Efficient Algorithms for Just-In-Time Scheduling on a Batch Processing Machine

Just-in-time scheduling problem on a single batch processing machine is investigated in this research. Batch processing machines can process more than one job simultaneously and are widely used in semi-conductor industries. Due to the requirements of just-in-time strategy, minimization of total earliness and tardiness penalties is considered as the criterion. It is an acceptable criterion for both manufacturer and customer. Since the research problem is proven to be NP-hard, the main objective of this research is to develop metaheuristic algorithms for finding efficient upper bounds for industry sized instances. Two algorithms are proposed for the research problem: a Hybrid Genetic Algorithm (HGA), and a Greedy Randomized Adaptive Search Procedure (GRASP). A dynamic programming approach is developed to sequence the batches in these algorithms. The computational results, based on available test problems in the literature, demonstrate that the proposed algorithms are effective, especially for large sized instances. The average percentage error of HGA is 6.82% and the corresponding value for GRASP is 11.64%. The results also show that the performance of the proposed algorithms is more considerable when the job sizes are small.