Satellite connections are critical for continuous network connectivity when disasters strike and for remote hosts that cannot use traditional network connections. While satellite Internet bitrates have increased, satellite latencies can still degrade TCP performance. Assessment of TCP over satellite networks is lacking, typically done only by simulation or emulation only, if at all. This paper presents experiments over a commercial satellite network comparing two popular TCP congestion control algorithms: Cubic (the default for most Internet servers) and BBR (recently deployed by Google servers). Analysis of the results shows similar steady-state bitrates for both BBR and Cubic, but with BBR having significantly higher bitrates (and, subsequently, higher round-trip times) than Cubic during start-up.

Materials:

• Paper: pdf
• Slides: pptx

See also:

• Saahil Claypool, Mark Claypool, Jae Chung, and Feng Li. Sharing but not Caring - Performance of TCP BBR and TCP CUBIC at the Network Bottleneck, In Proceedings of the 4th IARIA International Conference on Advances in Computation, Communications and Services (ACCSE), Nice, France, July 28 - August 2, 2019. Online at: http://www.cs.wpi.edu/~claypool/papers/bbr/

• Feng Li, Jae Won Chung, Xiaoxiao Jiang, and Mark Claypool. TCP CUBIC versus BBR on the Highway, In Proceedings of the Passive and Active Measurement Conference (PAM), Berlin, Germany, March 2018. Online at: http://www.cs.wpi.edu/~claypool/papers/driving-bbr/