摘要
在分析业务流自相似特性对队列性能影响的基础上,提出了一种适宜自相似网络环境的队列管理算法,简称SSRED。在SSRED算法的分组丢弃概率函数中引入了自相似参数H,其目标旨在降低自相似特性所造成的影响以提高网络性能。仿真实验与分析表明,使用SSRED算法有利于提高自相似网络环境中的吞吐量、降低丢包率以及减少网络延迟等性能。
A queue management algorithm, SSRED for short, was proposed to be suit for the self-similar traffic input based on the analysis of the influence of the self-similar characteristic of traffic to the queue performance. A self-similar parameter H was introduced in the packet- dropping probability function of the proposed algorithm, aiming to reduce the effect of the self-similarity so as to improve the performance. Simulations demonstrate that the SSRED can be used to improve the throughput, and reduce the packet loss ratio and the network delay under the self-similar traffic.
出处
《系统仿真学报》
EI
CAS
CSCD
北大核心
2007年第3期597-600,共4页
Journal of System Simulation
基金
国家自然科学基金(60573127)
教育部高等学校博士点基金(20040533036
湖南省自然科学基金(03JJY4054)
湖南省教育厅资助科研项目(05c409)。
关键词
自相似业务
队列管理
分组丢弃概率
性能评价
self-similar traffic
queue management
packet dropping probability
performance evaluation
