信息中心网络中的内置缓存技术研究  

Survey of In-Network Caching Techniques in Information-Centric Networks

作　　者：张国强[1,2] 李杨[3] 林涛[3] 唐晖[3] 

机构地区：[1]南京师范大学计算机科学与技术学院,江苏南京210046 [2]中国科学院计算技术研究所,北京100190 [3]中国科学院声学研究所高性能网络实验室,北京100190

出　　处：《软件学报》2014年第1期154-175,共22页Journal of Software

基　　金：国家自然科学基金(61100178,61174152,61303243,61202419);国家高技术研究发展计划(863)(2013AA013503)

摘　　要：互联网的应用方式正从以面向主机的点对点通信为主转向以海量内容获取为主.为适应这一转变,研究界提出了多种以信息/内容为中心的新型网络架构.这类网络架构中最重要的特征之一是利用网络内置缓存提高接收者驱动的内容获取的传输效率和网络资源的利用率.与传统的Web缓存、CDN缓存等相比,ICN缓存系统呈现了缓存透明化、泛在化和细粒度化等新特征,对缓存系统的建模、行为理解和优化方法都提出了新的挑战.在介绍了ICN缓存系统的新特征及带来的挑战后,首先从多方面着重阐述和比较了缓存网络的优化方法,之后对缓存网络系统的理论模型研究现状加以阐述,然后分析了仍待解决的关键问题和未来的研究方向.lnternet usage has dramatically transformed from host-centric end-to-end communication to content retrieval. In order to adapt to this change, several new information/content centric networking （ICN） architectures have been proposed. One common and important feature of these architectures is to leverage built-in network caches to improve the transmission efficiency of receiver-driven content retrieval and network resource utilization. Compared with traditional Web cache and CDN cache systems, ICN cache takes on several new characteristics： Transparency, ubiquity, and fine granularity, which put new challenges on the modeling, understanding and optimization of the networked cache system. In this paper, new features of ICN as well as their ensuing challenges are introduced, mechanisms to optimize the performance of cache network are analyzed and compared from various angles, and analytical models for the cache system are also presented. The study concludes with a discussion on some key issues and future research directions.

关 键 词：信息中心网络 内容中心网络 缓存 缓存协同 缓存网络 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]