To Peer or Not to Peer: Modeling the Evolution of the Internet's AS-Level Topology

Abstract

Abstract-Internet connectivity at the AS level, defined in terms of pairwise logical peering relationships, is constantly evolving. This evolution is largely a response to economic, political, and technological changes that impact the way ASs conduct their business. We present a new framework for modeling this evolutionary process by identifying a set of criteria that ASs consider either in establishing a new peering relationship or in reassessing an existing relationship. The proposed framework is intended to capture key elements in the decision processes underlying the formation of these relationships. We present two decision processes that are executed by an AS, depending on its role in a given peering decision, as a customer or a peer of another AS. When acting as a peer, a key feature of the AS's corresponding decision model is its reliance on realistic inter-AS traffic demands. To reflect the enormous heterogeneity among customer or peer ASs, our decision models are flexible enough to accommodate a wide range of AS-specific objectives. We demonstrate the potential of this new framework by considering different decision models in various realistic "what if" experiment scenarios. We implement these decision models to generate and study the evolution of the resulting AS graphs over time, and compare them against observed historical evolutionary features of the Internet at the AS level.

Fair, Flexible and Feasible ISP Billing

“…For each customer i, we first calculate the 95 th percentile billing volume Vi(0.95), and use a billing function B(x) = 50x 0.7 to translate these volumes into dollar charges. This form of the billing function is based on real-world transit prices [2] and has been used in prior work [7,3]. We refer to the sum total revenue obtained over all customers as R95, and use it as the minimum target revenue that that both the SVP and OWP schemes should assure to the transit provider.…”

Economics of quality of service

“…Furthermore, several authors have used ACE in order to assess the BE interconnection market and the development of the Internet topology (Chang et al 2006;Dhamdhere and Dovrolis 2009;Li et al 2004). However, this previous work provides only limited implications for the development of a QoS interconnection market.…”

Open peering by Internet transit providers: Peer preference or peer pressure?

“…Such models capture the decentralized and asynchronous processes through which ASes make peering decisions. Chang et al propose a model in which ASes select transit providers and settlement-free peers based on economic factors and other constraints [4]. Unlike our work, their model exogenously assigns provider and peer selection strategies to each AS.…”

“…Based on these values the average cost for 1 Gbps transit traffic in our simulation model is $11/Mbps. Transit cost exponent τ 0.75 Based on data from [4] and [22]. Based on these values the cost for 1 Gbps peering traffic in our simulation model is $0.31/Mbps.…”