Fuzzy logic congestion control in TCP/IP differentiated services networks for quality of service provisioning
Date
2004Author
Chrysostomou, Chrysostomos
Pitsillides, Andreas
Hadjipollas, George
Sekercioglu, Y. Ahmet
Polycarpou, Marios M.
ISBN
0-7803-8482-2Source
Proceedings - 2004 International Conference on Information and Communication Technologies: From Theory to Applications, ICTTA 2004Proceedings - 2004 International Conference on Information and Communication Technologies: From Theory to Applications, ICTTA 2004
Pages
373-374Google Scholar check
Keyword(s):
Metadata
Show full item recordAbstract
A two class Fuzzy Explicit Marking (FEM) controller was designed and used in Differentiated Services Networks for quality of service provisioning. The fuzzy control system is designed to regulate the queues of IP routers by achieving a specified desired target queue length (TQL), in order to maintain high utilization and low mean delay. The performance of active queue management (AQM) schemes were examined under dynamic traffic changes, by providing some time-varying dynamics. Simulative results shows that FEM-In/Out (FIO) outperforms Random Early Detection (RED) In/Out (RIO) in achieving higher utilization, lower packet losses, with a better differentiation between the best-effort and assured classes of service.