Research On The Technology Of Caching Placement And Lookup In Content Centric Networking

With the rapid development of streaming media,user generated content and other services,network's application mode is gradually transformed into massive contents' distribution and acquisition.While the end-to-end communication model of current internet lacks native support for content distribution.So,the Content Centric Networking(CCN)was proposed as a revolutionary network architecture,trying to solve the problems faced by the current network fundamentally.CCN changes the network communication mode from host-centric into content-centric through technologies of network caching and content-based routing,thereby enhancing the network content distribution performance.However,the default caching and routing scheme of CCN limit it's natural advantage of content distribution.Therefore,this paper is devoted to the study of caching placement and routing lookup scheme to improve the overall content delivery performance of CCN.The main contributions and research results are as follows:1.A utility-aware on-path caching and routing scheme is proposed.Along the content delivery path,this scheme places the response content according to the cache utility and creates transient route entries of which the survival time is consistent with the residence time of the response content in the target cache node.When a content is requested,this scheme performs cache lookups by taking advantage of transient route entries preferentially,realizing the full use of the cached contents on path.Simulation results show that this scheme can improve the cache hit ratio and the hop reduction ratio,besides,it can also reduce the number of cache replacement,thus enhancing the performance of the cache system.2.A off-path caching and routing scheme based on local centralized control is proposed.Along the content delivery path,the subsystem that has the biggest caching gain is determined by matching labels in data packets.In subsystems,the proposed scheme selects the optimal placement according to available cache space of nodes and content activity.When a content is requested,this scheme looks for the requested content by combining local content placement with route forwarding.Simulation results show that this scheme can achieve higher cache hit ratio and hop reduction ratio.3.A differentiated caching scheme based on service classification and node partition is proposed.For streaming media-on-demand services,this scheme uses push-pull cache strategy based on popularity to achieve its sequential storage in the edge network.For non-streaming contents,this scheme uses hash-based explicit cache strategy to implement its placement of single copy in the core network.Simulation results show that compared with the classic cache algorithms,this scheme can improve the cache hit ratio and the hop reduction ratio,and reduce the average request delay.