Study On Cache Placement Policy Based On Information-Centric Networking

With the rapid development of Internet technology and applications, and the rapid growth of Internet users, broadband, personalization and magnanimity has become the main theme of Internet development. Based on the high-speed data growth trend, it’s not difficult to predict that one of the main challenges of the future Internet will be the contradictory between reliable vast amounts of content distribution or high quality of service (QoS) and what our network infrastructure can provide, storage or transmission capacity etc. In order to deal with the above challenges and adapt to distribute content efficiently, academia has promoted a series of information-centric architecture in recent years. These architectures commonly are committed to the separation of locator and identifier, no longer concerning about the "Where"(addresses and host), but concerning about the "What"(the content or information that user or application needs).This paper first analyzes the main characteristics and key technology of Information-Centric Networking (ICN), then some well-known typical ICN models, such as CCN/NDN, PSIRP/PURSUIT etc. are discussed and analyzed. We introduce the cache group model and an optimal cooperative depth cache placement algorithm to solve the optimization equation we evaluated, and then we compare the performance and benefits with others. Finally, we also describe the design and implementation prototype of cache group model.Work and contribution of this paper includes the following two aspects:First, in the third chapter, based on the cache group model in autonomous system (AS), considering the division of the node’s cache into two separate parts, one for independent cache, another for cooperative function, the mathematical model for the content placement problem in cache group, together with the optimization objectives and constraints condition are introduced. To solve the equation, we propose the optimal cooperative depth placement algorithm, and the simulation results show that our proposed algorithm is effective in reducing the overall access delay.Second, in the fourth chapter, based on the CCN/NDN prototype CCNx, we discussed the design and implementation of cache group system model in detail, including the user request module, routing node module and controller. Cache group model prototype system not only shows that our model and algorithm can be simply and easily deployed, but also provides a foundation platform for further design and implementation of other cache placement policy based on cache group model.