A reinforcement learning based approach for multi-projects scheduling in cloud manufacturing
Shengkai Chen,
Shuiliang Fang and
Renzhong Tang
International Journal of Production Research, 2019, vol. 57, issue 10, 3080-3098
Abstract:
This paper discussed the multi-projects scheduling problem in Cloud Manufacturing system, where each of the projects is a set of interrelated tasks, and these projects need to be scheduled timely and carefully. However, scheduling massive projects can be challenging due to the uneven distribution of the services and the uncertain arrival of projects. Therefore, we (1) established a dual-objectives optimisation model to minimise both the total makespan and the logistical distance; (2) proposed a Reinforcement Learning based Assigning Policy (RLAP) approach to obtain non-dominated solution set; (3) designed a dynamic state representing an algorithm for agents to determine their decision environment when using RLAP. Experiment results show that RLAP can adjust the distribution of service load according to the nearby tasks, and the schedule quality is improved by $ 32.1\% $ 32.1% and $ 5.7\% $ 5.7% compared with NSGA-II and Q-learning, respectively. Besides, the RLAP method has the ability to schedule stochastically arriving projects.
Date: 2019
References: Add references at CitEc
Citations: View citations in EconPapers (1)
Downloads: (external link)
http://hdl.handle.net/10.1080/00207543.2018.1535205 (text/html)
Access to full text is restricted to subscribers.
Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
HTML/Text
Persistent link: https://EconPapers.repec.org/RePEc:taf:tprsxx:v:57:y:2019:i:10:p:3080-3098
Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/TPRS20
DOI: 10.1080/00207543.2018.1535205
Access Statistics for this article
International Journal of Production Research is currently edited by Professor A. Dolgui
More articles in International Journal of Production Research from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().