Traffic measurement algorithm for self-similar traffic based on probability admission mechanism

Effective traffic measurement algorithms are of critical importance to IP network management tasks: for instance, traffic engineering, network performance evaluation and network security. This paper proposes a traffic measurement algorithm for self-similar traffic model: probability-admission multistage filters algorithm. This algorithm uses multistage filters and probability admission mechanism to concentrate on large flows. Using analysis and simulation, this algorithm is shown to effectively reflect the bursts of self-similar traffic over multiple time scales and can improve accuracy when network flows are self-similar.