<title>Effect of traffic self-similarity on network performance</title>

Abstract

Recent measurements of network traffic have shown that self- similarity is an ubiquitous phenomenon present in both local area and wide area traffic traces. In previous work, we have shown a simple, robust application layer causal mechanism of traffic self-similarity, namely, the transfer of files in a network system where the file size distributions are heavy- tailed. In this paper, we study the effect of scale- invariant burstiness on network performance when the functionality of the transport layer and the interaction of traffic sources sharing bounded network resources is incorporated. First, we show that transport layer mechanisms are important factors in translating the application layer causality into link traffic self-similarity. Network performance as captured by throughput, packet loss rate, and packet retransmission rate degrades gradually with increased heavy-tailedness while queueing delay, response time, and fairness deteriorate more drastically. The degree to which heavy-tailedness affects self-similarity is determined by how well congestion control is able to shape a source traffic into an on-average constant output stream while conserving information. Second, we show that increasing network resources such as link bandwidth and buffer capacity results in a superlinear improvement in performance. When large file transfers occur with nonnegligible probability, the incremental improvement in throughput achieved for large buffer sizes is accompanied by long queueing delays vis-a- vis the case when the file size distribution is not heavy- tailed. Buffer utilization continues to remain at a high level implying that further improvement in throughput is only achieved at the expense of a disproportionate increase in queueing delay. A similar trade-off relationship exists between queueing delay and packet loss rate, the curvature of the performance curve being highly sensitive to the degree of self-similarity. Third, we investigate the effect of congestion control on network performance when subject to highly self-similar traffic conditions. We implement an open-loop congestion control using unreliable transport on top of UDP where the data stream is throttled at the source to achieve a fixed arrival rate. Decreasing the arrival rate results in a decline in packet loss rate whereas link utilization increases. In the context of reliable communication, we compare the performance of three versions of TCP--Reno, Tahoe, and Vegas--and we find that sophistication of control leads to improved performance that is preserved even under highly self-similar traffic conditions. The performance gain from Tahoe to Reno is relatively minor while the performance jump from TCP Reno to Vegas is more pronounced consistent with quantitative results reported elsewhere.