欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
利用分布式哈希表（DHT）技术和简单的随机邻居策略,提出了一种基于云对等网络的资源搜索算法（RCLOUD）,解决了以1-c的概率在d跳内完成查询的问题,c和d均为可设定的常数.该算法的一个主要优势是当节点加入或离开时邻居信息维护开销低.仿真实验结果表明,与经典Chord等P2P算法相比,RCLOUD网络中云节点只有在网络规模N增加一倍（或减半）时才会增加（或减少）其随机邻居的数量,并且不牺牲系统效率.这表明任意邻居的查找与N的大小无关,可以高概率将查询跳数控制在常数跳d以内.
英文摘要：
Based on distributed hash tabie （DHT）technology and simple uniformly-random neighbor selection stealegy,this paper explored the design space using the simple uniformly-random neighbor selection strategy,and proposed the RCLOUD network.The RCLOUD was the could network based some P2P ideas that was the first of its kind to resolve requests in d hops with a chosen probability of 1-c,where c and d were constants.A major advantage of it was that the neighbor information maintenance overhead was low when nodes join or leave.The simulation results show that compared with the traditional Chord algorithm a note increases（or dexreases） its number of random neighbors only when the total number of noded （N）doubles （or halves） wiithout sacificing the performance.Note that the location of particular neighbor is independent of N.It can resolve reqests in d hops with a chosen high probability.
同期刊论文项目
同项目期刊论文
期刊信息
位置：