一种基于聚合流的端到端统计时延界的新算法

A new algorithm for aggregate flow-based end-to-end delay bound

为分析融合网络中聚合业务的端到端时延性能,提出一种基于聚合流的融合网络端到端统计时延界的新算法。该算法利用MGF(矩母函数)重新表征了网络端到端时延界的MGF形式的概率模型。数值分析结果表明了该算法的有效性和优越性,该算法很大程度上提高了独立统计复用,对融合网络性能评价具有参考意义。

In order to analyze the end-to-end delay performance of aggregate traffic in converged networks,this paper proposes a new algorithm for the end-to-end statistical delay bound of aggregate flow-based converged networks.Using the theorem of the Moment Generating Function（MGF）,this algorithm re-characterizes the MGF probabilistic model of network end-to-end delay bound.Numerical analysis results show that this algorithm is effective and can improve independent statistical multiplexing to a great extent,offering much value of reference for converged network performance evaluation.