Narrow Results

We study structural feature and evolution of the Internet at the autonomous systems level. Extracting relevant parameters for the growth dynamics of the Internet topology, we construct a toy model for the Internet evolution, which includes the ingredients of multiplicative stochastic evolution of nodes and edges and adaptive rewiring of edges. The model reproduces successfully structural features of the Internet at a fundamental level. We also introduce a quantity called the load as the capacity of node needed for handling the communication traffic and study its time-dependent behavior at the hubs across years. The load at hub increases with network size N as ~ N^1.8. Finally, we study data packet traffic in the microscopic scale. The average delay time of data packets in a queueing system is calculated, in particular, when the number of arrival channels is scale-free. We show that when the number of arriving data packets follows a power law distribution, ~ n^-λ, the queue length distribution decays as n^1-λ and the average delay time at the hub diverges as ~ N^{(3-λ)/(γ-1)} in the N → ∞ limit when 2 < λ < 3γ being the network degree exponent.

The Internet is one of the largest and most complex communication and information exchange networks ever created. Therefore, its dynamics and traffic unsurprisingly take on a rich variety of complex dynamics, self-organization, and other phenomena that have been researched for years. This paper is a review of the complex dynamics of Internet traffic. Departing from normal treatises, we will take a view from both the network engineering and physics perspectives showing the strengths and weaknesses as well as insights of both. In addition, many less covered phenomena such as traffic oscillations, BGP storms, and comparisons of the Internet and biological models will be covered.

Classification of Internet traffic is very important to many applications such as network resource management, network security enforcement and intrusion detection. Many machine-learning algorithms have been successfully used to classify network traffic flows with good performance, but without information about the reliability in classifications. In this paper, we present a recently developed algorithmic framework, namely the Venn Probability Machine, for making reliable decisions under uncertainty. Experiments on publicly available real Internet traffic datasets show the algorithmic framework works well. Comparison is also made to the published results.

We use a wavelet based estimator for the parameter of long-range dependent process to analyze the scaling nature of internet traffic. Wherever and whenever these internet traffic are collected from, they exhibit long-range dependent properties. And the range of Hurst parameter is [0.5,1].