Application of sampling methodologies to network traffic characterization
SIGCOMM '93 Conference proceedings on Communications architectures, protocols and applications
New directions in traffic measurement and accounting
Proceedings of the 2002 conference on Applications, technologies, architectures, and protocols for computer communications
Properties and prediction of flow statistics from sampled packet streams
Proceedings of the 2nd ACM SIGCOMM Workshop on Internet measurment
Bitmap algorithms for counting active flows on high speed links
Proceedings of the 3rd ACM SIGCOMM conference on Internet measurement
Proceedings of the 3rd ACM SIGCOMM conference on Internet measurement
Proceedings of the 2004 conference on Applications, technologies, architectures, and protocols for computer communications
Ranking flows from sampled traffic
CoNEXT '05 Proceedings of the 2005 ACM conference on Emerging network experiment and technology
Proceedings of the 6th ACM SIGCOMM conference on Internet measurement
Impact of packet sampling on anomaly detection metrics
Proceedings of the 6th ACM SIGCOMM conference on Internet measurement
Is sampled data sufficient for anomaly detection?
Proceedings of the 6th ACM SIGCOMM conference on Internet measurement
An improved construction for counting bloom filters
ESA'06 Proceedings of the 14th conference on Annual European Symposium - Volume 14
Time-Out bloom filter: a new sampling method for recording more flows
ICOIN'06 Proceedings of the 2006 international conference on Information Networking: advances in Data Communications and Wireless Networks
Learn more, sample less: control of volume and variance in network measurement
IEEE Transactions on Information Theory
Fair sampling across network flow measurements
Proceedings of the 12th ACM SIGMETRICS/PERFORMANCE joint international conference on Measurement and Modeling of Computer Systems
Hi-index | 0.00 |
Due to the high-skewed nature of network flow size distributions, uniform packet sampling concentrates too much on a few large flows and ignores the majority of small ones. To overcome this drawback, recently proposed Sketch Guided Sampling (SGS) selects each packet at a probability that is decreasing with its current flow size, which results in better flow wide fairness. However, the pitfall of SGS is that it needs a large, high-speed memory to accommodate flow size sketch, making it impractical to be implemented and inflexible to be deployed. We refined the flow size sketch using a multi-resolution d-left hashing schema, which is both space-efficient and accurate. A new fair packet sampling algorithm which is named Space-Efficient Fair Sampling (SEFS) is proposed based on this novel flow size sketch. We compared the performance of SEFS with that of SGS in the context of flow traffic measurement and large flow identification using real-world traffic traces. The experimental results show that SEFS outperforms SGS in both application contexts while a reduction of 65 percent in space complexity can be achieved.