Application of pueromone to dynamic real-time scheduling for semiconductor wafer fab

New approaches for die dynamic real-time scheduling for semiconductor wafer fab are required urgently for introducing better response to uncertain semiconductor manufacturing environment. Imitating the collective activities of ant colonies, a new approach to constructing pheromone-based multi-agent-system for dynamic real-time scheduling for semiconductor wafer fab is proposed, and the relevant algorithm, pheromone-based dynamic real-time scheduling algorithm (PBDR), is presented. The MIMAC test bed dataset minifab is used to compare PBDR with FIFO, SRPT and CR. It is shown that PRDR is prior to FIFO, SRPT and CR with better performance of throughput rate, cycle time and on-time delivery rate, especially for on-time delivery rate performance.