ECSE Departmental Research Seminar, 16th January 2006

Abstract:

Network management and control is a complex problem that requires robust, possibly intelligent, control methodologies to obtain satisfactory performance. Active Queue Management (AQM) mechanisms have been introduced to assist the TCP congestion control. We briefly discuss the modelling and control approach followed by a number of representative AQM schemes, and address possible limitations to meet the diverse needs of today's Internet. Fuzzy Logic Control is adopted due to its reported strength in controlling non-linear systems using linguistic information. Emphasis is given towards the ability of effectively controlling the congestion in TCP/IP networks. The talk will mainly focus on differentiated services. The provision of quality of service (QoS) in a differentiated services (Diff-Serv) environment requires an adequate differentiation between high-priority/assured and low-priority/best-effort classes of service in the presence of congestion, giving priority/preference to assured-tagged traffic. For this purpose, a new active queue management scheme, implemented within the Diff-Serv framework, is presented that provides congestion control in TCP/IP networks using a fuzzy logic control approach. The proposed fuzzy logic approach for congestion control allows the use of linguistic knowledge to capture the dynamics of nonlinear probability marking functions, uses multiple inputs to capture the dynamic state of the network more accurately, and can offer effective implementation. A simulation study over a wide range of traffic conditions - considering multiple bottleneck links - shows that the fuzzy logic based controller outperforms the Random Early Detection (RED) implementation for Diff-Serv in terms of link utilization, packet losses, and queue fluctuations and delays. Also, the proposed scheme can offer better differentiation among assured and best-effort traffic, thus it can provide better QoS to different types of data streams, such as TCP/FTP traffic or TCP/Web-like traffic, whilst maintaining high utilization.

About the speaker:

Andreas Pitsillides, Associate Professor of Computer Science, University of Cyprus (UCY), spent 6 years in industry and 18 years in academia (7 with Swinburne University of Technology, Melbourne, Australia). Serves as Chairman of the Cyprus Research and Academic Network (CYNET). Andreas heads the Networks Group. His research interests include fixed and mobile/wireless networks, Internet technologies and their application in Mobile e-Services, especially e-health. He has a particular interest in adapting tools from various fields of applied mathematics such as control theory, and computational intelligence to solve problems in computer networks. Published over 120 referred journal, conference papers and book chapters, participates in numerous EC and locally funded research projects, presented invited lectures at major research organisations, short courses at international conferences and short courses to industry. Regularly serves on international conference executive committees (e.g. INFOCOM 2001-2003, and ICT98), general chair, technical committees, guest co-editor, invited speaker, and as a regular reviewer for conference and journal submissions. Andreas is also a member of the International Federation of Automatic Control (IFAC) Technical Committee (TC) on Networked Systems and the IFIP working group WG 6.3. (http://www.cs.ucy.ac.cy/networksgroup). He serves on the editorial board of the Journal of Computer Networks (COMNET).

.