On designing improved controllers for AQM routers supporting TCP flows

By Christopher V. Hollot, Vishal Misra, D. Towsley, W. Gong. Proceedings IEEE INFOCOM 2001. Conference on Computer Communications. Twentieth Annual Joint Conference of the IEEE Computer and Communications Society (Cat. No.01CH37213), 2001

1,068 citations recorded by the source corpus.

In this paper we study a previously developed linearized model of TCP and active queue management (AQM). We use classical control system techniques to develop controllers well suited for the application. The controllers are shown to have better theoretical properties than the well known RED controller. We present guidelines for designing stable controllers subject to network parameters like load level propagation delay etc. We also present simple implementation techniques which require a minimal change to RED implementations. The performance of the controllers are verified and compared with RED using ns simulations. The second of our designs, the proportional integral (PI) controller is shown to outperform RED significantly.

Subfields: Computer Networks and Communications, Management Information Systems

View Paper: https://www.semanticscholar.org/paper/0fa235ece12124d8bc60af5e32bd04d82b23b672

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

In Management Information Systems

Citations in the corpus

Internet congestion control (2002, methodology): “Another link algorithm, proposed in [45] and [46], is”
The BLUE active queue management algorithms (2002, background): “Subsequent algorithms [1], [17], [20] have also shown the benefits of decoupling queue length from congestion management.”
REM: active queue management (2001, background): “Recently, a proportional-plus-integral (PI) controller was proposed in [ 11 ] as an alternative active queue management scheme to RED, and simulation results were presented to demonstrate its superior equilibrium and transient performance.”
Host-to-Host Congestion Control for TCP (2010, background): “(differentiated services [35], [36]) and internally reschedules packets in its queue (active queue management [37], [38]).”
PIE: A lightweight control scheme to address the bufferbloat problem (2013, background): “Active queue management (AQM) schemes, such as RED [3], BLUE [4], PI [5], AVQ [6], etc, have been around for well over a decade.”
The war between mice and elephants (2001, background): “For example, RED with PI control [34] can be used for long ﬂows since the controller was designed specially for long-lived connections.”
Data center TCP (DCTCP) (2010, methodology): “AQM is not enough: Before designing DCTCP, we evaluated Active Queue Management (AQM) schemes like RED 5 and PI [17] that do not modify TCP’s congestion control mechanism.”
Real Time Scheduling Theory: A Historical Perspective (2004, neutral): “Successful control schemes were developed for high-performance servers [71, 79, 151], multimedia streaming [164, 228], real-time databases [12], web storage systems [144], network routers [110, 63], active queue management schemes [98, 99], and processor architecture [204] to name a few.”
Analysis and design of an adaptive virtual queue (AVQ) algorithm for active queue management (2001, methodology): “Using a mathematical tool motivated by the earlier work of Hollot et al,we present a simple rule to design the parameters of the AVQ algorithm.”
Dynamics of TCP/RED and a scalable control (2002, background): “The same stability analysis can also be applied to other AQMs, such as Virtual Queue [16], [17], [18] and REM/PI [19], [6], and clarifies the role of AQM.”
Analysis and design of controllers for AQM routers supporting TCP flows (2002, background): “This paper is an extended version of work appearing in [19] and [20].”
Network Optimization and Control (2008, neutral): “[84] and Kunniyur and Srikant [85].”