A hybrid particle swarm optimization algorithm for parallel batch processing machines scheduling

The paper studies the scheduling problem of minimizing maximum lateness on parallel identical batch processing machines with dynamic job arrivals and incompatible job families. Each machine can process several jobs simultaneously as a batch and each job is characterized by its release time, processing time, due date and job family. In view of the strongly NP-hard of this problem, heuristics are first proposed to solve the problem in a modest amount of computer time. In general, the quality of the solutions provided by heuristics degrades with the increase of the problem's scale. Combined the global search ability of particle swarm optimization (PSO), we proposed a hybrid PSO to improve the quality of solutions further. Computational results show that the hybrid heuristic combines the advantages of heuristic and genetic algorithm effectively and can provide very good solutions to some laruge problems in a reasonable amount of computer time.