TCP/AQM Congestion Control in Best-effort and Diff-Serv IP Networks
Network management and control is a complex problem that requires robust, intelligent, control methodologies to obtain satisfactory performance. Active Queue Management (AQM) mechanisms have been introduced for router support to assist the Transmission Control Protocol (TCP) congestion control to better perform than classical TCP/IP based approaches, which rely on implicit network state feedback. The complex, but challenging, concept of TCP/AQM congestion control, in both best-effort and Differentiated Services (Diff-Serv) environments, forms the basis of this research study.
Significant contribution has been made in formulating an effective and generic Active Queue Management (AQM) control methodology, using fuzzy logic based control, toward the solution of congestion control in TCP/IP networks. Specifically, an efficient and effective fuzzy-based nonlinear control law was derived that offers simplicity, and inherent robustness with effective control of the system under widely differing operating conditions, without the need to (re)tune the controller settings. The derived controller is independent of mathematical models of the controlled system, and can be easily adopted in different network environments (best-effort and Diff-Serv architectures were studied, using the same controller for both). Further, through extensive simulative evaluation of the proposed methodology, it is demonstrated that that fuzzy logic based AQM control methodology better handles the nonlinearities of the TCP/IP networks, in contrast with existing, well-known, conventional counterparts.