Analyzing the Evolution and the Future of the Internet Topology Focusing on Flow Hierarchy

In the Internet, Autonomous Systems (ASes) exchange traffic through interconnected links. As the volume of traffic increases, more traffic becomes concentrated on such links. To reduce the traffic concentration, an AS tries to construct a new link based on local agreements between pairs of ASes. However, the current and future traffic concentrations may not be adequately resolved, since they depend heavily on the global structure of the Internet topology. An evolution that considers the global structure is necessary to continually accommodate future traffic volumes. In this paper, we first develop a method to identify the hierarchical nature of traffic aggregation on the Internet topology, and use this method to discuss the long-term changes in traffic flow. Our basic approach is to extract the “flow hierarchy”, which is a hierarchical structure associated with traffic aggregation, from the Internet topology. To extract the flow hierarchy, we focus on structures called “modules” as the unit of traffic aggregation, and determine the hierarchy of the modules that appear in the Internet topology. Our results show that the current connection policy will lead to a severe traffic concentration in the future. We then examine a new evolution policy that attempts to reduce this traffic concentration. Our proposed policy increases the number of links as the hierarchy level decreases, thus relaxing the traffic concentration. We apply our evolution policy to the Internet topology in 2000, and evolve this scenario over 13 years. The results show that our evolution policy could reduce the traffic concentration by more than half compared with that without our evolution policy.