The works on physical modeling try to explicate the physical causes of self-similarity in network traffic based on network mechanisms and empirically established properties of distributed systems that, collectively, collude to induce self-similar burstiness at multiplexing points in the network layer [9], etc. The traditional time series analysis, physical modeling affects model selection by picking among competing and -in a statistical sense- equally well fitting models that are most congruent to the physical networking environment where the data arose in the first place. However, physical modeling aims for models of network traffic that relate to the physics of how traffic is generated in an actual network, hence, is capable of explaining empirically observed phenomena and put insights into the dynamic nature of the traffic.