基于动态内容流行度的NDN缓存决策和替换策略研究

A caching decision and replacement strategy based on dynamic content popularity for NDN

命名数据网络(NDN)中的路由器节点具有缓存能力,这就极大地提高了网络中的数据发送与检索效率。然而,由于路由器的缓存能力是有限的,设计有效的缓存策略仍然是一项紧迫的任务。为了解决这个问题,提出了一种动态内容流行度缓存决策和替换策略(DPDR)。DPDR综合考虑内容流行度和缓存能力,利用一个和式增加、积式减少(AIMD)的算法动态调节流行度阈值,并将超过流行度阈值的内容存入缓存空间;同时提出了一个缓存替换算法,综合考虑了缓存空间中内容的流行度和内容最后被访问时间等因素,将替换值最小的内容移出内容缓存。大量仿真结果显示,与其他算法相比,本文所提的算法能够有效提高缓存命中率,缩短平均命中距离和网络吞吐量。

In the named data networking(NDN),routers have the capacity of in-network cache,which greatly improve the efficiency of data distribution and retrieval in the network.However,because of the limited cache capacity in routers,how to design an effective caching strategy is still a grave challenge.To solve the problem,we present a caching decision and replacement strategy based on dynamic content popularity(DPDR).It fully considers content popularity and caching capacity and utilizes an additive increase multiplicative decrease(AIMD)algorithm to dynamically adjust the popularity threshold to store the arriving data whose popularity exceeds the popularity threshold in the cache space.In addition,we also propose a caching replacement algorithm,which takes the historical information of content popularity and the last request time into account to remove the contents with lowest replacement value from the cache store(CS).Simulation results show that compared with other schemes,the DPDR strategy can effectively improve cache hit rate,reduce average cache hit distance and decrease network throughput.