电信科学 ›› 2014, Vol. 30 ›› Issue (9): 45-52.doi: 10.3969／j.issn.1000-0801.2014.09.007

• 专题：信息中心网络（ICN） • 上一篇    下一篇

NDN中基于蚁群替换算法的邻居协作缓存管理策略

董利利1,王勇1,董永强1,2,杨鹏1,2   

  1. 1 东南大学计算机科学与工程学院 南京211189
    2 东南大学计算机网络和信息集成教育部重点实验室 南京211189
  • 出版日期:2014-09-20 发布日期:2017-07-05
  • 基金资助:
    国家高技术研究发展计划（“863”计划）基金资助项目;江苏省未来网络前瞻性研究基金资助项目

Collaborative Cacbe Management Strategy Based on Ant-Colony Replacement Algoritbm in Named Data Networking

Lili Dong1,Yong Wang1,Yongqiang Dong1,2,Peng Yang1,2   

  1. 1 School of Computer Science and Engineering, Southeast University, Nanjing 211189, China
    2 Key Laboratory of Computer Network and Information Integration, Ministry of Education, Southeast University, Nanjing 211189, China
  • Online:2014-09-20 Published:2017-07-05

在线阅读

4

PDF下载

503

被引次数

9

摘要：

为提高NDN（命名数据网络）中的缓存利用率，提出了一种基于蚁群替换算法的邻居协作缓存管理（ACNCM）策略。首先将单节点的缓存替换问题，建模为0／1背包问题，并根据缓存数据的大小、使用频率以及邻居副本深度等信息定义本地存储内容的缓存价值，提出基于蚁群算法的缓存替换算法。然后利用邻域协作的思想，通过路由节点之间定期交换自身节点的缓存信息，对单个节点替换出去的缓存内容，选择邻居节点完成协作式缓存管理。实验结果表明，ACNCM策略在缓存命中率、网络开销和平均响应时延方面均优于现有方法。

关键词: 命名数据网络, 缓存管理, 内容缓存价值, 蚁群替换算法

Abstract:

To improve the cache utilization in named data networking, a collaborative cache management strategy, named as ACNCM（ant-colony based neighbor cooperation cache management）, was proposed. The cache replacement problem in a single node was modeled as a 0／1 knapsack problem firstly, which could be well solved by an ant-colony replacement algorithm. To facilitate the execution of the algorithm, the inner content caching value was calculated by taking into account the size of the content, the access frequency of the content, and the status of neighboring cache copies. Once the to-be replaced content has been figured out, ACNCM was exploited to choose one available collaborative neighbor node to store the content, according to the regular exchange of caching information among neighboring nodes. The experimental results show that ACNCM outperforms the existing caching schemes in terms of cache hit rate, network overhead and the average response latency.

Key words: named data networking, cache management, content caching value, ant-colony replacement algorithm

No Suggested Reading articles found!