摘要
现有以信息为中心的网络(Information-Centric Network,ICN)缓存的内容的时空分布不够合理,存在无效缓存及同质化缓存等问题。对此,文中提出一种基于内容流行度和社团重要度的ICN缓存与替换策略,其结合内容流行度与节点的社团重要度来选择缓存节点,把具有不同流行度的内容分散缓存在社团重要度不同的节点上,使缓存内容的空间分布趋于合理,从而增加了缓存内容的多样性。同时,基于社团局部流行度来替换缓存内容的策略更有利于优化缓存内容的时间分布,实现缓存内容空间分布的动态调整。实验结果表明,所提策略能有效地减少用户请求的平均响应时间,提高缓存对象的命中率和全网的缓存差异度。
The temporal and spatial distribution of content in the existing information-centric networking(ICN)cache strategy is irrational,and there exists the problem of invalid caching and homogeneous caching.In light of this,this paper proposed a caching and replacing strategy in ICN based on content popularity and community importance.In this strategy,content popularity and community importance of node are combined to select caching nodes,and the contents with different popularities are cached discretely in nodes with different community importance,so as to make the spatial distribution of content be reasonable,thus improving the diversification of caching contents.Meanwhile,the replacing strategy based on local popularity in a community is propitious to optimize the temporal distribution of caching content,so that the spatial distribution of content can be adjusted dynamically.The experimental results show that the proposed strategy can effectively reduce the average response time of user interest and improve cache hit rate and cache difference in the whole network.
作者
罗建桢
蔡君
刘燕
赵慧民
LUO Jian-zhen;CAI Jun;LIU Yan;ZHAO Hui-min(Guangdong Polytechnic Normal University,Guangzhou 510665,China)
出处
《计算机科学》
CSCD
北大核心
2018年第7期116-121,共6页
Computer Science
基金
国家自然科学基金(61702120
61571141)
广东省自然科学基金(2017A030310591)
广东省教育厅(2014KTSCX149
2016KQNCX091)
广东省科技厅科技发展专项资金(2017A090905023)
广东省高等学校优秀青年教师培养计划项目(YQ2015105)
广东省应用型科技研发专项资金项目(2015B010131017)
广东省普通高校工程技术研究中心(2016GCZX006)
广州市科技计划项目(201604016108)资助