A novel computer network traffic modeling based on threshold-optimization

Aiming at bottlenecks (such as ambiguous physical meaning, complex mathematical expression, and so on) in traditional network traffic modeling analysis, this paper puts forward a novel threshold-optimization-based traffic model.In this model, the actual network traffic is divided into two different parts (i.e., a-traffic with burst characteristic, and b-traffic with steady characteristic) according to optimized threshold results obtained with particle swarm optimization algorithm. The atraffic and b-traffic are respectively described with mathematical formulas which not only can depict the traffic nature precisely but also can be resolved easily. It is proved that the threshold-optimization-based traffic model presented in this paper can describe the traffic nature more accurately.