Improving Congestion Control Algorithm in Distributed Spaceflight TT&C Networks
Gong Changqing, Bi Xiaoxia, Wang Xiaoyan · 2007
TT&C (tracking, telemetry, and command) networks usually include some wireless links; thus there are many packet losses are due to I ink errors, but not due to network congestion. TCP congestion control algorithm has no means to distinguish these two reasons of packet losses, and often reduces its data rate mistakenly, cannot keep a reasonable data rate. For solving this problem, a quantum neural network classifier is presented in this paper, which can classify packet loss cause over TT&C networks. Based on this classifier, TCP-QNN algorithm is proposed. The result of our simulation shows that the TCP-QNN algorithm is superior to Vegas, Reno and TCP-BP algorithm.