一种负载均衡网络中内部链路时延推测算法

A Novel Algorithm for Link Delay Inference in the Networks with Load-Balancing Routing

了解网络内部链路特征对运维大型IP网络至关重要.前人在假定固定路由条件下采用端到端主动测量的方式从网络边缘推测网络内部链路行为特征.由于网络中存在导致随机路由的负载均衡设备,使以前的主动测量方法无法实施.采用累计生成函数和随机过程方法解决随机路由条件下的网络内部链路时延推测问题.仿真结果表明,算法可以很好地解决随机路由下的内部链路时延推测问题.根据链路时延分布,可以用来判决瓶颈链路,为网络运维提供极具价值的参考.

Engineering a large IP backbone network without a view of internal link state is challenging. Previous algorithms assume that probes experience fixed routes in networks. As there are load-balancing equipments in networks, probes are delivered across random routes. This results in invalidation of the prevous algorithms. New algorithm proposed in this paper uses CGF (cumulate generating function) to infer delay characteristics of the internal link under stochastic routes. Simulation results prove that the algorithm could resolve the delay inference in the networks with load-balancing route. Based on the delay characteristics of the internal link, the bottleneck link can be located.