A stable adaptive PI controller for AQM

Active queue management (AQM) mechanisms have been proposed to support end-to-end congestion control mechanisms of transmission control protocol (TCP) in TCP/IP networks. This paper introduces a new AQM based on a stable adaptive proportional-integral (SAPI) controller. SAPI adaptively adjusts the PI controller parameters based on estimated network parameters to improve the transient performance of a fixed-gain PI controller. We present the SAPI scheme in detail, and provide guidelines for the selection of its parameters. Through extensive simulations, we demonstrate that SAPI maintains satisfactory transient and steady-state performance independent of traffic loads, round trip propagation delay, and bottleneck capacity. The simulation results also demonstrate that SAPI is robust to non-responsive UDP traffic and HTTP traffic, and it is effective for networks with multiple bottlenecks. Comparison with other well-known AQM algorithms like PI, REM and Q-SAPI shows that SAPI achieves faster convergence to queue length target and smaller queue length jitter.

[1]  Christophe Diot,et al.  Reasons not to deploy RED , 1999, 1999 Seventh International Workshop on Quality of Service. IWQoS'99. (Cat. No.98EX354).

[2]  Donald F. Towsley,et al.  A self-tuning structure for adaptation in TCP/AQM networks , 2003, SIGMETRICS '03.

[3]  T. V. Lakshman,et al.  SRED: stabilized RED , 1999, IEEE INFOCOM '99. Conference on Computer Communications. Proceedings. Eighteenth Annual Joint Conference of the IEEE Computer and Communications Societies. The Future is Now (Cat. No.99CH36320).

[4]  Donald F. Towsley,et al.  On designing improved controllers for AQM routers supporting TCP flows , 2001, Proceedings IEEE INFOCOM 2001. Conference on Computer Communications. Twentieth Annual Joint Conference of the IEEE Computer and Communications Society (Cat. No.01CH37213).

[5]  Oliver W. W. Yang,et al.  Self-tuning PI TCP flow controller for AQM routers with interval gain and phase margin assignment , 2004, IEEE Global Telecommunications Conference, 2004. GLOBECOM '04..

[6]  Moshe Zukerman,et al.  QoS in best-effort networks , 2002, IEEE Commun. Mag..

[7]  Donald F. Towsley,et al.  Analysis and design of controllers for AQM routers supporting TCP flows , 2002, IEEE Trans. Autom. Control..

[8]  Moshe Zukerman,et al.  RaQ: A robust active queue management scheme based on rate and queue length , 2007, Comput. Commun..

[9]  Sally Floyd,et al.  Adaptive RED: An Algorithm for Increasing the Robustness of RED's Active Queue Management , 2001 .

[10]  Donald F. Towsley,et al.  Modeling TCP Reno performance: a simple model and its empirical validation , 2000, TNET.

[11]  Yue-Dong Xu,et al.  Nonlinear PI active queue management based on hyperbolic secant functions , 2005, 2005 International Conference on Machine Learning and Cybernetics.

[12]  Steven H. Low,et al.  REM: active queue management , 2001, IEEE Netw..

[13]  Li Qing,et al.  Designing Adaptive PI Algorithm Based on Single Neuron , 2005, ICCNMC.

[14]  David Ott,et al.  Tuning RED for Web traffic , 2000, SIGCOMM.

[15]  QUTdN QeO,et al.  Random early detection gateways for congestion avoidance , 1993, TNET.

[16]  Bo Li,et al.  API: adaptive proportional-integral algorithm for active queue management under dynamic environments , 2004, 2004 Workshop on High Performance Switching and Routing, 2004. HPSR..

[17]  Sammy Chan,et al.  PD-RED: to improve the performance of RED , 2003, IEEE Communications Letters.

[18]  Oliver W. W. Yang,et al.  On designing self-tuning controllers for AQM routers supporting TCP flows based on pole placement , 2004, IEEE Journal on Selected Areas in Communications.

[19]  Deborah Estrin,et al.  Recommendations on Queue Management and Congestion Avoidance in the Internet , 1998, RFC.

[20]  Xiaolin Chang,et al.  A stable queue-based adaptive controller for improving AQM performance , 2006, Comput. Networks.

[21]  Jen-te Yu,et al.  A robust nonlinear PI controller for improving AQM performance , 2004, 2004 IEEE International Conference on Communications (IEEE Cat. No.04CH37577).