FAFC: fast adaptive fuzzy AQM controller for TCP/IP networks

Recently, many active queue management (AQM) algorithms have been proposed to address performance degradations of end-to-end congestion control. However, these AQM algorithms present weaknesses for stabilizing delays in heavily loaded networks. In this paper, we describe a novel adaptive fuzzy control algorithm to improve best effort TCP/IP networks performance. Compared to traditional AQM algorithms (RED, PID and others), our proposal avoids buffer overflows/underflows, and minimizes packet dropping. We propose an on-line adaptation mechanism that captures fluctuating network conditions, while classical AQM algorithms require static tuning. The algorithm stability is mathematically proven. Simulation results show that for the same link utilization, our fast adaptive fuzzy controller provides better performance than RED and PID.

[1]  Srinivasan Keshav.  Congestion control in computer networks , 1991 .

[2]  Hiroyuki Ohsaki,et al.  Steady State Analysis of the RED Gateway: Stability, Transient Behavior, and Parameter Setting , 2002 .

[3]  Liu Bao-hong,et al.  Design of a robust active queue management algorithm based on feedback compensation , 2003, SIGCOMM 2003.

[4]  Sally Floyd,et al.  Promoting the use of end-to-end congestion control in the Internet , 1999, TNET.

[5]  Seungwan Ryu,et al.  A predictive and robust active queue management for Internet congestion control , 2003, Proceedings of the Eighth IEEE Symposium on Computers and Communications. ISCC 2003.

[6]  Srinivasan Keshav.  A control-theoretic approach to flow control , 1991, SIGCOMM 1991.

[7]  Chunming Qiao,et al.  Advances in internet congestion control , 2003, IEEE Communications Surveys & Tutorials.

[8]  Kevin Jeffay,et al.  The effects of active queue management on web performance , 2003, SIGCOMM '03.

[9]  Lin Chuang,et al.  Design a PID controller for active queue management , 2003, Proceedings of the Eighth IEEE Symposium on Computers and Communications. ISCC 2003.

[10]  B. Barden.  Recommendations on queue management and congestion avoidance in the Internet , 1998 .

[11]  Stephen Yurkovich,et al.  Fuzzy Control , 1997 .

[12]  Frank Kelly,et al.  Mathematical modeling of the Internet , 1999 .

[13]  Sammy Chan,et al.  PD-controller: a new active queue management scheme , 2003, GLOBECOM '03. IEEE Global Telecommunications Conference (IEEE Cat. No.03CH37489).

[14]  Richard J. La,et al.  Analysis of adaptive random early detection (ARED) , 2003 .

[15]  H. T. Kung,et al.  Internet congestion control: cooperative end-system and gateway algorithms , 1998 .

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

[17]  Yuan Gao,et al.  Variable structure control in active queue management for TCP with ECN , 2003, Proceedings of the Eighth IEEE Symposium on Computers and Communications. ISCC 2003.

[18]  M. Jamshidi.  Large-Scale Systems: Modeling, Control and Fuzzy Logic , 1996 .

[19]  Mathieu Robin,et al.  A Comparative Study of Active Queue Management Schemes , 2004 .

[20]  Wenhua Dou,et al.  Design of a robust active queue management algorithm based on feedback compensation , 2003, SIGCOMM '03.

[21]  Jon Crowcroft,et al.  Differentiated end-to-end Internet services using a weighted proportional fair sharing TCP , 1998, CCRV.