Search

Job shop scheduling problem (JSSP) is a typical NP-hard problem. In order to improve the solving efficiency for JSSP, a hybrid differential evolution and estimation of distribution algorithm based on neighbourhood search is proposed in this paper, which combines the merits of Estimation of distribution algorithm and Differential evolution (DE). Meanwhile, to strengthen the searching ability of the proposed algorithm, a chaotic strategy is introduced to update the parameters of DE. Two mutation operators are adopted. A neighbourhood search (NS) algorithm based on blocks on critical path is used to further improve the solution quality. Finally, the parametric sensitivity of the proposed algorithm has been analysed based on the Taguchi method of design of experiment. The proposed algorithm was tested through a set of typical benchmark problems of JSSP. The results demonstrated the effectiveness of the proposed algorithm for solving JSSP. [ABSTRACT FROM PUBLISHER]

This article presents an effective estimation of distribution algorithm, named P-EDA, to solve the blocking flow-shop scheduling problem (BFSP) with the makespan criterion. In the P-EDA, a Nawaz-Enscore-Ham (NEH)-based heuristic and the random method are combined to generate the initial population. Based on several superior individuals provided by a modified linear rank selection, a probabilistic model is constructed to describe the probabilistic distribution of the promising solution space. The path relinking technique is incorporated into EDA to avoid blindness of the search and improve the convergence property. A modified referenced local search is designed to enhance the local exploitation. Moreover, a diversity-maintaining scheme is introduced into EDA to avoid deterioration of the population. Finally, the parameters of the proposed P-EDA are calibrated using a design of experiments approach. Simulation results and comparisons with some well-performing algorithms demonstrate the effectiveness of the P-EDA for solving BFSP. [ABSTRACT FROM AUTHOR]

The permutation flow-shop scheduling problem (PFSP) is a typical combinational and non-deterministic polynomial-hard problem, with discrete solution space. In this paper, a novel bacterial foraging optimisation algorithm (BFO) has been proposed to solve the PFSP. Difficulties such as slow convergent speeds and entrapment in the local optimum were incurred by the original BFO algorithm in solving a high-dimensional combinatorial optimisation problem. In order to deal with these difficulties, a differential evolution operator and a chaotic search operator were each introduced into the original BFO algorithm to enhance the activity levels of the individual bacterium and to extend the local searching space. Theoretical analysis showed that the improved algorithm obtained more motility in chemotaxis and could converge to the global optimum with a probability of 1. Simulation results and comparisons to both continuous and combinatorial benchmark problems were used to demonstrate the effectiveness of this novel optimisation algorithm. [ABSTRACT FROM AUTHOR]