Active queue management algorithm based on data-driven predictive control

In this paper, we propose a novel active queue management (AQM) algorithm based on data-driven predictive control for Internet system with large delay, complex change and bad disturbance, called Data-AQM. The data-driven predictive control algorithm elegantly combines data-driven subspace identification and predictive control. For its inherent characteristics, data-driven predictive controller can be obtained directly based on the input-output data alone and does not require any explicit model of the system. According to the input-output data, the future queue length in data buffer, which is the basis of optimizing drop probability, is predicted. Furthermore, considering system constraints, the control requirement is converted to the optimal control objective, then the drop probability is obtained by solving the optimal problem online. Finally, the performances of Data-AQM are evaluated through a series of simulations. The simulation results show that Data-AQM algorithm is superior to random early detection (RED) algorithm in terms of stability and robustness.

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

[2]  Bart De Moor,et al.  A unifying theorem for three subspace system identification algorithms , 1995, Autom..

[3]  Van Jacobson,et al.  Random early detection gateways for congestion avoidance , 1993, TNET.

[4]  James B. Rawlings,et al.  Tutorial overview of model predictive control , 2000 .

[5]  Vishal Misra,et al.  Fluid-based analysis of a network of AQM routers supporting TCP flows with an application to RED , 2000, SIGCOMM 2000.

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

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

[8]  Hoseinali Borhan,et al.  A Robust Design Optimization Framework for Systematic Model-Based Calibration of Engine Control Systems , 2014 .

[9]  Biao Huang,et al.  A data driven subspace approach to predictive controller design , 2001 .

[10]  Shan Xiuming,et al.  Design of a fuzzy controller for active queue management , 2002 .

[11]  Hong Chen,et al.  Design and analysis of a model predictive controller for active queue management. , 2012, ISA transactions.

[12]  Anindo Banerjea,et al.  The Tenet real-time protocol suite: design, implementation, and experiences , 1996, TNET.

[13]  Ki Baek Kim.  Design of feedback controls supporting TCP based on the state-space approach , 2006, IEEE Trans. Autom. Control..

[14]  Ping Wang,et al.  Design of a Data-Driven Predictive Controller for Start-up Process of AMT Vehicles , 2011, IEEE Transactions on Neural Networks.

[15]  Amir Hossein Jahangir,et al.  AQM controller design for TCP networks based on a new control strategy , 2014, Telecommun. Syst..

[16]  David D. Clark,et al.  Explicit allocation of best-effort packet delivery service , 1998, TNET.

[17]  Hong Chen,et al.  Field programmable gate array/system on a programmable chip-based implementation of model predictive controller , 2012 .

[18]  Hiroyuki Ohsaki,et al.  On control parameters tuning for active queue management mechanisms using multivariate analysis , 2003, 2003 Symposium on Applications and the Internet, 2003. Proceedings..

[19]  Yunhao Liu,et al.  A robust proportional controller for AQM based on optimized second-order system model , 2008, Comput. Commun..