摘要
在向下一代互联网络演进的过程中,多路径网络已经成为提高网络性能及可靠性的有效手段。在网络中,可选用的多条路径提供了流量流向的通路,然而如何有效地均衡各条路径的流量,提高网络的性能,是多路径网络必须解决的一个重要问题。针对丢包率比较敏感的应用需求,如VOIP,将预测思想与最优化理论相结合,研究了在多路径网络环境下的流量均衡问题。流量均衡算法首先预测每条路径的丢包率,并以减少所有路径丢包率之和及达到最优的资源利用率为目标,将流量均衡问题转化为最优问题。理论分析及仿真实验表明,该算法能有效地降低网络丢包率,提高网络性能。
During the migration to next generation network, multipath network may be used for improving reliability and robustness. The chose multipath in network is the paths which supply the traffic to transfer. How to balance the traffic availability is one of the most important problems in multipath network to improve the performance. To loss ratesensitive traffic,such as VOIP (Voice over Internet Protocol), this paper provided an algorithm to solve the problem of balancing the traffic in muhipath network by prediction and optimization theory. The algorithm predicts the packet loss rate of each and every path at first, then aiming at the minimum sum of the packet loss rate and achieving the optimal utilization ratio of resources, it converts a traffic balancing problem into optimization problem. The experimental results demonstrate that the proposed algorithm can perform well on QOS, such as packet loss rate.
出处
《计算机科学》
CSCD
北大核心
2010年第7期74-78,114,共6页
Computer Science
基金
国家自然科学基金(06273078)
河北省科技厅博士基金项目(554701303)资助
关键词
多路径网络
流量均衡
优化
预测
Multipath network, Traffic allocation, Optimization theory, Prediction