YATES: Rapid Prototyping for Traffic Engineering Systems

[ paper ] [ doi ]

ACM SOSR 2018

Praveen Kumar, Chris Yu, Yang Yuan, Nate Foster, Robert Kleinberg, and Robert Soulé.

Abstract

This paper presents the design and implementation of YATES, a software framework that seeks to dramatically lower the cost of experimenting with different traffic engineering approaches. YATES offers a suite of tools that make it possible to rapidly prototype and evaluate the performance of traffic engineering systems including tools for modeling topologies, routing schemes, demands, prediction algorithms, and failures. YATES comes with two backends: a network simulator that calculates congestion, throughput, loss, latency, etc., and an SDN-based implementation that can be used to validate results obtained via simulation and also provides an easy path to deployment. We evaluate YATES by prototyping 17 TE systems of varying complexity.

BibTeX

@inproceedings{kumar2018yates,
  author = {Kumar, Praveen and Yu, Chris and Yuan, Yang and Foster, Nate and
      Kleinberg, Robert and Soul\'{e}, Robert},
  title = {{YATES}: Rapid Prototyping for Traffic Engineering Systems},
  year = {2018},
  publisher = {Association for Computing Machinery (ACM)},
  booktitle = {Proceedings of the Symposium on SDN Research (SOSR)},
  location = {Los Angeles, CA, USA},
  series = {SOSR '18}
}

[ paper ] [ doi ]