Abstract
Addressing performance degradations in end-to-end congestion control has been one of the most active research areas in the last decade. Active queue management (AQM) is a promising technique to congestion control for reducing packet loss and improving network utilization in transmission control protocol (TCP)/Internet protocol (IP) networks. AQM policies are those policies of router queue management that allow for the detection of network congestion, the notification of such occurrences to the hosts, and the adoption of a suitable control policy. Radial bias function (RBF)-based AQM controller is proposed in this paper. RBF as a nonlinear controller is suitable as an AQM scheme to control congestion in TCP communication networks since it has nonlinear behavior. Particle swarm optimization (PSO) algorithm is also employed to derive RBF output weights such that the integrated-absolute error is minimized. Furthermore, in order to improve the robustness of RBF controller, an error-integral term is added to RBF equation. The output weights and the coefficient of the integral error term in the latter controller are also optimized by PSO algorithm. It should be noted that in both proposed controllers the parameters of radial basis functions are selected to symmetrically partition the input space. The results of the comparison with adaptive random early detection (ARED), random exponential marking (REM), and proportional-integral (PI) controllers are presented. Integral-RBF has better performance not only in comparison with RBF but also with ARED, REM and PI controllers in the case of link utilization while packet loss rate is small.
Similar content being viewed by others
References
Huang CJ, Cheng CL, Chuang YT, Jang JS (2006) Admission control schemes for proportional differentiated services enabled internet servers using machine learning techniques. Expert Syst Appl 31:458–471
Kim KJ, Jeong IJ, Park JC, Park YJ, Kim CG, Kim TH (2007) The impact of network service performance on customer satisfaction and loyalty: high-speed internet service case in Korea. Expert Syst Appl 32:822–831
Jacobson V (1988) Congestion avoidance and control. In: Proceedings of the ACM SIGCOMM, pp 314–329
Floyd S, Jacobson V (1993) Random early detection gateways for congestion avoidance. IEEE/ACM Trans Network 1:397–413
Kunniyur S, Srikant R (2001) Analysis and design of an adaptive virtual queue (AVQ) algorithm for active queue management. In: Proceedings of the ACM SIGCOMM, pp 123–134
Athuraliya S, Low SH, Li VH, Yin Q (2001) REM: active queue management. IEEE Network 15:48–53
Aweya J, Ouellette M, Montuno DY, Felske K (2008) Design of rate-based controllers for active queue management in TCP/IP networks. Comput Communicat 31:3344–3359
Cho HC, Fadali SM, Lee H (2008) Adaptive neural queue management for TCP networks. Comput Electr Eng 34:447–469
Zhang W, Tan L, Peng G (2009) Dynamic queue level control of TCP/RED systems in AQM routers. Comput Electr Eng 35:59–70
Yu L, Ma M, Hu W, Shi Z, Shu Y (2011) Design of parameter tunable robust controller for active queue management based on H ∞ control theory. J Network Comput Appl 34:750–764
Feng W, Kandlur DD, Saha D, Shin KG (1999) A self-configuring RED gateway. In: Proceedings of the IEEE INFOCOM, pp 1320–1328
Lin D, Morris R (1997) Dynamics of random early detection. In: Proceedings of the ACM SIGCOM, pp 127–137
Qtt TJ, Lakshman TV, Wong L (1999) SRED: stabilized RED. In: Proceedings of the IEEE INFOCOM, pp 1346–1355
Anjum F, Tassiulas L (1999) Fair bandwidth sharing among adaptive and nonadaptive flows in the internet. In: Proceedings of the IEEE INFOCOM, pp 1412–1420
Nabeshima M (2002) Improving the performance of active buffer management with per-flow information. IEEE Commun Lett 6:306–308
Liu S, Başar T, Srikant R (2005) Exponential-RED: a stabilizing AQM scheme for low- and high-speed TCP protocol. IEEE/ACM Trans Networking 13:1068–1081
Aweya J, Ouellette M, Montuno DY, Chapman A (2001) A control theoretic approach to active queue management. Comput Networks 36:203–235
Xiong N, Vasilakos AV, Yang LT, Wang C-X, Kannan R, Chang C-C, Pan Y (2010) A novel self-tuning feedback controller for active queue management supporting TCP flows. Inf Sci 180:2249–2263
Xiong N, Yang LT, Yang Y, Defago X, He Y (2008) A novel numerical algorithm based on self-tuning controller to support TCP flows. Mathe Comput Simul 79:1178–1188
Zhang C, Yin J, Cai Z, Chen W (2010) RRED: robust RED algorithm to counter low-rate denial-of-service attacks. IEEE Commun Lett 14:489–491
Feng W, Shin KG, Kandlur DD, Saha D (2002) The BLUE active queue management algorithms. IEEE/ACM Trans Networking 10:513–528
Long C, Zhao B, Guan X, Yang J (2005) The YELLOW queue management algorithm. Comput Networks 47:525–550
Feng W-C, Kapadia A, Thulasidasan S (2002) GREEN: proactive queue management over a best-effort network. In: Proceedings of the IEEE GLOBECOM, pp 1774–1778
Haykin S (1999) Radial-basis function networks. In: Neural networks-a comprehensive foundation, Chap. 5, 2nd edn. Prentice Hall, pp 256–318
Yao D (2002) High-resolution EEG mapping: a radial-basis function based approach to the scalp Laplacian estimate. Clin Neurophysiol 113:956–967
Eberhart RC, Shi Y (1998) Comparison between genetic algorithms and particle swarm optimization. In: Proceedings of the international conference on evolutionary programming, pp 611–616
Hollot CV, Misra V, Towsley D, Gong WB (2001) On designing improved controllers for AQM routers supporting TCP flows. In: Proceedings of the IEEE INFOCOM, pp 1726–1734
Li Y, Ko KT, Chen G (2005) A Smith predictor-based PI-controller for active queue management. IEICE Trans Commun 88:4293–4300
Chang X, Muppala JK (2006) A stable queue-based adaptive controller for improving AQM performance. Comput Networks 50:2204–2224
Hollot C, Misra V, Towsley D, Gong WB (2002) Analysis and design of controllers for AQM routers supporting TCP flows. IEEE Trans Automat Contr 47:945–959
Kim KB, Low SH (2003) Analysis and design of AQM based on state-space models for stabilizing TCP. In: Proceedings of the American control conference, pp 260–265
Ren F, Lin C, Wei B (2005) A robust active queue management algorithm in large delay network. Comput Communicat 28:485–493
Wang X, Wang Y, Zhou H, Huai X (2006) PSO-PID: a novel controller for AQM routers. In: Proceedings of the IEEE/IFIP WOCN, pp 1–5
Chen C-K, Kuo H-H, Yan J-J, Liao T-L (2009) GA-based PID active queue management control design for a class of TCP communication networks. Expert Syst Appl 36:1903–1913
Wang J-S, Gao Z-W, Shu Y-T (2007) RBF-PID based adaptive active queue management algorithm for TCP network. In: Proceedings of the IEEE international conference on control and automation, pp 171–176
Farokhian Firuzi M, Haeri M (2005) Active queue management in TCP networks based on self tuning control approach. In: Proceedings of the IEEE conference on control applications, pp 904–909
Di Fatta G, Re GL, Urso A (2002) A fuzzy approach for the network congestion problem. Lecture Notes Comput Sci 2329:286–295
Fengyuan RYR, Xiuming S (2002) Design of a fuzzy controller for active queue management. Comput Communicat 25:874–883
Rahmani R, Kanter T, Åhlund C (2010) a self configuring fuzzy active queue management controller in heterogeneous networks. In: Proceedings of the international conference on telecommunications, pp 634–641
Lima MM de AE, de Fonseca NLS, Geromel JC (2004) An optimal active queue management controller. In: Proceedings of the IEEE international conference on communications, pp 2261–2266
Bigdeli N, Haeri M (2009) Predictive functional control for active queue management in congested TCP/IP networks. ISA Trans 48:107–121
Chen C-K, Hung Y-C, Liao T-L, Yan J-J (2007) Design of robust active queue management controllers for a class of TCP communication networks. Inf Sci 177:4059–4071
Chen C-K, Liao T-L, Yan J-J (2009) Active queue management controller design for TCP communication networks: variable structure control approach. Chaos Solitons Fractals 40:227–285
Fengyuan R, Chuang L, Xunhe Y, Xiuming S, Fubao W (2002) A robust active queue management algorithm based on sliding mode variable structure control. In: Proceedings of the IEEE INFOCOM, pp 13–20
Mahdi Alavi SM, Hayes MJ (2009) Robust active queue management design: a loop-shaping approach. Comput Commun 32:324–331
Bigdeli N, Haeri M (2009) CDM-based design and performance evaluation of a robust AQM method for dynamic TCP/AQM networks. Comput Commun 32:213–229
Park EC, Lim H, Park KJ, Choi CH (2004) Analysis and design of the virtual rate control algorithm for stabilizing queues in TCP networks. Comput Networks 44:17–41
Quet PF, Ozbay H (2004) On the design of AQM supporting TCP flows using robust control theory. IEEE Trans Autom Control 49:1031–1036
Manfredi S, di Bernardo M, Garofalo F (2009) Design, validation and experimental testing of a robust AQM control. Control Eng Pract 17:394–407
Rahnami K, Arabshahi P, Gray A (2005) Neural network based model reference controller for active queue management of TCP flows. In: Proceedings of the IEEE international conference on aerospace, pp 1696–1704
Lochin E, Talavera B (2011) Managing Internet routers congested links with a Kohonen-RED queue. Eng Appl Artificial Intell 24:77–86
Misra V, Gong WB, Towsley DF (2000) Fluid-based analysis of a network of AQM routers supporting TCP flows with an application to RED. In: Proceedings of the ACM SIGCOMM, pp 151–160
Broomhead DS, Lowe D (1988) Multivariable functional interpolation and adaptive networks. Complex Syst 2:321–355
Poggio T, Girosi F (1990) Networks for approximation and learning. Proc IEEE 78:1481–1497
Kennedy J, Eberhart RC (1995) Particle swarm optimization. In: Proceedings of the IEEE international conference on neutral networks, pp 1942–1948
Shi Y, Eberhart R (1998) Parameter selection in particle swarm optimization. In: Proceedings of the international conference on evolutionary programming, pp 591–601
Suganthan PN (1999) Particle swarm optimiser with neighborhood operator. In: Proceedings of the IEEE congress on evolutionary computation, pp 1958–1962
Yoshida H, Fukuyama Y, Takayama S, Nakanishi Y (1999) A particle swarm optimization for reactive power and voltage control in electric power systems considering voltage security assessment. In: Proceedings of the IEEE international conference on systems, man, and cybernetics, vol. 6, pp 497–502
Naka S, Genji T, Yura T, Fukuyama Y (2001) Practical distribution state estimation using hybrid particle swarm optimization. In: Proceedings of the IEEE power engineering society winter meeting, vol. 2, pp 815–820
Ratnaweera A, Halgamuge S, Watson H (2003) Particle swarm optimization with self-adaptive acceleration coefficients. In: Proceedings of the first international conference on fuzzy systems and knowledge discovery, pp 264–268
van den Bergh F, Engelbrecht AP (2006) A study of particle swarm optimization particle trajectories. Inf Sci 176:937–971
Engelbrecht AP (2007) Computational intelligence-an introduction, chap. 16, 2nd edn. Wiley, London, pp 289–357
Floyd S, Gummadi R, Shenker S (2001) Adaptive RED: a algorithm for increasing the robustness of RED’s active queue management. (http://www.icir.org/floyd/papers/adaptiveRed.pdf)
Acknowledgments
This work is supported by Islamic Azad University South Tehran Branch under a research project entitled as “Design and Simulation of Optimal Neural Controllers for Active Queue Management in TCP Communication Networks.”
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Sheikhan, M., Shahnazi, R. & Hemmati, E. Adaptive active queue management controller for TCP communication networks using PSO-RBF models. Neural Comput & Applic 22, 933–945 (2013). https://doi.org/10.1007/s00521-011-0786-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-011-0786-0