Modern tools to measure Internet traffic such as Wireshark or Atheris offer complex opportunities to collect packet data from high speed networks. Advanced statistical methods are required to support an adequate teletraffic analysis of these traces and the evaluation of relevant performance indices, for instance, of captured packet flows stemming from new multimedia services in Internet. They allow us to cope with immanent dependencies and underlying heavy-tailed distributions of interesting features of the traffic such as the bitrates, volumes or lengths of sessions, the inter-arrival times, loss rates and delay distributions of the packet streams or their equivalent bandwidth.  In the tutorial we shall discuss useful statistical techniques to handle the arising strongly correlated or long-range dependent time series and heavy-tailed marginal distributions. The latter features characterize the underlying random variables of the observed data. Advanced procedures to compute the demanded bandwidth of observed streams or the delay-loss profiles of packet flows during a session will be stated. The analysis concepts will be illustrated by real traces arising from some popular Internet applications.  The tutorial shall stimulate the participants to incorporate adaptations of the sketched statistical procedures into open source tools or their own codes according to their personal needs.

The paper deals with a multi-server controllable queueing system M(t)/M/K with time-dependent and, in particular, with periodic arrival rates. The models with homogeneous and heterogeneous servers are of interest. In latter case the fastest free server allocation mechanism is assumed and the preemption is allowed. The control problem consists in evaluation of the optimal number of servers during some specified stages and is solved by finite horizon dynamic programming approach. To calculate the transient solutions we use a forth-order Runge-Kutta method for the system with a truncated queue length. The results are compared with corresponding queues operating in a stationary regime. It is shown that the optimal control policies are also time dependent and periodic as arrival rates and heterogeneous systems are superior in performance comparing to the homogeneous ones.

Tandem queueing systems often arise in wireless networks modeling. Queueing models are very suitable for network performance evaluation but the system complexity exponential growth (or state space explosion) could make the analysis barely feasible. The paper presents a comparative study of various methods of a state space reduction for markovian arrival processes (MAP) and phase-type distributions (PH) applied to tandem queueing systems. The applied methods include non- linear optimization, EM-algorithm and linear minimization. While most of the described algorithms are well-studied, a number of issues arises when applying them to a tandem system of a real wireless network. Particularly, it is shown that while all the algorithms could be applied to tandems with a small number of queues, bigger tandems require ad- ditional eort to get the appropriable results. Nevertheless, the results presented show that the departure MAPs reduction may help to solve the state space explosion problem.