用户兴趣感知的内容副本优化放置算法

User interest-aware content replica optimized placement algorithm

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。

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 results show that each metric improves by 30% on average,which verifies the effectiveness of the proposed algorithm.