针对命名数据网络(named data networking,NDN)中缓存冗余高、资源利用率低的问题,提出基于数据冗余包的协同缓存放置策略(cooperative cache placement strategy based on da-ta redundancy packet,CCPS-DRP)。该策略先对网络进行社区...针对命名数据网络(named data networking,NDN)中缓存冗余高、资源利用率低的问题,提出基于数据冗余包的协同缓存放置策略(cooperative cache placement strategy based on da-ta redundancy packet,CCPS-DRP)。该策略先对网络进行社区划分,再利用复杂网络中节点介数确定关键路由节点,将数据冗余包中的相同数据副本存放于其中,并动态管理冗余数据副本,实现关键节点集中管理与动态冗余清理的协同机制,以减少相同数据内容的重复缓存,使路由节点中的缓存容量得到充分利用,降低网络负载。实验结果表明,无论在均匀分布或高度偏斜分布的场景下,还是在严格资源限制或有较高资源的场景下,CCPS-DRP在缓存命中率和平均请求时延方面的性能均明显优于常见的随处缓存策略、概率缓存策略等,其通过协同缓存与冗余控制显著提升了网络性能。展开更多
Content-Centric Networking is a novel future network architecture that attracts increasing research interests in recent years. In-network caching has been regarded as a prominent feature of Content-Centric Networking ...Content-Centric Networking is a novel future network architecture that attracts increasing research interests in recent years. In-network caching has been regarded as a prominent feature of Content-Centric Networking since it is able to reduce the network traffic, alleviate the server bottleneck and decrease the user access latency. However, the CCN default caching scheme results in a high caching redundancy, causing an urgent need for an efficient caching scheme. To address this issue, we propose a novel implicit cooperative caching scheme to efficiently reduce the caching redundancy and improve the cache resources utilization. The simulation results show that our design achieves a higher hit ratio and a shorter cache hit distance in comparison with the other typical caching schemes.展开更多
缓存是命名数据网络(named data networking,NDN)有别于传统网络最突出的特性之一,NDN中默认所有节点都具有缓存所有经过数据的功能.这种"处处缓存"策略导致网内大量冗余数据的产生,使网内缓存被严重浪费.针对上述问题,首次...缓存是命名数据网络(named data networking,NDN)有别于传统网络最突出的特性之一,NDN中默认所有节点都具有缓存所有经过数据的功能.这种"处处缓存"策略导致网内大量冗余数据的产生,使网内缓存被严重浪费.针对上述问题,首次提出了一种基于节点分类(based on node classification,BNC)的数据存储策略.基于节点位置的不同,将数据返回客户端所经过的节点分为"边缘"类节点与"核心"类节点.当数据经过"核心"类节点时,通过权衡该类节点的位置与数据在不同节点的流行度分布,将数据存储在对其他节点最有利的节点中;当数据经过"边缘"类节点时,通过该数据流行度来选择最有利于客户端的位置.仿真结果表明,提出的策略将有效提高数据命中率,减少数据请求时延和距离.展开更多
文摘针对命名数据网络(named data networking,NDN)中缓存冗余高、资源利用率低的问题,提出基于数据冗余包的协同缓存放置策略(cooperative cache placement strategy based on da-ta redundancy packet,CCPS-DRP)。该策略先对网络进行社区划分,再利用复杂网络中节点介数确定关键路由节点,将数据冗余包中的相同数据副本存放于其中,并动态管理冗余数据副本,实现关键节点集中管理与动态冗余清理的协同机制,以减少相同数据内容的重复缓存,使路由节点中的缓存容量得到充分利用,降低网络负载。实验结果表明,无论在均匀分布或高度偏斜分布的场景下,还是在严格资源限制或有较高资源的场景下,CCPS-DRP在缓存命中率和平均请求时延方面的性能均明显优于常见的随处缓存策略、概率缓存策略等,其通过协同缓存与冗余控制显著提升了网络性能。
基金supported in part by the 973 Program under Grant No.2013CB329100in part by NSFC under Grant No.61422101,62171200,and 62132017+1 种基金in part by the Ph.D. Programs Foundation of MOE of China under Grant No.20130009110014in part by the Fundamental Research Funds for the Central Universities under Grant No.2016JBZ002
文摘Content-Centric Networking is a novel future network architecture that attracts increasing research interests in recent years. In-network caching has been regarded as a prominent feature of Content-Centric Networking since it is able to reduce the network traffic, alleviate the server bottleneck and decrease the user access latency. However, the CCN default caching scheme results in a high caching redundancy, causing an urgent need for an efficient caching scheme. To address this issue, we propose a novel implicit cooperative caching scheme to efficiently reduce the caching redundancy and improve the cache resources utilization. The simulation results show that our design achieves a higher hit ratio and a shorter cache hit distance in comparison with the other typical caching schemes.
文摘缓存是命名数据网络(named data networking,NDN)有别于传统网络最突出的特性之一,NDN中默认所有节点都具有缓存所有经过数据的功能.这种"处处缓存"策略导致网内大量冗余数据的产生,使网内缓存被严重浪费.针对上述问题,首次提出了一种基于节点分类(based on node classification,BNC)的数据存储策略.基于节点位置的不同,将数据返回客户端所经过的节点分为"边缘"类节点与"核心"类节点.当数据经过"核心"类节点时,通过权衡该类节点的位置与数据在不同节点的流行度分布,将数据存储在对其他节点最有利的节点中;当数据经过"边缘"类节点时,通过该数据流行度来选择最有利于客户端的位置.仿真结果表明,提出的策略将有效提高数据命中率,减少数据请求时延和距离.
