Dynamic software allocation algorithm for saving power in pervasive computing  

普适计算中节约电量的动态软件部署算法(英文)

作　　者：韩松乔[1] 张申生[1] 张勇[1] 曹健[1] 

机构地区：[1]上海交通大学计算机科学与工程系,上海200240

出　　处：《Journal of Southeast University(English Edition)》2007年第2期216-220,共5页东南大学学报（英文版）

基　　金：The National Natural Science Foundation of China(No60503041);the Science and Technology Commission of ShanghaiInternational Cooperation Project (No05SN07114)

摘　　要：A novel dynamic software allocation algorithm suitable for pervasive computing environments is proposed to minimize power consumption of mobile devices. Considering the power cost incurred by the computation, communication and migration of software components, a power consumption model of component assignments between a mobile device and a server is set up. Also, the mobility of components and the mobility relationships between components are taken into account in software allocation. By using network flow theory, the optimization problem of power conservation is transformed into the optimal bipartition problem of a flow network which can be partitioned by the max-flow rain-cut algorithm. Simulation results show that the proposed algorithm can save si^nificantlv more energy than existing algorithms.为了节约移动设备的电量消耗,提出了一种适合于普适计算环境的动态软件部署算法.综合考虑了软件组件的计算、通信和移动所消耗的费用,建立了一个在移动设备和服务器间组件部署的电量消耗模型.在软件部署中同时也考虑了组件的移动性和组件间的移动关系.利用网络流理论,将节约电量的最优化问题转化为一个流网络的最优分割问题,而后者可采用最大流最小切割算法实现最优切分.实验结果表明提出的算法比现有算法能够节约更多的电量.

关 键 词：power aware software allocation code mobility graph theory pervasive computing 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]