Fast and accurate traffic matrix measurement using adaptive cardinality counting

Abstract

Traffic matrix (TM) can be used to detect, identify, and trace network anomaly caused by DDoS attacks and worm outbreaks. To detect network anomaly as early as possible, we need to obtain TM in a fast and accurate manner. Many existing TM estimation techniques are found not sufficient for this purpose due to their high overhead or low accuracy. We propose a cardinality-based TM measurement approach with an adaptive counting algorithm to produce both packetlevel and flow-level TM, which is well-suited for TM-based anomaly detection on a network basis. Our results show that the approach can obtain TM in almost real-time (once very 10 seconds) with low average relative error (less than 5%). Our approach has low processing, storage and communication overhead, e.g. software implementation can support OC-192 line speed. It can also be implemented in a passive mode and deployed incrementally without changing current routing infrastructure.