Hybrid Estimation of Distribution Algorithm for solving Single Row Facility Layout Problem

• EDAhybrid hybridizes Estimation of Distribution Algorithm and PSO.
• Extended Artificial Chromosome Genetic Algorithm (eACGA) is developed as comparer.
• SRFLP is chosen to test the performance of EDAhybrid and eACGA.
• Enhanced SRFLP is designed to make the basic SRFLP closer to real case.
• EDAhybrid can be used as a method to deal with SRFLP and get high quality solution.

The layout positioning problem of facilities on a straight line is known as Single Row Facility Layout Problem (SRFLP). The objective of SRFLP, categorized as NP Complete problem, is to arrange the layout so that the sum of distances between all facilities’ pairs can be minimized.Estimation of Distribution Algorithm (EDA) efficiently improves the solution quality in first few runs, but the diversity loss grows rapidly as more iterations are run. To maintain the diversity, hybridization with metaheuristic algorithms is needed. This research proposes Hybrid Estimation of Distribution Algorithm (EDAhybrid), an algorithm which consists of hybridization of EDA, Particle Swarm Optimization (PSO), and Tabu Search. Another hybridization algorithm, extended Artificial Chromosomes Genetic Algorithm (eACGA), is also built as benchmark. EDAhybrid’s performance is tested in 15 benchmark problems of SRFLP and it successfully achieves optimum solution. Moreover, the mean error rates of EDAhybrid always get the lowest value compared to other algorithms.SRFLP can be enhanced by considering more constraints, so it becomes enhanced SRFLP. Computational results show that EDAhybrid can also solve Enhanced SRFLP effectively. Therefore, we can conclude that EDAhybrid is a promising metaheuristic algorithm which can be used to solve the basic and enhanced SRFLP.