Understanding how new TCP congestion control algorithms interact with the default TCP Cubic over a wide-range of network conditions is important for moving congestion control research forward. Unfortunately, lacking are studies over actual satellite Internet networks where high latencies pose challenges to TCP performance. This paper presents results from experiments over a commercial satellite Internet link assessing TCP congestion control algorithm performance for Cubic when competing with algorithms using four different approaches: loss-based (Cubic), bandwidth-estimation based (BBR), utility function-based (PCC) and satellite optimized (Hybla). Analysis shows: 1) the default Cubic algorithms are fair to each other; 2) Cubic dominates PCC during steady state; 3) Hybla dominates Cubic during start-up; and 4) BBR dominates Cubic during both start-up and steady state.

Download:

• Paper: pdf
• Slides: pptx
• Video: youtube

See also:

• Saahil Claypool, Jae Chung, and Mark Claypool. Comparison of TCP Congestion Control Performance over a Satellite Network, In Proceedings of the Passive and Active Measurement Conference (PAM), Virtual Conference, March 29-31, 2021. Online at: http://www.cs.wpi.edu/~claypool/papers/tcp-sat-pam-21/