通信学报 ›› 2016, Vol. 37 ›› Issue (2): 32-38.doi: 10.11959/j.issn.1000-436x.2016027

• 学术论文 • 上一篇    下一篇

分布式环境中基于市场机制的资源自适应调价策略

丁长松1,2,王志英1,胡志刚3   

  1. 1 国防科技大学计算机学院,湖南 长沙 410073
    2 湖南中医药大学管理与信息工程学院,湖南 长沙 410208
    3 中南大学软件学院,湖南 长沙 410083
  • 出版日期:2016-02-26 发布日期:2016-02-26
  • 基金资助:
    国家自然科学基金资助项目;湖南省科技厅基金资助项目;湖南省科技厅基金资助项目;湖南省教育厅优秀青年基金资助项目

Self-adaptive price adjustment strategy based on market mechanism in distributed environment

Chang-song DING1,2,Zhi-ying WANG1,Zhi-gang HU3   

  1. 1 College of Computer, National University of Defense Technology, Changsha 410073,China
    2 School of Management and Information Engineering, H nan University of Chinese Medicine, Changsha 410208,China
    3 School of Software, Central South University, Changsha 410083,China
  • Online:2016-02-26 Published:2016-02-26
  • Supported by:
    The National Natural Science Foundation of China;The Science and Technology Projects Fund of Hunan Province;The Science and Technology Projects Fund of Hunan Province;Scientific Research Fund for Outstanding Young Teachers of Hunan Provincial Education Department

摘要:

针对分布式环境中资源定价面临的资源使用率、价格、收益三者之间的冲突问题,提出一种基于市场机制的资源自适应调价策略。该策略在保障资源提供者收益前提下,通过资源价格自适应动态调整来平衡资源节点上的任务分配与资源提供者收益之间的冲突。理论分析证明了调价策略的有效性,并在此基础上设计了自适应调价算法。仿真实验采用真实分布式系统中资源节点信息作为实验节点的性能参数,在大规模网格任务中检验了自适应调价策略的性能表现。实验结果表明,基于市场机制的“自适应调价策略”在保障资源收益、均衡资源利用率的性能表现方面显著优于传统的定价策略。

关键词: 分布式计算, 市场机制, 自适应, 调价策略

Abstract:

To solve the resource pricing problem of the collision among resource utilization, price and benefits in distributed computing environments, a self-adaptive pricing strategy of resource services based on market mechanism was proposed. On the premise of the local resource benefits, this adaptive pricing strategy guaranteed the resource to self-adapt the price dynamically so as to balance the collision between the assigned tasks on the resource node and the benefits of the resource provider. The theoretical ana is proved the effectiveness of the pricing strategy, and the algorithm of the pricing strategy was designed. Resources information in the real distributed systems was used as the performance parameters of experimental node in the sim lation experiments, and the performance of the adaptive pricing strategy was tested in a large-scale grid mission. Experimental results show that, compared with the traditional pricing strategies, the adaptive pricing strategy based on market mechanism has vastly superior performance on the resource benefits and the balance of resource utilization.

Key words: distributed computing, market mechanism, self-adaptive, price adjustment strategy

No Suggested Reading articles found!