Fuzzy RED: congestion control for TCP/IP Diff-Serv
R. Loukas, Sebastian Köhler, P. Andreas, Tran-Gia Phuoc · 2002
Network congestion control remains a critical issue and a high priority. The explosion of the Internet made the use of effective congestion control algorithms a necessity. The fact that the Internet relies mainly on the TCP/IP protocol suggests that we must focus our efforts in this area. The existing TCP/IP protocol was designed for best effort services and can not support efficiently new user demands for integrated services. Currently we see new proposed Internet architectures to deal with integrated services networks (e.g. Int-Serv, Diff-Serv). The design of effective congestion control strategies for integrated services networks is known to be difficult because of their structural complexity, the nature of services supported, and the variety of dynamic parameters involved. As a result, a number of researchers are now looking at alternative non-analytical control system design and modeling schemes that have the ability to cope with these difficulties in order to devise effective, robust congestion control techniques as an alternative (or supplement) to traditional control approaches. We study congestion control issues in TCP/IP Diff-Serv and present a novel congestion algorithm that uses fuzzy logic based control theory.