Online Supervised Learning Approach for Machine Scheduling

Bartosz Sądel,

Bartłomiej Śnieżyński


Due to rapid growth of computational power and demand for faster and more optimal solution in today's manufacturing, machine learning has lately caught a lot of attention. Thanks to it's ability to adapt to changing conditions in dynamic environments it is perfect choice for processes where rules cannot be explicitly given. In this paper proposes on-line supervised learning approach for optimal scheduling in manufacturing. Although supervised learning is generally not recommended for dynamic problems we try to defeat this conviction and prove it's viable option for this class of problems. Implemented in multi-agent system algorithm is tested against multi-stage, multi-product ow-shop problem. More specically we start from dening considered problem. Next we move to presentation of proposed solution. Later on we show results from conducted experiments and compare our approach to centralized reinforcement learning to measure algorithm performance.

Słowa kluczowe: supervised learning, reinforcement learning, scheduling, multi-agent system

[1] Sendil Kumar C., Panneerselvam R., Literature review of jit-kanban system. The International Journal of Advanced Manufacturing Technology, 2007, 32 (3), pp. 393408.

[2] Olhager J., Östlund B., An integrated push-pull manufacturing strategy. European Journal of Operational Research, 1990, 45 (2), pp. 135142.

[3] Ouelhadj, D., Petrovic, S., A survey of dynamic scheduling in manufacturing systems. Journal of Scheduling, 2008, 12 (4), pp. 417.

[4] Qu S., Chu T., Wang J., Leckie J.O., Jian W., A centralized reinforcement learning approach for proactive scheduling in manufacturing. In: ETFA, IEEE, 2015, pp. 18.

[5] ‘nie»y«ski B., Agent strategy generation by rule induction. Computing and Informatics, 2013, 32 (5).

[6] ‘nie»y«ski B., A strategy learning model for autonomous agents based on classication. International Journal of Applied Mathematics and Computer Science, 2015, 35 (3), pp. 471482.

[7] Selen W.J., Hott D.D., A mixed-integer goal-programming formulation of the standard ow-shop scheduling problem. Journal of the Operational Research Society, 1986, pp. 11211128.

[8] Reeves C.R., A genetic algorithm for owshop sequencing. Computers & operations research, 1995, 22 (1), pp. 513.

[9] Beke T., Multi-agent reinforcement learning in a exible job shop environment: the vcst case. Master's thesis, Gent Universiteit, Gent, Belgium 2013.

[10] Ingimundardottir H., Runarsson T.P., Supervised learning linear priority dispatch rules for job-shop scheduling. In: Learning and Intelligent Optimization: 5th International Conference. Springer 2011 pp. 263277.

[11] Gersmann K., Hammer B., Improving iterative repair strategies for scheduling with the {SVM}. Neurocomputing, 2005, 63, pp. 271  292.

Czasopismo ukazuje się w sposób ciągły on-line.
Pierwotną formą czasopisma jest wersja elektroniczna.

Wersja papierowa czasopisma dostępna na