一种用于Optical Crossbar的自适应分组汇聚算法

A New Adaptive Assembly Algorithm in Optical Crossbar for Switching Networks

在对现有分组汇聚机制进行深入分析的基础上,考虑不同网络环境下的流量特性不同,提出了一种动态网络流量自适应分组汇聚算法。理论分析及仿真实验表明,该算法可自适应网络流量特性的变化,通过优化汇聚分组长度解决连续阻塞问题、提高汇聚分组利用率,同时兼顾时间门限,使之在低流量负载下也能最大程度保证汇聚时延,较好地弥补传统算法的不足,保证了Optical Crossbar网络对于实时流量的低时延和高传输效率．

In optical crossbar networks, packet assembly is one of the critical technologies and will significantly affect the performance of networks. This paper focuses on the study of assembly mechanism and propose a new adaptive assembly algorithm, which reduces the self-similarity of IP traffic, enhances the data packet utilization and avoids the bandwidth contention, to provide bandwidth and delay guarantees of optical crossbar.