通信学报 ›› 2014, Vol. 35 ›› Issue (12): 21-27.doi: 10.3969/j.issn.1000-436x.2014.12.003

• 学术论文 • 上一篇    下一篇

用户兴趣感知的内容副本优化放置算法

阳小龙1,王欣欣1,张敏1,隆克平1,黄琼2   

  1. 1 北京科技大学 计算机与通信工程学院,北京100083
    2 重庆邮电大学 移动通信技术重点实验室,重庆400065
  • 出版日期:2014-12-25 发布日期:2017-06-17
  • 基金资助:
    国家重点基础研究发展计划(“973 计划)基金资助项目;国家自然科学基金资助项目;国家自然科学基金资助项目;国家自然科学基金资助项目;国家高技术研究发展计划(“863”计划)基金资助项目

User interest-aware content replica optimized placement algorithm

Xiao-long YANG1,Xin-xin WANG1,Min ZHANG1,Ke-ping LONG1,Qiong HUANG2   

  1. 1 College of Computer and Communication Engineering,University of Science and Technology Beijing,Beijing 100083,China
    2 Key Laboratory of Mobile Communication Technology,Chongqing University of Posts and Telecommunications,Chongqing 400065,China
  • Online:2014-12-25 Published:2017-06-17
  • Supported by:
    The National Basic Research Program of China (973 Program);The National Natural Science Foundation of China;The National Natural Science Foundation of China;The National Natural Science Foundation of China;The National High Technology Research and Development Program of China (863 Program)

摘要:

提出了用户兴趣感知的内容副本优化放置算法。该算法首先基于聚类算法从用户访问日志提取各用户的群体内容兴趣主题,依据其所辖用户的个体兴趣度加权得其群体兴趣度,并对其进行实时更新;然后在非线性优化模型下,以最小化平均响应时间为目标,优先放置群体兴趣度较大的副本,以实现被放置副本与用户内容兴趣主题的最大匹配。在平均响应时间、请求响应匹配度、负载均衡和邻近副本利用率等方面,与1-Greedy-Insert等算法进行对比,仿真结果显示各性能指标平均提升了约30%,验证了算法的有效性。

关键词: 副本放置, 兴趣感知, 聚类算法, 兴趣主题

Abstract:

A user interest-aware content replica optimized placement algorithm (UIARP) is proposed.Firstly,the interest subjects of the user-collective are extracted from their content access logs by clustering algorithms,and according to the weighting of the individual interest degree,their collective interest degree would be got and updated in real time; then under the nonlinear optimization model,replicas of larger collective interest degree have priority to be placed,with the goal of minimizing the average response time,which achieves the maximum match between placing replicas and users’ content demand.This algorithm not only ensures that users get interested replicas quickly,but also improves the system efficiency.From four aspects including average response time,the matching degree of request response,load balancing and the utilization rate of adjacent replicas,using 1-Greedy-Insert or others as compared algorithms,the simulation re-sults show that each metric improves by 30% on average,which verifies the effectiveness of the proposed algorithm.

Key words: eplica placement, interest-aware, clustering algorithm, subjects of interest

No Suggested Reading articles found!