Stable Queue Management in communication networks. (April 2015)

• Record Type: Journal Article
• Authors: Pourmohammad, Sajjad; Fekih, Afef; Perkins, Dmitri
• Is Part Of: Control engineering practice. Volume 37(2015)
• Page Start: 67
• Page End: 79
• Publication Date: 2015-04
• Subjects: Queue Management -- Congestion control -- Feedback control; Automatic control -- Periodicals; 629.89
• DOI: 10.1016/j.conengprac.2015.01.001
• Languages: English
• ISSNs: 0967-0661

Abstract

Abstract: Since Active Queue Management (AQM) was recommended by the Internet Engineering Task Force (IETF) as an efficient way to overcome performance limitations of Transmission Control Protocol (TCP), several studies have proven control theory to be a promising field for the design and analysis of congestion control in homogenous communication networks. AQM is gaining increased importance due to reports of buffer-induced latencies throughout the Internet. The increasing volume and diversity of traffic types (i.e., data, voice, and video) suggests that traffic management mechanisms, in general, and AQM schemes, specifically, must not only focus on the critical issue of congestion control but must also consider the QoS demands of heterogeneous traffic. However, to combine quality-of-service provisioning with congestion control, AQM design needs to be reconsidered. In this paper, we propose a state feedback controller design scheme for heterogeneous networks preserving the closed-loop system stability. Delay dependant stability conditions of the closed loop system are derived based on the Lyapunov-Krasovskii method. The proposed approach offers flexible choice of control parameters allowing the network administrator to control fairness and response time for each individual source node in a network of multiple links with different delay properties. The performance and robustness of the proposed controller were illustrated and analyzed using event-based computer simulations. Highlights: A Stable Queue Management scheme based on optimal feedback control theory. Considering realistic heterogeneous network configurations with different link properties. Proof of close-loop stability of the system using the Lyapunov–Krasovskii method. QoS settings are included in the controller design besides congestion control. Improved performance, fairness and robustness.