计算机科学与探索 ›› 2022, Vol. 16 ›› Issue (1): 153-162.DOI: 10.3778/j.issn.1673-9418.2009086

• 人工智能 • 上一篇    下一篇

基于Stackelberg博弈的边缘云资源定价机制研究

刘荆欣1, 王妍1,+(), 韩笑1, 夏长清2,3,4, 宋宝燕1   

  1. 1.辽宁大学 信息学院,沈阳 110036
    2.中国科学院 沈阳自动化研究所 机器人学国家重点实验室,沈阳 110016
    3.中国科学院 沈阳自动化研究所 网络化控制系统重点实验室,沈阳 110016
    4.中国科学院 机器人与智能制造创新研究院,沈阳 110169
  • 收稿日期:2020-08-07 修回日期:2020-10-13 出版日期:2022-01-01 发布日期:2020-10-23
  • 通讯作者: + E-mail: wang_yan@lnu.edu.cn
  • 作者简介:刘荆欣(1996—),女,山东招远人,硕士研究生,CCF学生会员,主要研究方向为边缘计算资源管理、任务调度等。
    王妍(1978—),女,辽宁抚顺人,博士,教授,硕士生导师,CCF会员,主要研究方向为工业物联网数据处理、任务调度、大数据技术等。
    韩笑(1994—),男,辽宁锦州人,硕士研究生,主要研究方向为边缘计算下的任务调度。
    夏长清(1985—),男,山东威海人,博士,助理研究员,CCF会员,主要研究方向为工业物联网、边缘计算下的任务调度等。
    宋宝燕(1965—),女,辽宁开原人,博士,教授,硕士生导师,CCF高级会员,主要研究方向为数据库理论和技术、大数据管理等。
  • 基金资助:
    国家重点研发计划(2019YFB1406002);国家自然科学基金(61903356);机器人学国家重点实验室开放基金(2019-022);辽宁省自然科学基金计划重点项目(20180520029);辽宁省经济社会发展课题(2019lslktqn-023)

Research on Edge Cloud Resource Pricing Mechanism Based on Stackelberg Game

LIU Jingxin1, WANG Yan1,+(), HAN Xiao1, XIA Changqing2,3,4, SONG Baoyan1   

  1. 1. College of Information, Liaoning University, Shenyang 110036, China
    2. State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China
    3. Key Laboratory of Networked Control System, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China
    4. Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang 110169, China
  • Received:2020-08-07 Revised:2020-10-13 Online:2022-01-01 Published:2020-10-23
  • About author:LIU Jingxin, born in 1996, M.S. candidate, student member of CCF. Her research interests include edge computing resource management, task scheduling, etc.
    WANG Yan, born in 1978, Ph.D., professor, M.S. supervisor, member of CCF. Her research interests include industrial Internet of things data processing, task scheduling, big data technology, etc.
    HAN Xiao, born in 1994, M.S. candidate. His research interest is task scheduling under edge computing.
    XIA Changqing, born in 1985, Ph.D., assistant researcher, member of CCF. His research interests include industrial Internet of things, task scheduling under edge computing, etc.
    SONG Baoyan, born in 1965, Ph.D., professor, M.S. supervisor, senior member of CCF. Her research interests include database theory and techniques, big data management, etc.
  • Supported by:
    National Key Research and Development Program of China(2019YFB1406002);National Natural Science Foundation of China(61903356);Foundation of State Key Laboratory of Robotics(2019-022);Key Project of the Natural Science Foundation of Liaoning Province(20180520029);Economic and Social Development Project of Liaoning Province(2019lslktqn-023)

摘要:

移动边缘计算(MEC)支持终端设备将任务或应用程序卸载到边缘云服务器处理,边缘云服务器处理外来任务会消耗本地资源,为激励边缘云提供资源服务,构建向终端设备收费以奖励边缘云的资源定价机制尤为重要。现有的定价机制依赖中间商的静态定价,费用高且终端任务处理不及时,难以实现边缘云计算资源的有效利用。针对上述问题,提出一种基于Stackelberg博弈的边缘云资源定价机制。首先,针对资源定价时终端设备因资金不足而导致的本地任务搁置问题,提出包含贷款和激励的辅助机制,实现终端设备任务的及时处理;其次,提出影响资源定价的四种价格导向因素,制定了一致性与弹性两种定价方案,提高定价的准确性和效率,并为动态定价做准备;然后,为了使终端设备与边缘云直接进行动态定价,构建基于斯坦克伯格(Stackelberg)博弈的资源定价机制模型,将资源需求与定价问题转化为边缘云收益最大与终端设备支付成本最小问题;最后,通过改进的强化学习SARSA算法得到资源需求及定价的最优策略。实验表明,提出的定价机制在边缘云收益最大化方面优于其他定价算法12%以上,同时弹性定价方案下边缘云的收益优于一致性定价方案24%。

关键词: 移动边缘计算(MEC), 资源定价机制, Stackelberg博弈, 强化学习

Abstract:

Mobile edge computing (MEC) supports terminal devices to offload tasks or applications to edge cloud server for processing. Edge cloud server will consume local resources when processing external tasks, so it is particularly important to build a resource pricing mechanism that charges terminal devices to reward edge cloud. The existing pricing mechanism relies on the static pricing of intermediaries, and high cost and late processing of terminal tasks make it difficult to realize the effective utilization of edge cloud computing resources. Aiming at the above problems, this paper proposes an edge cloud resource pricing mechanism based on Stackelberg game. Firstly, in view of the local task shelving problem of terminal devices due to insufficient funds during resource pricing, an auxiliary mechanism including loans and incentives is proposed to realize the timely processing of terminal devices tasks. Secondly, four price-oriented factors that affect resource pricing are proposed, and two pricing schemes, consistency and elasticity, are formulated to improve the accuracy and efficiency of pricing and prepare for dynamic pricing. Then, in order to make the dynamic pricing between terminal devices and edge cloud directly, a resource pricing mechanism model based on Stackelberg game is built, and the resource demand and pricing problem is transformed into the problem of maximum revenue of edge cloud and minimum payment cost of terminal devices. Finally, through improved reinforcement learning SARSA (state action reward state action) algorithm, the optimal strategy of resource demand and pricing is obtained. Experiments show that the pricing mechanism proposed in this paper is more than 12% better than other pricing algorithms in terms of edge cloud revenue maximization, and the edge cloud revenue under the elasticity pricing scheme is 24% better than that of the consistency pricing scheme.

Key words: mobile edge computing (MEC), resource pricing mechanism, Stackelberg game, reinforcement learning

中图分类号: