Network calculus is an elegant theory which uses envelopes to determine theworst-case performance bounds in a network. Statistical network calculus is theprobabilistic version of network calculus, which strives to retain thesimplicity of envelope approach from network calculus and use the arguments ofstatistical multiplexing to determine probabilistic performance bounds in anetwork. The tightness of the determined probabilistic bounds depends on theefficiency of modelling stochastic properties of the arrival traffic and theservice available to the traffic at a network node. The notion of effectivebandwidth from large deviations theory is a well known statistical descriptorof arrival traffic. Similarly, the notion of effective capacity summarizes thetime varying resource availability to the arrival traffic at a network node.The main contribution of this paper is to establish an end-to-end stochasticnetwork calculus with the notions of effective bandwidth and effective capacitywhich provides efficient end-to-end delay and backlog bounds that growslinearly in the number of nodes ($H$) traversed by the arrival traffic, underthe assumption of independence.
展开▼
机译：网络演算是一种优雅的理论，它使用包络来确定网络中最坏情况下的性能范围。统计网络演算是网络演算的概率版本，它努力保持网络演算的包络方法的简单性，并使用统计复用的参数来确定网络中的概率性能边界。所确定的概率边界的紧密度取决于对到达流量的随机属性和网络节点上的流量可用服务进行建模的效率。大偏差理论中的有效带宽概念是众所周知的到达流量统计描述符。同样，有效容量的概念总结了网络节点的到达流量随时间变化的资源可用性。本文的主要贡献是建立了具有有效带宽和有效容量概念的端到端随机网络演算，它提供了有效的端在独立性假设下，到达流量经过的节点数（$ H $）线性增长的端到端延迟和积压范围。
展开▼
