A Novel Parallel Simulated Annealing Methodology to Solve the No-Wait Flow Shop Scheduling Problem with Earliness and Tardiness Objectives

Abstract

In this paper, the no-wait flow shop problem with earliness and tardiness objectives is considered. The problem is proven to be NP-hard. Recent no-wait flow shop problem studies focused on familiar objectives, such as makespan, total flow time, and total completion time. However, the problem has limited studies with solution approaches covering the concomitant use of earliness and tardiness objectives. A novel methodology for the parallel simulated annealing algorithm is proposed to solve this problem in order to overcome the runtime drawback of classical simulated annealing and enhance its robustness. The well-known flow shop problem datasets in the literature are utilized for benchmarking the proposed algorithm, along with the classical simulated annealing, variants of tabu search, and particle swarm optimization algorithms. Statistical analyses were performed to compare the runtime and robustness of the algorithms. The results revealed the enhancement of the classical simulated annealing algorithm in terms of time consumption and solution robustness via parallelization. It is also concluded that the proposed algorithm could outperform the benchmark metaheuristics even when run in parallel. The proposed algorithm has a generic structure that can be easily adapted to many combinatorial optimization problems.

A hybridization of evolution strategies with iterated greedy algorithm for no-wait flow shop scheduling problems

“…Additionally, this author introduced two heuristics for adjusting speed tailored to the specific problem, aiming to improve the quality of the non-dominated solutions acquired. Karacan et al 46 thoroughly examined the NWFSSP with the primary aim of optimizing both earliness (E) and tardiness (TT) objectives. To tackle this intricate challenge, he introduced a novel perspective on enhancing the parallel simulated annealing algorithm.…”