基于概率的启发式ICN缓存内容放置方法

Probability-based heuristic content placement method for ICN caching

提出一种基于概率存储的启发式住处中心网络内容缓存方法(PCP)。主要思想是请求消息和数据消息在传输过程中统计必要信息,当数据消息返回时,沿途各缓存节点按照一定概率决策是否在本地缓存该内容。设计缓存概率时综合考虑内容热度和缓存放置收益,即内容热度越高,放置收益越大的内容被缓存的概率越高。实验结果表明,PCP在缓存服务率、缓存命中率、平均访问延迟率等方面,与现有方法相比具有显著优势,同时PCP开销较小。

A probability-based heuristic caching strategy（PCP） was proposed. The major idea was that relevant information was collected when the interest and data packet are transmitted. When the data packet is returned back, on-path cache nodes decide whether to cache the content with certain probability. The probability is associated with the content popularity and placement benefit, i.e., proportional to content popularity and content placement benefit. The experimental results indicate PCP can achieve salient performance gain in terms of cache service ratio, cache hit ratio, access latency ratio, compared with current strategies. Meanwhile, PCP＇s overhead is affordable.