The Effects of a Performance Enhancing Proxy on TCP Congestion Control over a Satellite Network

Abstract

Satellite networks often use Performance Enhancing Proxies (PEPs) in order to overcome the inherent high latencies that are detrimental to TCP throughputs. Measurements of TCP performance over Satellite PEPs are lacking, both for actual PEP benefits and for interactions between PEPs and TCP congestion control algorithms. This paper presents results from experiments that assess the benefits of a PEP for a commercial satellite network, considering four TCP congestion control algorithms: Cubic, BBR, Hybla and PCC. Without the PEP, the four algorithms have similar steady state throughputs (about 70 Mb/s), but significant differences in start-up throughputs. In particular, the PEP dramatically improves (3x) start-up throughputs for TCP Cubic -the default congestion control algorithm used by most Internet servers. Overall, the PEP equalizes performance irrespective of the TCP congestion control algorithm chosen.