Hybrid Monte Carlo tree search based multi-objective scheduling

Abstract As markets demand targeted products for highly differentiated use cases, the number of variants in production increases, whilst volume per variant decreases. Different product result differences work content on workstation level which cause takt time losses and a poor utilization. In this context, matrix-structured systems with neither temporal nor spacial linkage emerged to reduce effects different entire system. However, require far more complex control. To that end, paper presents scheduling approach. The proposed system considers variable process sequences their allocation workstations order optimize objectives. This contribution Monte Carlo tree search based optimizer combined local as post derive schedules short span enabling reactive scheduling. application scheduler benchmark problem an industrial demonstrates quality results illustrates how reassigns dynamically.