An implementation of LoSS detection using SOSS model

Abstract

Recent studies have shown that malicious Internet traffic such as Denial of Service (DoS) packets introduces distribution error and perturbs the self-similarity property of network traffic. As a result, Loss of Self-Similarity (LoSS) is detected due to the abnormal traffic packets hence degrading the Quality of Service (QoS) performance. In order to fulfill the demand for high speed and accuracy for online Internet traffic monitoring, we propose LoSS detection with second order self-similarity statistical (SOSS) model and estimate the self-similarity parameter using the Optimization Method (OM). We test our approach using synthetic and real traffic data. For the former, we use fractional Gaussian noise (fGn) generator, while for the latter we use FSKSMNet simulation dataset. We investigate the behavior of self-similarity property for normal and abnormal traffic packets with different aggregation sampling level (m). The results show that normal Internet activities preserve exact self-similarity property while abnormal traffic perturbs the structure of self-similarity property. The results also demonstrate that fixed m is not sufficient to detect distribution error accurately. Accordingly, we suggest a multi-level aggregation sampling approach to improve the accuracy of LoSS detection.