Network traffic measurement studies have shown the presence of self-similar behavior in both local area and wide area traffic traces. In this study we investigated the magnitude of the self-similarity behavior of network traffic and its Hurst measurement, H. Our study has revealed several characteristics of H based on the network traffic changes. From the finding, H can be used as traffic load indicated only if the sampling size is large. On the other hand for a smaller sampling size, H can be used to indicate the change in traffic pattern. However network traffic does not always exhibit self-similarity property. Activities such as peer-to-peer can steer the traffic to lose this property
Many researchers have discussed the effects of heavy-tailedness in network traffic patterns and show...
The self-similarity properties of the considered traffic were checked on different time scales obtai...
It is critical to properly understand the nature of network traffic in order to effectively design m...
We present a new method to estimate the Hurst pa-rameter of the increment process in network traffic...
The discovery of the self similarity of Ethernet traffic at Bellcore has had a profound effect on th...
We present a new method to estimate the Hurst parameter of the increment process in network traffic ...
The optimal computer network performance models require accurate traffic models, which can capture t...
Self-similarity is a major assumption used in the modelling and characterization of Internet traffic...
Recent measurements of local-area and wide-area traffic have shown that network traffic exhibits va...
There is a growing evidence that aggregated traffic in a variety of network, with different extent ...
Recent traffic analyses from various packet networks have shown the existence of long-range dependen...
Since the seminal study of Leland, Taqqu, Willinger and Wilson [41] which set the groundwork for con...
Recent measurements of network traffic have shown that self-similarity is a ubiquitous phe-nomenon p...
The article analyses the indicators implemented for investigating the network self-similarity: the H...
High-resolution traffic measurements from modern communications networks provide unique opportunitie...
Many researchers have discussed the effects of heavy-tailedness in network traffic patterns and show...
The self-similarity properties of the considered traffic were checked on different time scales obtai...
It is critical to properly understand the nature of network traffic in order to effectively design m...
We present a new method to estimate the Hurst pa-rameter of the increment process in network traffic...
The discovery of the self similarity of Ethernet traffic at Bellcore has had a profound effect on th...
We present a new method to estimate the Hurst parameter of the increment process in network traffic ...
The optimal computer network performance models require accurate traffic models, which can capture t...
Self-similarity is a major assumption used in the modelling and characterization of Internet traffic...
Recent measurements of local-area and wide-area traffic have shown that network traffic exhibits va...
There is a growing evidence that aggregated traffic in a variety of network, with different extent ...
Recent traffic analyses from various packet networks have shown the existence of long-range dependen...
Since the seminal study of Leland, Taqqu, Willinger and Wilson [41] which set the groundwork for con...
Recent measurements of network traffic have shown that self-similarity is a ubiquitous phe-nomenon p...
The article analyses the indicators implemented for investigating the network self-similarity: the H...
High-resolution traffic measurements from modern communications networks provide unique opportunitie...
Many researchers have discussed the effects of heavy-tailedness in network traffic patterns and show...
The self-similarity properties of the considered traffic were checked on different time scales obtai...
It is critical to properly understand the nature of network traffic in order to effectively design m...