Machine-learnt versus analytical models of TCP throughput

Abstract

We first study the accuracy of two well-known analytical models of the average throughput of long-term TCP flows, namely the so-called SQRT and PFTK models, and show that these models are far from being accurate in general. Our simulations, based on a large set of long-term TCP sessions, show that 70% of their predictions exceed the boundaries of TCP-Friendliness, thus questioning their use in the design of new TCP-Friendly transport protocols. We then investigate the reasons of this inaccuracy, and show that it is largely due to the lack of discrimination between the two packet loss detection methods used by TCP, namely by triple duplicate acknowledgments or by timeout expirations. We then apply various machine learning techniques to infer new models of the average TCP throughput. We show that they are more accurate than the SQRT and PFTK models, even without the above discrimination, and are further improved when we allow the machine-learnt models to distinguish the two loss detection techniques. Although our models are not analytical formulas, they can be plugged in transport protocols to make them TCP friendly. Our results also suggest that analytical models of the TCP throughput should certainly benefit from the incorporation of the timeout loss rate.

A comprehensive survey on machine learning for networking: evolution, applications and research opportunities

“…Network protocols adapt their operation based on estimated network parameters that allow to infer the congestion state. For example, some multicast and multipath protocols rely on predictions of TCP throughput to adjust their behavior [238,316], and the TCP protocol computes the retransmission timeout based on RTT estimations [22]. However, the conventional mechanisms for estimating these network parameters remain inaccurate, primarily because the relationships between the various parameters are not clearly understood.…”

“…For the aforementioned reasons, several ML-based approaches have addressed the limitations of inferring the congestion in various network architectures by estimating different network parameters: throughput [238,316,371], RTT [22,128], and mobility [309] in TCP-based networks, table entries rate in NDNs [230], and congestion level in DTNs [412]. As depicted in Table 13, the majority of these proposals apply diverse supervised learning techniques, mostly for prediction.…”

“…El Khayat et al [238] apply multiple supervised learning techniques for predicting the TCP throughput in a wired network. From the different features used in the learning phase for building the ML models, the authors find that the Timeout Loss Rate (TLR) adds significant improvement in prediction accuracy.…”

Detecting Triangle Inequality Violations in Internet Coordinate Systems by Supervised Learning

“…[13]). However, in our experiments, we did not notice any significant improvement with these methods.…”

“…Unlike previous heuristics-based work, we look for discriminative variables by using supervised learning methods, the use of which has become a trend in the field of networking [12,13]. In particular, we collect training data from popular ICS algorithms such as Vivaldi [5] and extract as many variables of different kinds as possible.…”