基于平均强化学习的订单生产方式企业订单接受策略

doi:10.3724/SP.J.1087.2013.00976

计算机应用 ›› 2013, Vol. 33 ›› Issue (04): 976-979.DOI: 10.3724/SP.J.1087.2013.00976

基于平均强化学习的订单生产方式企业订单接受策略

郝鹃¹,²,余建军²,周文慧²

1. 广东外语外贸大学思科信息学院，广州 510006
2. 华南理工大学工商管理学院，广州 510640

收稿日期:2012-09-12 修回日期:2012-10-28 出版日期:2013-04-01 发布日期:2013-04-23
通讯作者: 余建军
作者简介:郝鹃(1973-)，女，湖北武汉人，博士研究生，主要研究方向：运营管理、商务智能；余建军(1978-)，男，江西抚州人，副教授，主要研究方向：工业工程、运营管理；周文慧(1976-)，男，湖南郴州人，副教授，主要研究方向：工业工程、服务管理。
基金资助:
国家自然科学基金资助项目(71071059);教育部人文社会科学项目(08JC630028);教育部博士点基金资助项目(20100172120040)

Order acceptance policy in Make-to-Order manufacturing based on average-reward reinforcement learning

HAO Juan¹,²,³,YU Jianjun²,³,ZHOU Wenhui²,³

1. Cisco School of Informatics, Guangdong University of Foreign Studies, Guangzhou Guangdong 510006, China
2. School of Business Administration, South China University of Technology, Guangzhou Guangdong 510640, China
3. School of Business Administration, South China University of Technology, Guangzhou Guangdong 510640, China

Received:2012-09-12 Revised:2012-10-28 Online:2013-04-01 Published:2013-04-23
Contact: YU Jianjun

摘要/Abstract

摘要： 从收益管理思想出发，采用平均强化学习算法研究不确定环境下订单生产(MTO)方式企业的订单接受问题。以最大化平均期望收益为优化目标，采用多级价格机制，把订单类型、价格和提前期的不同组合作为系统状态划分标准，结合平均强化学习原理，提出了具有学习能力的订单接受算法(RLOA)。仿真结果表明，RLOA算法具有学习和选择性接受订单的能力，与其他订单接受规则相比，在平均收益、订单类型接受状况和适应性等方面都有较好表现。

关键词: 订单接受, 平均强化学习, 订单生产方式企业, 收益管理

Abstract: From the perspective of revenue management, a new approach for order acceptance under uncertainty in Make-to-Oder (MTO) manufacturing using average-reward reinforcement learning was proposed. In order to maximize the average expected revenue, the proposed approach took order types and different combinations of price and leadtime as criteria for the classification of the system states based on multi-level pricing mechanism. The simulation results show that the proposed algorithm has learning and selective ability to accept the order. Comparisons made with other order acceptance policies show the effectiveness of the proposed algorithm in average revenue, accepted order types, and adaptability.

Key words: order acceptance, average-reward reinforcement learning, Make-to-Order (MTO) manufacturing, revenue management

郝鹃余建军周文慧. 基于平均强化学习的订单生产方式企业订单接受策略[J]. 计算机应用, 2013, 33(04): 976-979.

HAO Juan YU Jianjun ZHOU Wenhui. Order acceptance policy in Make-to-Order manufacturing based on average-reward reinforcement learning[J]. Journal of Computer Applications, 2013, 33(04): 976-979.

参考文献

［1］HENDRY L, LAND M, STEVENSON M, et al. Investigating implementation issues for workload control (WLC)：a comparative case study analysis ［J］. International Journal of Production Economics,2008，112(1):452-469.

［2］STEVENSON M, HENDRY L C. Aggregate load-oriented workload control: a review and a re-classification of a key approach ［J］. International Journal of Production Economics, 2006, 104(2):676-693.

［3］GUERREROH H, KERN G M. How to more effectively accept and refuse orders ［J］. Production and Inventory Management, 1988, 29(3):59-63.

［4］SLOTNICK S A. Order acceptance and scheduling: a taxonomy and review ［J］. European Journal of Operational Research, 2011, 212(1):1-11.

［5］YANG B, GEUNES J. Heuristic approaches for solving single resource scheduling problems with job-selection flexibility ［R］. Gainesville FL,USA: University of Florida, Department of Industrial and Systems Engineering, 2004.

［6］CHARNSIRISAKSKUL K, GRIFFIN P M, KESKINOCAK P. Pricing and scheduling with leadtime flexibility ［J］. European Journal of Operational Research, 2006, 171(1):153-69.

［7］张欣,马士华.基于有限生产能力和产出缓存的订单接受策略［J］.工业工程与管理,2008,13(2):34-38.

［8］HERBOTS J, HERROELEN W, LEUS R. Dynamic order acceptance and capacity planning on a single bottleneck resource ［J］. Naval Research Logistics, 2007，54(8):874-889.

［9］范丽繁,陈旭.基于收益管理的MTO企业订单定价和接受策略［J］. 系统工程，2011, 29(2):87-93.

［10］SNOEK M. Neuro-genetic order acceptance in a job shop setting ［C］// Proceedings of the 7th International Conference on Neural Information Processing. Seoul: [s.n.], 2000:815-819.

［11］HING M, van HARTEN M. Reinforcement learning versus heuristics for order acceptance on a single resource ［J］. Journal of Heuristics, 2007, 13(2):167-187.

［12］LI X P, WANG J, SAWHENY R. Reinforcement learning for joint pricing,lead-time and scheduling decisions in make-to-order systems ［J］. European Journal of Operational Research, 2012, 221(1): 99-109.

［13］CHERAGHI S H, DADASHZADEN M, VENKITACHALAM P. Revenue management in manufacturing: a research landscape ［J］. Journal of Business & Economics Research, 2010, 8(2):63-72.

［14］RUSSELL S, NORVIG P. 人工智能——一种现代方法［M］. 2版. 姜哲,金奕江，张敏，等译.北京：人民邮电出版社,2010.

［15］MITCHELL T M.机器学习［M］. 曾华军,张银奎，译.北京：机械工业出版社,2009,

［16］周晶,杨慧.收益管理方法与应用［M］.北京:科学出版社,2009.

［17］RREDONDO F A, MARTINEZ E. Learning and adaptation of a policy for dynamic order acceptance in make-to-order manufacturing ［J］. Computer & Industrial Engineering, 2010， 58(1):70-83.

基于平均强化学习的订单生产方式企业订单接受策略

Order acceptance policy in Make-to-Order manufacturing based on average-reward reinforcement learning

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics