exploited to prevent the optimization algorithm from premature convergence. Meanwhile, fuzzy c-means clustering acts as several multi-parent crossover operators to utilize the information of the population efficiently to enhance the convergence. Experimental results revealed that the new optimization model is a promising alternative to assist project managers in dealing with construction project resource leveling.