Optimal Deployment of Distributed Passive Measurement Monitors

Flow-level traffic measurement is important for network management. The widely used centralized per-flow measurement faces a great challenge due to the demanding requirement on both memory bandwidth and memory size within a single traffic monitor. This paper addresses the issue of deploying a Distributed Passive Measurement System (DPMS) in a large scale network; specifically, we study how to optimally place traffic monitors and sample stochastic traffic flows, so that the probability of a packet being sampled (a.k.a. measurement coverage) is maximized. We formulate this problem as a Stochastic Chance Constrained Optimization (SCCO) problem; and we propose a Hybrid Intelligent (HI) algorithm to solve this problem. The HI algorithm consists of two major components, namely, uncertain function approximation and genetic algorithm. Equipped with the HI algorithm, we are able to address the optimal tradeoff between measurement coverage and deployment cost for networks with random traffic, which has not been studied before. Our simulations and experiments demonstrate the effectiveness of our algorithm, i.e., a small deployment cost or a small number of monitors are sufficient to maintain a high level of measurement coverage.