Fuzzy logic controller of Random Early Detection based on average queue length and packet loss rate

The utilisation of fuzzy logic (FL) has shown to be useful in designing new active queue management (AQM) methods that can be used to alleviate congestions in wired and wireless networks. In this paper, we propose a FL controller technique based on the traditional random early detection (RED) algorithm to discover the congested router buffer as soon as the congestion occurs in the network. The proposed technique relies on the average queue length and the packet loss rate as input linguistic variables and produces a single output linguistic variable, i.e. the packet dropping probability. We compare the proposed method with the classic RED algorithm in terms of different performance metrics, including packets dropping probability, average queue length, throughput, average queueing delay, and packet loss rate. The simulation results obtained from this comparison revealed that our FL method outperforms RED with reference to average queue length, throughput, packet loss rate and packet dropping probability function. In addition, our method provides average queueing delay results similar to that of RED. Finally, the performance measures results of the proposed method is not impacted with the traffic load states (high or low), whereas, REDpsilas results get impacted when the traffic load becomes high.

[1]  James Aweya,et al.  A control theoretic approach to active queue management , 2001, Comput. Networks.

[2]  Serge Fdida,et al.  Comparison of tail drop and active queue management performance for bulk-data and Web-like Internet traffic , 2001, Proceedings. Sixth IEEE Symposium on Computers and Communications.

[3]  Michael Welzl,et al.  Network Congestion Control - Managing Internet Traffic , 2005 .

[4]  David L. Black,et al.  The Addition of Explicit Congestion Notification (ECN) to IP , 2001, RFC.

[5]  M. E. Woodward,et al.  Communication and computer networks - modelling with discrete-time queues , 1993 .

[6]  Wu-chang Fengy,et al.  BLUE: A New Class of Active Queue Management Algorithms , 1999 .

[7]  Andreas Pitsillides,et al.  Fuzzy logic controlled RED: congestion control in TCP/IP differentiated services networks , 2003, Soft Comput..

[8]  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).

[9]  Lotfi A. Zadeh,et al.  Fuzzy Logic , 2009, Encyclopedia of Complexity and Systems Science.

[10]  W. Richard Stevens,et al.  TCP Slow Start, Congestion Avoidance, Fast Retransmit, and Fast Recovery Algorithms , 1997, RFC.

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

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

[13]  Robert Tappan Morris,et al.  Dynamics of random early detection , 1997, SIGCOMM '97.

[14]  Nils J. Nilsson,et al.  Artificial Intelligence , 1974, IFIP Congress.

[15]  Kang G. Shin,et al.  The BLUE active queue management algorithms , 2002, TNET.

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

[17]  Sumit Ghosh,et al.  A survey of recent advances in fuzzy logic in telecommunications networks and new challenges , 1998, IEEE Trans. Fuzzy Syst..

[18]  M. Black.  Vagueness. An Exercise in Logical Analysis , 1937, Philosophy of Science.

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