D.V. BELKOV, E.N. EDEMSKAYA

Recent studies of real traffic data in modern computer networks have shown that traffic exhibits self-similar (or fractal) properties over a wide range of time scales. The properties of self-similar traffic are very different from the traditional models of traffic based on Poisson, Markov-modulated Poisson, and related processes. The use of traditional models in networks characterized by self-similar processes can lead to incorrect conclusions about the performance of analyzed networks. These include serious over-estimations of the performance of computer networks, insufficient allocation of communication and data processing resources, and difficulties ensuring the quality of service expected by network users. The self-similar network traffic can have a detrimental impact on network performance, including amplified queuing delay, retransmission rate and packet loss rate. Modern network traffic consists of more bursts than Poisson models predict over many time scales. This difference has implications for congestion control mechanisms and performance. The video traffic research is important because self-similar nature of network traffic leads to a number of undesirable effects like high buffer overflow rates, large delays and persistent periods of congestion and the severity of these conditions is directly proportional to the degree of self-similarity. On the other hand, the long memory property of self-similar traffic is able to help to forecast traffic for the purpose of quality of service (QoS) provision. Another interesting area in the network traffic studies is using the methods of nonlinear analysis (chaos theory) for its parameter modeling and prediction. The article contains H.263 encoded video traffic research. H.263 encoded video is expected to account for large portions of the traffic in future wireline and wireless networks. To date the analysis of H.263 encoded video has received only little literature. The experiment was executed in the Matlab environment and OpenTStool. The video flows have 16 kbit/sec (frameH16), 64 kbit/sec (frameH64), 256 kbit/sec (frameH256) and variable bit rate (frameVBR). For each video was grabbed the (uncompressed) YUV information with bttvgrab (Version 0.15.10) and stored it on disk. The YUV information was grabbed at a frame rate of 25 frames/sec in the QCIF format. The YUV frame sequences were used as input for the H.263 encoder. Next results are got: Lyapunov indexes for studied processes are equal to the zero, the dynamic system is periodic, and the phase trajectories form the cycle. For frameH16 description the two differential equalizations or two discrete maps system is necessary. For frameH64, frameH256, frameVBR description the three differential equalizations or three discrete maps system is necessary. Keywords: video traffic, quality of service, phase trajectories, attractor, correlations dimension, Lyapunov indexes.

Send an article