adPD:一种速度自适应的动态并行下载技术  

A Speed-Based Adaptive Dynamic Parallel Downloading Technique

作　　者：周旭[1] 卢显良[1] 侯孟书[1] 詹川[1] 

机构地区：[1]电子科技大学计算机学院,成都610054

出　　处：《计算机科学》2005年第4期168-170,177,共4页Computer Science

摘　　要：本文在介绍了现有的并行下载算法的基础上提出了一种新的速度自适应的动态并行下载机制-adPD。adPD通过为速度不同的连接动态分配大小不同的下载任务,可以很好地适应传输连接速度的变化,做到按速度比例分配下载任务量,充分利用带宽。同时,通过划分大小不固定的文件分块,adPD还可以尽可能地减少发送数据请求的数量,缩短请求等待的空闲时间,在减轻提供服务的节点的负载的同时,提高了下载速度。最后,通过实验结果分析了adPD的实际性能,验证了adPD是一种高效的并行下载算法。In this paper, we describe adPD, an improved parallel downloading approach to retrieving files by estab- lishing parallel connections with multiple copies. adPD assigns each server equal portion of file as large as possible, which ensures client downloading from each server without interrupt. And after faster server finish its own work, ad- PD will reallocate part of unfinished work of some slower server to the faster server. By this means, adPD can dynam- ically adjust the proportion of a file retrieved from each server during the downloading process, and can also reduce the number of block requests. Experiment results show that adPD is an effective parallel download scheme especially in Peer-to-Peer environments. Our experiment results show that adPD is an effective parallel download scheme.

关 键 词：速度自适应 并行 下载技术 实验结果分析 动态分配 连接速度 比例分配 充分利用 数据请求 任务量 算法 带宽 文件 发送 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构] U415.5[自动化与计算机技术—计算机科学与技术]