基于MAS协同的动态资源优化调度策略研究  

Research on resource allocation algorithm based on MAS cooperative bidding game

作　　者：史德嘉[1] 王璞[2] 

机构地区：[1]湖南商学院计算机与电子工程学院,长沙410205 [2]湘潭大学信息学院,湖南湘潭411000

出　　处：《计算机应用研究》2009年第11期4063-4065,共3页Application Research of Computers

基　　金：湖南省自然科学基金重点资助项目(06JJ2033)

摘　　要：目前,围绕着网格中的资源调度方法,虽然已提出了各种调度算法,但是都不能很好地适应网格环境下的自治性、动态性、分布性和异构性等特征。针对动态计算网格资源调度问题,基于多智能体协同技术和市场博弈机制,对计算网格资源分配技术进行了深入研究,提出了能够反映供求关系的基于计算经济机制的网格资源调度模型,建立了消费者的效用函数,给出了资源调度的动态博弈算法。仿真实验说明资源利用率比传统算法好,整个资源的供需合理、负载均衡。Currently, much research can be found about grid scheduling and proposed some algorithms on it. However, since grid resources are autonomic, distributed and their status change over time, those scheduling algorithms do not fit for the cases well. With MAS coordinated technology and market bidding game rules, introduced a grid resource allocation model based on market economy, which could show the relation between supply and demand. Gave the utility function of consumer. The resuits of emulation test show that the approach significantly improves resource utilization, which make the allocation of the whole network resource tend to be more reasonable.

关 键 词：多AGENT系统 资源调度 计算经济 动态定价 效用函数 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]