A Q-Learning Rescheduling Approach to the Flexible Job Shop Problem Combining Energy and Productivity Objectives

The flexible job shop problem (FJSP) has been studied in recent decades due to its dynamic and uncertain nature. Responding a system’s perturbation an intelligent way with minimum energy consumption variation is important matter. Fortunately, thanks the development of artificial intelligence machine learning, lot researchers are using these new techniques solve rescheduling shop. Reinforcement which popular approach intelligence, often used rescheduling. This article presents Q-learning combining productivity objectives context failure. First, genetic algorithm was adopted generate initial predictive schedule, then strategies were developed handle failures. As system should be capable reacting quickly unexpected events, multi-objective proposed trained select optimal methods that minimize makespan at same time. conducted on benchmark instances evaluate performance.