Adding Geographical Embedding to AS Topology Generation

TL;DR

This paper enhances AS topology models by incorporating geographical embeddings, enabling more realistic routing path and latency simulations, validated against real-world data.

Contribution

It introduces a novel model that adds geographical information to the Positive Feedback Model for more accurate AS topology and latency representation.

Findings

Generated latencies match measured data.

Geographical properties align with real-world datasets.

Model enables realistic routing path simulation.

Abstract

To study large-scale effects on the Internet various mod- els have been introduced to generate Internet-like autono- mous system (AS) topologies. The models for large-scale AS topologies have been focused on replicating structural graph properties. One of the most promising model is the Positive Feedback Model model (PFP). These models how- ever lack the ability to generate routing path and realistic latency. We present a model to enrich the AS peering graph with peering points. Our new model allows to calculate path for the connections between end hosts and to infer the latency from these paths. We introduce a new notion for the genera- tion of AS topologies: the compactness of an AS. We introduce an algorithm based on the PFP algorithm which generates instances for our model. Verifying the gen- erated model instances shows that the resulting latencies as well as the geographic properties match measured data sets.