Golden age:on multi-source software update propagation in pervasive networking environments

作     者：LI WenZhong FU XiaoMing CHAN Edward LU SangLu CHEN DaoXu 

作者机构：State Key Laboratory for Novel Software TechnologyNanjing University Institute of Computer ScienceUniversity of Goettingen Department of Computer ScienceCity University of Hong Kong 

出 版 物：《Science China(Information Sciences)》 (中国科学:信息科学(英文版))

年 卷 期：2013年第56卷第8期

页      面：104-118页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 08[工学] 081201[工学-计算机系统结构] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by National Basic Research Program of China (973 Program) (Grant No.2009CB320705) National Natural Science Foundation of China (Grant Nos. 61003213,61073028,61021062) funding from Alexander von Humboldt Foundation 

主　　题：pervasive computing software update propagation mobile ad hoc networks 

摘      要：With the development of Internet technology,a large portion of computer softwares appear to run in a network-oriented,distributed-deployed,and self-evolving *** emerging wireless communication technologies broaden the usage of software in mobile platforms,enabling the pervasive computing paradigm,where people can access information/service anytime and anywhere with portable *** the pervasive networking environment where mobile devices operate on the ad hoc mode and communicate with each other opportunistically without wireless infrastructures,distributing the evolving software updates to a set of mobile terminals is a challenging *** this paper,we address the problem of distributing multiple software updates in pervasive networks with storage and bandwidth constraints,and propose age-based solutions to tackle this *** basic idea is to introduce different age-based priority mechanisms for propagation decision making in order to resolve the contention of wireless bandwidth and storage *** investigate a number of update propagation strategies including random spread,youngest age,and golden *** models are derived to analyse the performance of the proposed *** is shown that the golden age strategy has the burst effect,which could be used to enhance the efficiency of software update *** principles for choosing golden age values are proposed aiming to optimize different utility *** simulations under various network parameters show that the golden age strategy outperforms other strategies for multi-source software updates propagation.