Machine-Learned Recognition of Network Traffic for Optimization through Protocol Selection

We introduce optimization through protocol selection (OPS) as a technique to improve bulk-data transfer on shared wide-area networks (WANs). Instead of just fine-tuning the parameters network protocol, our empirical results show that itself can result in up four times higher throughput some key cases. However, OPS for foreground traffic (e.g., TCP CUBIC, BBR, UDT) depends knowledge about protocols used by background (i.e., other users). Therefore, we build and empirically evaluate several machine-learned (ML) classifiers, trained local round-trip time (RTT) time-series data gathered using active probing, recognize mix with an accuracy 0.96.