Multi-Temporal Analysis and Scaling Relations of 100,000,000,000 Network Packets
Abstract
Our society has never been more dependent on computer networks. Effective utilization of networks requires a detailed understanding of the normal background behaviors of network traffic. Large-scale measurements of networks are computationally challenging. Building on prior work in interactive supercomputing and GraphBLAS hypersparse hierarchical traffic matrices, we have developed an efficient method for computing a wide variety of streaming network quantities on diverse time scales. Applying these methods to 100,000,000,000 anonymized source-destination pairs collected at a network gateway reveals many previously unobserved scaling relationships. These observations provide new insights into normal network background traffic that could be used for anomaly detection, AI feature engineering, and testing theoretical models of streaming networks.
Keywords
Cite
@article{arxiv.2008.00307,
title = {Multi-Temporal Analysis and Scaling Relations of 100,000,000,000 Network Packets},
author = {Jeremy Kepner and Chad Meiners and Chansup Byun and Sarah McGuire and Timothy Davis and William Arcand and Jonathan Bernays and David Bestor and William Bergeron and Vijay Gadepally and Raul Harnasch and Matthew Hubbell and Micheal Houle and Micheal Jones and Andrew Kirby and Anna Klein and Lauren Milechin and Julie Mullen and Andrew Prout and Albert Reuther and Antonio Rosa and Siddharth Samsi and Doug Stetson and Adam Tse and Charles Yee and Peter Michaleas},
journal= {arXiv preprint arXiv:2008.00307},
year = {2020}
}
Comments
6 pages, 6 figures,3 tables, 49 references, accepted to IEEE HPEC 2020