Title :
A Dynamic Probability Mark Method of Congestion Control Based on Explicit Feedback
Author :
Jia, Lin ; Hu, Weihua
Author_Institution :
Comput. Sci., Hangzhou Dianzi Univ., Hangzhou, China
Abstract :
With the rapid development of network technology, computer network evolved to the mobile wireless Internet gradually, and showing a highly heterogeneous trend. The traditional TCP protocol is designed for wire circumstance and is obviously poor in such circumstance. This paper proposes a new TCP scheme, called TCP-C, which is based on Explicit Congestion Notification algorithm ( ECN), referencing the idea of bandwidth estimation algorithm in TCP Westwood, adopting fuzzy control theory to mark the packets with nonlinear and dynamical. Combining the advantages of designed ideas of ECN and TCP Westwood, the modified protocol can be more accurately response to congestion status or impending congestion status, and NS-2 simulation shows that the performance is superior to TCP Reno and other similar protocols.
Keywords :
feedback; fuzzy control; nonlinear control systems; probability; telecommunication congestion control; transport protocols; ECN; NS-2 simulation; TCP Reno; TCP Westwood; TCP protocol; TCP-C scheme; bandwidth estimation algorithm; computer network; congestion control; dynamic probability mark method; explicit congestion notification algorithm; explicit feedback; fuzzy control theory; mobile wireless Internet; network technology; Bandwidth; Estimation; Heuristic algorithms; Internet; Protocols; Throughput; Wireless communication; bandwidth estimation; congestion control; explicit feedback; fuzzy control theory;
Conference_Titel :
Networking and Distributed Computing (ICNDC), 2010 First International Conference on
Conference_Location :
Hangzhou
Print_ISBN :
978-1-4244-8382-2
DOI :
10.1109/ICNDC.2010.37