Improving the start-up behavior of a congestion control scheme for TCP
Conference proceedings on Applications, technologies, architectures, and protocols for computer communications
Improving TCP performance over wireless networks at the link layer
Mobile Networks and Applications
Improving TCP performance over mobile networks
ACM Computing Surveys (CSUR)
TCP westwood: end-to-end congestion control for wired/wireless networks
Wireless Networks
FSKD'09 Proceedings of the 6th international conference on Fuzzy systems and knowledge discovery - Volume 3
Performance evaluation of TCP connections in ideal and non-ideal network environments
Computer Communications
TCP Veno: TCP enhancement for transmission over wireless access networks
IEEE Journal on Selected Areas in Communications
TCP-Jersey for wireless IP communications
IEEE Journal on Selected Areas in Communications
JTCP: jitter-based TCP for heterogeneous wireless networks
IEEE Journal on Selected Areas in Communications
Hi-index | 0.00 |
While modern wireless networks have been in development for a couple of decades, the Transmission Control Protocol (TCP) which runs over those networks has existed since the mid 1970s. As it was developed before wireless networks were even conceived, TCP was not optimized to consider the physical characteristics of wireless links. Specifically, TCP responds to packet loss due to link errors in the same way it responds to packet loss due to congestion: it cuts back the rate at which traffic is sent. A means of improving performance of TCP over wireless links is to classify packet losses, and react only to those losses perceived as being caused by network congestion. There is a demonstrated applicability of fuzzy inference in solving problems that are difficult to stochastically model or analyze. Fuzzy inference systems allow problems to be defined intuitively using a propositional IF THEN rule base. In this paper, we use environmental variables available to TCP implementations to feed a fuzzy inference system that classifies packet loss due to congestion or wireless problem without sacrificing the end-to-end reliability of TCP. Using the network simulator ns-3 we demonstrate that our TCP+FUZZY Classifier implementation performs better than de facto TCP implementations on the Internet while maintaining TCP-friendliness property.