Research On Cache Technology Based On Content Popularity In Named Data Networking

The main function of the Internet is to satisfy the needs of users for connection and resource sharing.In the past decade,content acquisition services represented by video distribution and file download have become mainstream application requirements on the Internet.With the growth of Internet users year by year,TCP/IP network architecture has many disadvantages in data packet distribution,such as low security,insufficient flexibility,and poor scalability,and it is difficult to satisfy new network requirements in the future.To solve the above problems,researchers have proposed a new type of network architecture Information Centric Networking(ICN)to improve the quality of network services.Named Data Networking(NDN)is one of the famous ICN network architectures.NDN aims to change the traditional content delivery method and caching method through router node caching and participating in forwarding.The built-in pervasive caching is one of the most important features of named data networking(NDN),which can provide effective data delivery even in presence of short-lived and intermittent connectivity.NDN-caching can reduce the expected flood of global data traffic by providing cache storage at intermediate nodes for transmitted contents,making data broadcasting in an efficient way.In addition,the network cache function can also shorten the content delivery time and greatly improve the quality of service.How to design an efficient caching strategy to maximize the use of NDN's in-network caching function is one of the problems faced by NDN.At present,the commonly used caching strategies in NDN such as LCE,ProbCache,CL4M,and LCD can improve system performance to a certain extent,but the improvement effect is limited.To further improve the performance of NDN,we designed three caching strategies suitable for different scenarios from different perspectives:1.According to the local content popularity,a caching strategy based on Entropy weighting method and TOPSIS is proposed.The caching strategy includes the following steps:Firstly,the user's request process is modeled by the Entropy weighting method and TOPSIS,and the best cache node is calculated for the cache object according to the real-time state of the node.Secondly,to reduce the cache redundancy on the delivery path and improve the utilization of data packets in the nodes,a novel cache replacement algorithm(composed of an active cache replacement algorithm and a passive cache replacement algorithm)are proposed.Finally,an effective cache mechanism and packet migration scheme are proposed to further improve the cache performance according to the different types of cache nodes2.Considering the global popularity,a cache placement strategy based on compound popularity(content popularity and node popularity)is proposed.The scheme aims to enhance the reuse rate of data packets by jointly considering the content popularity and the node popularity in a period of time.Meanwhile,in the scheme,the content popularity can be calculated in a lightweight way.3.Considering the static characteristics of nodes in the network,a cache placement strategy based on topology layering is proposed.The scheme uses the K-means clustering algorithm to classify the nodes and uses the classification results as the basis to realize the stratification of the complex topology of multiple servers.Meanwhile,it combines the global popularity and local popularity of the content to complete the precise layer placement of popular content,so as to improve the caching performance in the case of low network caching capabilities.