ITMgen — A first-principles approach to generating synthetic interdomain traffic matrices

Abstract

We present the design and evaluation of ITMgen, a tool for generating synthetic but representative Interdomain Traffic Matrices (ITMs). ITMgen is motivated by the observation that gravity-based models do not reflect application level or regional characteristics of Internet traffic. ITMgen works at the level of connections, taking into account the relative sizes of ASes, their popularity with respect to various applications, and the relation between forward and reverse traffic for different application types. The necessary parameters for integrating application types and the distribution of content popularity can be realistically estimated by combining public sources like Alexa that capture traffic trends at a macro level with local traffic sampling (NetFlow, DPI) for providing an additional enhancement layer at the micro level. Using the above philosophy we demonstrate that we can synthesize ITMs that match realworld measurements closer than the current state of the art. In addition, the modular design philosophy of ITMgen makes it easy to integrate additional enhancement layers that improve the accuracy of our existing implementation.

Carbon Footprints on Inter-Domain Paths: Uncovering CO2 Tracks on Global Networks

“…We compute the global inter-domain traffic matrix for all ASes in the AS-Rel data set (almost all ASes in the Internet) using the model provided by Mikians et al [46]. In this model, the amount of traffic from AS i to AS j is the sum of traffic sent from all users and servers in AS i to all servers and users in AS j for all application types:…”

“…Since log 10 d htt p falls into the range of (0.4, 1.5) for HTTP(S) data and media [46], we assume log 10 d htt p = 1. Furthermore, we assume the size of each AS to be its number of IPv4 addresses from the Pfx2AS data set, except Tier-1 ASes with no users and large CDNs with no users requesting a service.…”

“…Furthermore, we assume the size of each AS to be its number of IPv4 addresses from the Pfx2AS data set, except Tier-1 ASes with no users and large CDNs with no users requesting a service. Moreover, p htt p i ( j) follows the Zipf distribution [80] with a slope of 1.2 [46]. For each source AS, we thus generate a vector of relative popularities from the Zipf distribution.…”

Backpressure on the Backbone: A Lightweight, Non-Intrusive Traffic Engineering Approach

“…The connection of each border router to the cluster-external Internet is represented by a dedicated network interface. Each router hosts one such NIC, which is connected to an instance of an inter-domain traffic generator (ITMGen) [51]. All such instances within the same AS are identical, and their cumulatively produced traffic rate complies with ITMGen, which specifies a traffic matrix describing the average traffic flow between any AS pair.…”

“…Subsequently, p ij is approximated as p ij = pj 1−pi , i = j and p ii = 0. All other configuration parameters of ITMGen are retained [51]. Given that packet-level simulation of backbone networks is generally not tractable in terms of simulation runtimes [5], [52], we assume that the generated traffic is organized in 50 MB-sized batches (i.e., equal to the NIC twin-buffer size).…”