信任驱动的云联盟博弈算法  

Trust-driven cloud coalition game algorithm

作　　者：段昌敏[1] 沈济南[1,2] 周慧华[1] Duan Changmin Shen Jinan Zhou Huihua(School of Information ＆ Engineering, Hubei University for Nationalities, Enshi Hubei 445000, China School of Computer Science ＆ Techlwlogy, Huazhong University of Science ＆ Technology, Wuhan 430074, China)

机构地区：[1]湖北民族学院信息工程学院,湖北恩施445000 [2]华中科技大学计算机科学与技术学院,武汉430074

出　　处：《计算机应用研究》2017年第9期2577-2581,2598,共6页Application Research of Computers

基　　金：国家自然科学基金资助项目(61662022);湖北省自然科学基金资助项目(2015CFC783;2016CFB371)

摘　　要：为了解决云联盟中云资源提供者间的信任问题,提出一种基于信任机制的云联盟算法。算法将多个云资源提供者以合作形式完成用户任务的问题形式化为联盟博弈模型,在建立联盟时兼顾考虑成员间的信任关系及成员收益,使得具有更高信任度的资源提供者能够建立联盟以降低任务执行代价,并确保参与联盟的个体成员收益最大化;同时,证明了该算法求解的联盟结构是稳定的,并且满足Pareto最优性质。实验结果验证了算法的有效性和可行性。In order to solve the problem of trust among cloud resource providers in cloud coalition, this paper proposed a cloud coalition formation algorithm based on trust mechanism. The algorithm modeled the cooperation among multiple cloud resource providers to execute user＇ s tasks as a coalitional game model. When establishing a coalition, takeing into account the trust relationship among coalition＇ s members and their profit, the algorithm made the cloud ressource providers with higher trust degree establish coalition to reduce the execution cost and guarantee maximizing the member＇ s profit. At the same time, this pa- per proved that the coalition structure produced by the proposed algorithm was stable, and satisfied the Pareto optimality. The experimental results verify the feasibility and effectiveness of the algorithm.

关 键 词：云计算 联盟博弈 信任关系 PARETO最优 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]