对等网络中改进蚁群智能搜索算法研究  

Intelligent Search Study Based on Improved Ant Colony Algorithm in P2P Networks

作　　者：苏锦旗 郭玉龙 

机构地区：[1]西安邮电大学经济与管理学院,西安

出　　处：《数据挖掘》2014年第3期19-26,共8页Hans Journal of Data Mining

基　　金：国家自然科学基金项目(71173248);陕西社会科学基金(13Q081);西安邮电大学青年教师科研基金项目(ZL2012-30)。

摘　　要：为了提高蚁群算法在P2P网络资源搜索中存在搜索盲目、搜索效率低的问题,论文将多态蚁群算法和应用到了P2P网络搜索。针对搜索一段时间后网络中发起的对新的文件请求,引入合成信息素的概念,以减少搜索初始阶段消息转发的盲目性。对无结构P2P网络中的洪泛算法、蚁群算法、引入合成信息素后的蚁群算法进行模拟实验,实验结果表明所提出的算法可有效提高P2P网络的搜索性能。In order to enhance the practicality of ant colony algorithm and improve the search efficiency of peer-to-peer networks, this paper presents a new approach of unstructured P2P information re-trieval based on the polymorphic ant colony algorithm. In order to meet the new file requirement after a while of searching, the conception of generated pheromone is imported to decrease the blindness of pack forwarding in early searching stage. Based on the simulator framework, simu-lating the flooding, ant colony algorithm, ant colony algorithm with generated pheromone in un-structured peer-to-peer networks, and analyzing the experience data, the experience results indi-cate that the algorithm is effective and can enhance the performance of peer-to-peer networks.

关 键 词：对等网 搜索 多态蚁群算法 合成信息素 

分 类 号：TP39[自动化与计算机技术—计算机应用技术]