Research On Caching Based On Content Popularity Prediction In Content Centric Networking

With the continuous development of the Internet, the user's business needs more diverse and complex, and the network traffic load is increasing day by day, which presents new challenges to the existing network architecture. Traditional network uses the host address as the core of the communication model. But in the future of Internet Ecology,the user is more concerned about the information itself rather than the destination of the information. In this context, the information-centric networking has attracted more and more attention in academic circles.This is a new type of network architecture based on information for routing, distributing and caching. Network caching is one of the salient features of this new network model. By this way, ICN can achieve faster content access, improve resource utilization and reduce the user waiting time. There are many forms of ICN implementation, CCN is one of them.The traditional CCN used LCE caching strategy, which can not use limit cache space efficiently, distinguish the difference between the contents of different access frequency, resulting in a waste of resources and serious content redundancy, is not conducive to improve the diversity of the cache content at the same time, also the whole of the load of the network has brought many pressure, unable to distinguish the difference between the contents of different access frequency, resulting in a waste of resources and serious content redundancy. This strategy is not conducive to improve the diversity of content, increasing the overall load of the network.In the content center network, the content is the core, the design of the cache system should also focus on the characteristics of the content itself. Aiming at this problem, this paper proposes a BEACON cache policy system based on the content popularity prediction. First, we define a new concept of content popularity to measure the user preference in the content, and design the content popularity collection and statistics module,for monitoring function. Secondly, we use the gray prediction theory to predict the popularity based on the historical data. Then, we design the topological evaluation module. On the basis of this, the design of BEACON caching strategy is completed. Finally, we compare the difference in performance between the BEACON strategy and several other commonly used strategies based on the simulation environment.The experimental results show that the BEACON strategy can effectively improve the network cache hit rate, improve the utilization rate of cache resources, reduce network load, thereby reducing the time consumption of the user access to resources, enhance the overall performance of the network.