Global Internet public peering capacity of interconnection: a complex network analysis

Abstract: A massive and growing part of Autonomous System (AS)-level traffic exchanges takes place at Internet Exchange Points (IXPs). This paper leverages PeeringDB, a database providing a partial but reasonable view of the global interconnection of ASes at IXPs, to model a complex graph enabling the characterization of the key Internet peering players and their interactions over time. We model a PeeringDB snapshot as a weighted directed bipartite graph, called the pDB c-graph, that captures the port size ASes possess at IXPs using available metadata. This novel model of the Internet is shown to picture relevant features of a complex network that groups ASes and IXPs in geographical areas of influence. From this model, we extract central players of public peering such as hypergiant AS content providers and major regional traffic receivers. Most importantly, this graph model opens the way to apply spectral analysis using reduced Google matrix in order to retrieve the intensity of possible interactions between ASes on the basis of pure connectivity information. As an illustration, we retrieve the timely evolution of the peering network to show how the central content and cloud providers have increased their reach to eyeball networks during Covid-19 pandemic.