A Collaborative Caching Method Based on Popularity Prediction in Named Data Networks

Abstract

The present invention requests protection of a collaborative caching method based on popularity prediction in a named data network. When storing content in a named data network (Named Data Networking, NDN), multiple caching strategies along the path or caching strategies at important nodes are used to cause This ensures high redundancy of node data in the network and low utilization of cache space. This paper adopts the method of "partial collaborative caching". First, after predicting the future popularity of the content, each node allocates an optimal proportion of cache space as a local cache space to store highly popular content. The remaining part of each node stores content with relatively low popularity through neighborhood cooperation. The optimal space division ratio is calculated by considering the number of hops that the Interest packet hits the node in the network and the server-side request hits. Compared with the traditional cache strategy, this method increases the utilization rate of the cache space in the network, reduces the cache redundancy in the network, improves the cache hit rate of the nodes in the network, and improves the performance of the entire network.

Description

technical field [0001] The invention is a research on the cache strategy in the named data network, and belongs to the technical field of the future network. In particular, it involves the prediction mechanism of content popularity in the network, the cooperative caching strategy between neighboring nodes, and the division method of the node cache space ratio. Background technique [0002] With the rapid development of Internet technology and applications, "broadband", "content" and "personalization" have become the main theme of network development. People's demand for data content is becoming stronger and stronger. Service evolution transfer. According to Cisco's prediction, all content-related traffic on the Internet will account for more than 97.5% by 2016, and the traditional host-centric network architecture cannot meet the development requirements of current network information services. For this reason, Information-Centric Networking (ICN), as a revolutionary futur...

AI Technical Summary

Problems solved by technology

The above strategy only stores content indiscriminately in a small number of locations, and the rest of the nodes with poor locations will be idle, resulting in a waste of cache space in the network

Images