Scheduling unrelated parallel machines to minimize total weighted tardiness

This paper addresses the batch scheduling problem of unrelated parallel machines attempting to minimize the total weighted tardiness. Identical or similar jobs are typically processed in batches to decrease setup and/or processing times. Local dispatching rules such as the earliest weighted due date, the shortest weighted processing time, and the earliest weighted due date with a process utilization spread are tailored to the batch scheduling requirements. Based on the features of batch scheduling, a two-level batch scheduling framework is suggested. Existing heuristics, which show excellent performance in terms of total weighted tardiness for the single machine scheduling, such as the modified earliest due date rule and the modified cost over time rule, are extended for the problem. The simulated annealing algorithm as a meta-heuristic is also presented to obtain near optimal solutions. The proposed heuristics are compared through computational experiments with data from the dicing process of a compound semiconductor manufacturing facility