Dynamic Monte-Carlo Tree Search Algorithm for Multi-Objective Flexible Job-shop Scheduling Problem

Lu, Chunliang; Chiu, Shih-Yuan; Wu, Jiinpo; Chao, Li-Lian

doi:10.18576/amis/100431

Cited by 3 publications

(3 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Alternatively, the scheduling problem can be modelled as N + 1 game where n production orders try to optimize their cycle time and the production system as single player thrives for high utilization [15]. Lately, Monte Carlo tree search (MCTS) has gained a lot of interest as means to solve complex problems in gaming [16] but also in the domain of scheduling [17][18][19]. Monte Carlo tree search as an algorithm is an iterative anytime approach using search trees to represent Markov decision problems.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Especially hybrid MO-MCTS approaches have demonstrated their abilities by solving the Pareto Kacem benchmark problem [19,22,23]. However, the Kacem benchmark problem does not cover important restrictions (transport, setup) and does not offer process flexibility.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Accounting for the fact that only minor improvement is to be expected by a neighborhood search, a pre-selection of the solutions to execute local search on is advisable. In literature [19,22,23] local search is executed on rollout states. To improve the efficiency of the entire optimizer, the following strategies have been developed:…”

Section: Interaction Of Local Search and Base Optimizermentioning

confidence: 99%

See 2 more Smart Citations

Hybrid Monte Carlo tree search based multi-objective scheduling

Hofmann

Liu

May

et al. 2022

Prod. Eng. Res. Devel.

View full text Add to dashboard Cite

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

show abstract