基于非完全信息博弈的云资源分配模型  

An Uncompleted Information Game Based Resources Allocation Model for Cloud Computing

作　　者：苑迎[1,2] 王翠荣[2] 王聪[2] 任婷婷[2] 刘冰玉[2] 

机构地区：[1]东北大学信息科学与工程学院,沈阳110819 [2]东北大学秦皇岛分校,河北秦皇岛066004

出　　处：《计算机研究与发展》2016年第6期1342-1351,共10页Journal of Computer Research and Development

基　　金：国家自然科学基金项目(61300195;61402094);河北省自然科学基金项目(F2014501078;F2016501079);辽宁省教育厅科学研究一般项目(L2013099);河北省科技计划项目(15210146);秦皇岛市科技计划项目(201401A028);东北大学秦皇岛分校校内基金项目(XNB201607)~~

摘　　要：针对云环境下相互竞争的多租赁市场运营模式,以提高资源供求双方利益及资源能效为目标,提出了一种基于非完全信息博弈的云资源分配模型.首先利用隐Markov理论根据服务提供商(service provider,SP)的历史资源需求情况预测其当前出价,以预测值为基础构建动态博弈定价模型,激励服务提供商选择符合整体利益的最优购买出价策略,从而实现利益最大化;然后设计了支持多服务提供商、多种资源同时分配,以分类资源单位价格进行分配的资源分配模型,保证了基础设施提供商(infrastructure provider,INP)的收益最优.仿真实验表明:在博弈定价模型中,预测价格与实际交易价格相近且交易价格低于实际估值,能够保障服务提供商的利益;基于不同种类资源单价的分配模型能够增加基础设施提供商的收益.Considering the competing characteristics under multi-tenant environment in cloud computing and aiming to improve the profit of both the resource supply and demand sides,an uncompleted information game based cloud resource allocation model is proposed.Firstly,a hidden Markov model（HMM）is introduced to predict the current bid of service providers based on the historical resource demand.Then a game model for dynamical pricing is established base on the predicted bid value.It can motivate service providers to choose the optimal bidding strategy in accordance with overall interests and so as to achieve maximum benefits.Finally,a resource allocation model on the basis of unit prices of different types of resources is put forward to guarantee optimal gains for infrastructure provider（INP）.The allocation model can support synchronous allocation for both multi service providers and various resources.Simulation results show that,in the pricing game model,the predicted price is close to the actual transaction price which is lower than the actual valuation,so it can guarantee the profit of service providers;the resource allocation model can simultaneously increase infrastructure provider＇s revenue.

关 键 词：云计算 虚拟化 资源分配 非完全信息博弈 隐马尔可夫预测 

分 类 号：TP393.02[自动化与计算机技术—计算机应用技术]