Performance modeling of TCP/AQM with generalized AIMD under intermediate buffer sizes

For TCP/AQM systems, the issue of buffer sizing has recently received much attention. In the recent literature, it is suggested that the buffer size be O(radicN) for high link utilization contrasting to the traditional bandwidth-delay product, i.e., O(N) for 100% utilization where the link has capacity NC serving N flows. However, these results are all limited to the drop-tail scheme and there has been no systematic modeling framework for any buffer sizing between O(radicN) and O(N). In this paper, we study the limiting behavior of a TCP/AQM system for an intermediate buffer sizing of O(N^gamma) (0.5lesgamma<1). We develop a stochastic model in a discrete-time setting to characterize the system dynamics and then show that we can have 100% link utilization and zero packet loss probability for a large number of flows when the buffer size requirement is anywhere between O(radicN) and O(N). Our model is general enough to cover any queue-based AQM scheme with ECN marking (including the drop-tail) and various generalized AIMD algorithms for each TCP flow