|
Authors: | Ignasi Paredes-Oliva, Pere Barlet-Ros, Xenofontas Dimitropou |
Group: | Communication Systems |
Type: | Inproceedings |
Title: | FaRNet: Fast Recognition of High Multi-Dimensional Network Traffic Patterns |
Year: | 2013 |
Month: | June |
Book Titel: | ACM SIGMETRICS |
Abstract: | Extracting knowledge from big network trac data is a mat- ter of foremost importance for multiple purposes ranging from trend analysis or network troubleshooting to capac- ity planning or trac classication. An extremely useful approach to prole trac is to extract and display to a net- work administrator the multi-dimensional hierarchical heavy hitters (HHHs) of a dataset. However, existing schemes for computing HHHs have several limitations: 1) they require signicant computational overhead; 2) they do not scale to high dimensional data; and 3) they are not easily extensible. In this paper, we introduce a fundamentally new approach for extracting HHHs based on generalized frequent item-set mining (FIM), which allows to process trac data much more eciently and scales to much higher dimensional data than present schemes. Based on generalized FIM, we build and evaluate a trac proling system we call FaRNet. Our comparison with AutoFocus, which is the most related tool of similar nature, shows that FaRNet is up to three orders of magnitude faster. |
Location: | Pittsburgh, PA |
Resources: | [BibTeX] [Paper as PDF] |