On the Impact of BER on Realistic TCP Traffic in Satellite Networks

There are many factors governing the performance of TCP-based applications traversing satellite channels. The end-to-end performance of TCP is known to be degraded by the delay, noise and asymmetry inherent in geosynchronous systems. This result has been largely based on experiments that evaluate the performance of TCP in single flow tests. While single flow tests are useful for deriving information on the theoretical behavior of TCP and allow for easy diagnosis of problems, they do not represent a broad range of realistic situations and therefore cannot be used to authoritatively comment on performance issues. The experiments discussed in this report test TCP’s performance in a more dynamic environment with competing traffic flows from hundreds of TCP connections running simultaneously across the satellite channel. Another aspect we investigate is TCP’s reaction to bit errors on satellite channels. TCP interprets loss as a sign of network congestion. This causes TCP to reduce its transmission rate leading to reduced performance when loss is due to corruption. We allowed the bit error rate on our satellite channel to vary and tested the performance of TCP as a function of these bit error rates. Our results show that the average performance of TCP on satellite channels is good even under conditions of loss as high as bit error rates of 10. Network General, [email protected] Ohio UNiversity, [email protected] Ohio University, [email protected] ICSI / ICIR, [email protected]