GA-PSO-Optimized Neural-Based Control Scheme for Adaptive Congestion Control to Improve Performance in Multimedia Applications

Majlesi Journal of Electrical Engineering

مقاله 2، دوره 6، شماره 1، خرداد 2012   

نوع مقاله: Review Article

نویسندگان

Mansour Sheikhan^{* 1}؛ Ehsan Hemmati²؛ Reza Shahnazi³

¹Department of Communication Engineering, South Tehran Branch, Islamic Azad University, Tehran, Iran

²Department of Electronic Engineering, South Tehran Branch, Islamic Azad University, Tehran, Iran

³Modeling and Optimization Research Center in Science and Engineering, South Tehran Branch, Tehran, Islamic Azad University, Iran

چکیده

Active queue control aims to improve the overall communication network throughput, while providing lower delay and small packet loss rate. The basic idea is to actively trigger packet dropping (or marking provided by explicit congestion notification (ECN)) before buffer overflow. In this paper, two artificial neural networks (ANN)-based control schemes are proposed for adaptive queue control in TCP communication networks. The structure of these controllers is optimized using genetic algorithm (GA) and the output weights of ANNs are optimized using particle swarm optimization (PSO) algorithm. The controllers are radial bias function (RBF)-based, but to improve the robustness of RBF controller, an error-integral term is added to RBF equation in the second scheme.  Experimental results show that GA- PSO-optimized improved RBF (I-RBF) model controls network congestion effectively in terms of link utilization with a low packet loss rate and outperforms Drop Tail, proportional-integral (PI), random exponential marking (REM), and adaptive random early detection (ARED) controllers.

کلیدواژه‌ها

IAU-South Tehran Branch؛ en

مراجع

[1] B. Braden, D. Clark, J. Crowcroft, B. Davie, S. Deering, and D. Estrin, et al., “Recommendations on queue management and congestion avoidance in the Internet”, IETF RFC2309, Apr. 1998 (http://www.rfc.net/rfc2309.html).

[2] W. Zhang, L. Tan, and G. Peng, “Dynamic queue level control of TCP/RED systems in AQM routers”, Computers & Electrical Engineering, Vol. 35, Iss. 1, pp. 59-70, 2009.

[3] L. Yu, M. Ma, W. Hu, Z. Shi, and Y. Shu, “Design of parameter tunable robust controller for active queue management based on H∞ control theory”, J. Network and Computer Applications, Vol. 34, Iss. 2, pp. 750-764, 2011.

[4] S. Floyd, and V. Jacobson, “Random early detection gateways for congestion avoidance”, IEEE/ACM Trans. Networking, Vol. 1, Iss. 4, pp. 397-413, 1993.

[5] D. Lin, and R. Morris, “Dynamics of random early detection”, In: Proc. ACM SIGCOM, pp. 127-137, 1997.

[6] W. Feng, D.D. Kandlur, D. Saha, and K.G. Shin, “A self-configuring RED gateway”, In: Proc. IEEE INFOCOM, pp. 1320-1328, 1999.

[7] S. Floyd, R. Gummadi, and S. Shenker, “Adaptive RED: a algorithm for increasing the robustness of RED’s active queue management”, 2001 (http://www.icir.org/floyd/papers/adaptiveRed.pdf).

[8] F. Anjum, and L. Tassiulas, “Fair bandwidth sharing among adaptive and non-adaptive flows in the Internet”, In: Proc. IEEE INFOCOM, pp. 1412-1420, 1999.

[9] T.J. Qtt, T.V. Lakshman, L. Wong, “SRED: stabilized RED”, In: Proc. IEEE INFOCOM, pp. 1346-1355, 1999.

[10] J. Aweya, M. Ouellette, D.Y. Montuno, and A. Chapman, “A control theoretic approach to active queue management”, Computer Networks, Vol. 36, Iss. 2-3, pp. 203-235, 2001.

[11] M. Nabeshima, “Improving the performance of active buffer management with per-flow information”, IEEE Commun. Lett., Vol. 6, Iss. 7, pp. 306-308, 2002.

[12] S. Liu, T. Başar, and R. Srikant, “Exponential-RED: a stabilizing AQM scheme for low- and high-speed TCP protocol”, IEEE/ACM Trans. Networking, Vol. 13, Iss. 5, pp. 1068-1081, 2005.

[13] B. Hariri, and N. Sadati, “NN-RED: an AQM mechanism based on neural networks”, Electronics Letters, Vol. 43, Iss. 19, pp. 1053-1055, 2007.

[14] N. Xiong, L.T. Yang, Y. Yang, X. Defago, and Y. He, “A novel numerical algorithm based on self-tuning controller to support TCP flows”, Mathematics and Computers in Simulation, Vol. 79, Iss. 4, pp. 1178-1188, 2008.

[15] S. Jinsheng, C. Guanrong, and M. Zukerman, “PD-RED: to improve the performance of RED”, IEEE Commun. Lett., Vol. 7, Iss. 8, pp. 406-408, 2003.

[16] N. Xiong, A.V. Vasilakos, L.T. Yang, C-X. Wang, R. Kannan, C-C. Chang, and Y. Pan, “A novel self-tuning feedback controller for active queue management supporting TCP flows”, Information Sciences, Vol. 180, Iss. 11, pp. 2249-2263, 2010.

[17] C. Zhang, J. Yin, Z. Cai, and W. Chen, “RRED: robust RED algorithm to counter low-rate denial-of-service attacks”, IEEE Commun. Lett., Vol. 14, Iss. 5, pp. 489-491, 2010.

[18] S. Kunniyur, and R. Srikant, “Analysis and design of an adaptive virtual queue (AVQ) algorithm for active queue management”, In: Proc. ACM SIGCOMM, pp. 123-134, 2001.

[19] S. Athuraliya, S.H. Low, V.H. Li, and Q. Yin, “REM: active queue management”, IEEE Network, Vol. 15, Iss. 3, pp. 48-53, 2001.

[20] W. Feng, K.G. Shin, D.D. Kandlur, and D. Saha, “The BLUE active queue management algorithms”, IEEE/ACM Trans. Networking, Vol. 10, Iss. 4, pp. 513-528, 2002.

[21] W-C. Feng, A. Kapadia, and S. Thulasidasan, “GREEN: proactive queue management over a best-effort network”, In: Proc. IEEE GLOBECOM, pp. 1774-1778, 2002.

[22] C. Long, B. Zhao, X. Guan, and J. Yang, “The YELLOW queue management algorithm”, Computer Networks, Vol. 47, Iss. 4, pp. 525-550, 2005.

[23] Y. Li, K.T. Ko, and G. Chen, “A Smith predictor-based PI-controller for active queue management”, IEICE Trans. Commun., Vol. 88, Iss. 11, pp. 4293-4300, 2005.

[24] K.B. Kim, and S.H. Low, “Analysis and design of AQM based on state-space models for stabilizing TCP”, In: Proc. American Control Conf., pp. 260-265, 2003.

[25] C-K. Chen, H-H. Kuo, J-J. Yan, and T-L. Liao, “GA-based PID active queue management control design for a class of TCP communication networks”, Expert Systems with Applications, Vol. 36, Iss. 2, pp. 1903-1913, 2009.

[26] R. Fengyuan, L. Chuang, Y. Xunhe, S. Xiuming, and W. Fubao, “A robust active queue management algorithm based on sliding mode variable structure control”, In: Proc. IEEE INFOCOM, pp. 13-20, 2002.

[27] X. Guan, B. Yang, B. Zhao, G. Feng, and C. Chen, “Adaptive fuzzy sliding mode active queue management algorithms”, Telecommunication Systems, Vol. 35, Iss. 1-2, pp. 21-42, 2007.

[28] M.M. de A.E. Lima, N.L.S. de Fonseca, and J.C. Geromel, “An optimal active queue management controller”, In: Proc. IEEE Int. Conf. Communications, pp. 2261-2266, 2004.

[29] P. Zhang, C-Q. Ye, X-Y. Ma, Y-H. Chen, and X. Li, “Using Lyapunov function to design optimal controller for AQM routers”, J. Zhejiang University Science A, Vol. 8, Iss. 1, pp. 113-118, 2007.

[30] E.C. Park, H. Lim, K.J. Park, and C.H. Choi, “Analysis and design of the virtual rate control algorithm for stabilizing queues in TCP networks”, Computer Networks, Vol. 44, Iss. 1, pp. 17-41, 2004.

[31] M. Farokhian Firuzi, and M. Haeri, “Active queue management in TCP networks based on self tuning control approach”, In: Proc. IEEE Conf. Control Applications, pp. 904-909, 2005.

[32] Z. Na, Q. Guo, Z. Gao, J. Zhen, and C. Wang, “A novel adaptive traffic prediction AQM algorithm”, Telecommunication Systems, Online First: 17 June 2010 (doi: 10.1007/s11235-010-9359-2).

[33] C-K. Chen, Y-C. Hung, T-L Liao, and J-J. Yan, “Design of robust active queue management controllers for a class of TCP communication networks”, Information Sciences, Vol. 177, Iss. 19, pp. 4059-4071, 2007.

[34] W. Liu, S. Zhang, M. Zhang, and T. Liu, “A fuzzy-logic control algorithm for active queue management in IP networks”, J. Electronics (China), Vol.25, Iss. 1, pp. 102-107, 2008.

[35] G. Di Fatta, G.L. Re, and A. Urso, “A fuzzy approach for the network congestion problem”, Lecture Notes in Computer Science, Vol. 2329, pp. 286-295, 2002.

[36] R. Rahmani, T. Kanter, and C. Åhlund, “A self configuring fuzzy active queue management controller in heterogeneous networks”, In: Proc. Int. Conf. Telecommunications, pp. 634-641, 2010.

[37] S.M. Mahdi Alavi, and M.J. Hayes, “Robust active queue management design: a loop-shaping approach”, Computer Communications, Vol. 32, Iss. 2, pp. 324-331, 2009.

[38] N. Bigdeli, and M. Haeri, “Predictive functional control for active queue management in congested TCP/IP networks”, ISA Transactions, Vol. 48, Iss. 1, pp. 107-121, 2009.

[39] C-K. Chen, T-L. Liao, and J-J. Yan, “Active queue management controller design for TCP communication networks: variable structure control approach”, Chaos, Solitons & Fractals, Vol. 40, Iss. 1, pp. 227-285, 2009.

[40] K. Rahnami, P. Arabshahi, and A. Gray, “Neural network based model reference controller for active queue management of TCP flows”, In: Proc. IEEE Int. Conf. Aerospace, pp. 1696-1704, 2005.

[41] H.C. Cho, S.M. Fadali, and H. Lee, “Adaptive neural queue management for TCP networks”, Computers & Electrical Engineering, Vol. 34, Iss. 6, pp. 447-469, 2008.

[42] E. Lochin, and B. Talavera, “Managing Internet routers congested links with a Kohonen-RED queue”, Engineering Applications of Artificial Intelligence, Vol. 24, Iss. 1, pp. 77-86, 2011.

[43] X. Wang, Y. Wang, H. Zhou, and X. Huai, “PSO-PID: a novel controller for AQM routers”, In: Proc. IEEE/IFIP WOCN, pp. 1-5, 2006.

[44] D.E. Goldberg, Genetic Algorithms in Search, Optimization and Learning, Addison Wesley, 1989.

[45] M. Chen, and Z. Yao, “Classification techniques of neural networks using improved genetic algorithm”, In: Proc. IEEE Int. Conf. Genetic and Evolutionary Computing, pp. 115-119, 2008.

[46] Y. Shi, and R. Eberhart, “Parameter selection in particle swarm optimization”, In: Proc. Int. Conf. Evolutionary Programming, pp. 591-601, 1998.

[47] C. Hollot, V. Misra, D. Towsley, and W.B. Gong, “Analysis and design of controllers for AQM routers supporting TCP flows”, IEEE Trans. Automat. Contr., Vol. 47, Iss. 6, pp. 945-959, 2002.

[48] S. Athuraliya, S.H. Low, V.H. Li, and Q. Yin, “REM: active queue management”, IEEE Network, Vol. 15, Iss. 3, pp. 48-53, 2001.