Modified Coral Reef Optimization Methods for Job Shop Scheduling Problems

Abstract

The job shop scheduling problem (JSSP) is a fundamental operational research topic with numerous applications in the real world. Since the JSSP is an NP-hard (nondeterministic polynomial time) problem, approximation approaches are frequently used to rectify it. This study proposes a novel biologically-inspired metaheuristic method named Coral Reef Optimization in conjunction with two local search techniques, Simulated Annealing (SA) and Variable Neighborhood Search (VNS), with significant performance and finding-solutions speed enhancement. The two-hybrid algorithms’ performance is evaluated by solving JSSP of various sizes. The findings demonstrate that local search strategies significantly enhance the search efficiency of the two hybrid algorithms compared to the original algorithm. Furthermore, the comparison results with two other metaheuristic algorithms that also use the local search feature and five state-of-the-art algorithms found in the literature reveal the superior search capability of the two proposed hybrid algorithms.

Mushroom Picking Framework with Cache Memories for Solving Job Shop Scheduling Problem

“…Table III contains Q-Learning Algorithm (QL, [33]) and a hybrid EOSMA algorithm [34] that mixes the strategies of Equilibrium Optimizer (EO) and Slime Mould Algorithm (SMA). Table IV shows results for the Coral Reef Optimization (CROLS, [35]). The average errors for CROLS, QL and EOSMA algorithms have been calculated based on average results given in the original papers.…”

“…The average errors for CROLS, QL and EOSMA algorithms have been calculated based on average results given in the original papers. In the case of the Coral Reef Optimization results reported in [35] were given for only chosen instances of the problem. The Coral Reef algorithm was run for three different reef sizes.…”

“…The Coral Reef algorithm was run for three different reef sizes. For each task in the table, the best Coral Reef Optimization result was chosen from among the three available results in [35]. In the case of QL0 and QL1 [33] running times of algorithms were not given.…”