Abstract
The phenomena of congestion and packet-drops in high-speed communications and computer networks do affect the quality-of-service and overall performance more than ever existing time-delays with uncertain variations. Their control and, possibly, prevention are subject to extensive research ever since the internet is available. Because of the uncertainties and time-varying phenomena, obtaining the accurate and complete information on the network traffic patterns, especially for the multi-bottleneck case, is rather difficult hence learning intelligent controls are needed. One such control is a multi-agent flow controller (MAFC) based on Q-learning algorithm in conjunction with the theory of Nash equilibrium of opponents’ strategies. The other is a model-independent Q-learning control (MIQL) scheme having focus on the flow with higher priority, which also does not need prior-knowledge on communication traffic and congestion. The competition of communication flows with different priorities is considered as a two-player non-cooperative game. The Nash Q-learning algorithm control obtains the Nash Q-values through trial-and-error and interaction with the network environment so as to improve its behaviour policy. The MAFC can learn to take the best actions in order to regulate source flows that guarantee high throughput and low packet-loss ratio. The MIQL control, through a specific learning processing, does achieve the optimum sending rate for the sources with lower priority while observing the sources with higher priority. Designed intelligent controls achieve superior performances in controlling the flows in high-speed networks in comparison to the standard ones and avoid communications congestion.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Aström, K.J.: Introduction: complex systems and control. In: Astöm, KJ., Albertos, P., Blanke, M., Isidori, A., Sanz, R. (eds.) Control of Complex Systems, Chapter 1, pp. 1–20. Springer, London (2001)
Siljak, D.D.: Decentralized Control of Complex Systems. Academic Press, Boston (1991)
Wiener, N.: Cybernetics or Control and Communication in the Animal and the Machine. MIT Press, Coambridge, MA (1948).
Tsien, H.-S.: Engineering Cybermetics. McGraw-Hill, New York, NY (1954).
Dimirovski, G.M., Gough, N.E., Barnett, S.: Categories in systems and control theory. Int. J. Control 8(9), 1081–1090 (1977)
Gitt, W.: Information: the third fundamental quantity. Siemens Rev. 56, 36–41 (1989)
Kalman, R.E.: On the general theory of control: In: Proceedings of the First International Congress on Automatic Control. Butterworth Scientific Institute, London, UK, vol. 1, pp. 481–506. Also in Russian: Trudyi I Kongressa IFAK, Izdatelystvo AN SSSR, Moskva, SSSR, vol. 2, pp. 521–547 (1961)
Pontryagin, L.S., Boltyanskiy, V.G., Gamkrelidze, R.V., Mishchenko, E.F.: Matematicheskaya teoriya optimalynih processov, Izdatelystvo fizichko-matematicheskoy literaturi, Moskva, SSSR. Also in English (1962): The Mathematical Theory of Optimal Processes. J. Wiley InterScience, New York (1961)
Savkin, A.V., Matveev, A.S.: Cyclic linear differential automata: a simple class of hybrid dynamical systems. Automatica 36(5), 727–734 (2000)
Imer, O.C., Basar, T.: Control of congestion in high-speed networks. Eur. J. Control 7(2–3), 132–144 (2001)
Jacobson, V.: Congestion avoidance and control. ACM Comput. Commun. Rev. 18, 314–329 (1988)
Alpcan, T., Basar, T.: A game theoretical analysis of intrusion detection in access control systems. In: Proceedings of the 43rd IEEE Conference on Decision and Control, Paradise Island, Bahamas, 14–17 Dec. The IEEE Press, Piscataway, NJ, USA, pp. 1568–1573 (2004)
Basar, T., Olsder, G.J.: Dynamic Non-cooperative Game Theory, 2nd edn. The SIAM, Philadelphia, PA (1999)
Dimirovski, G.M: Network Q-Learning control prevent cyber intrusion risks: synergies of control theory and computational intelligence. In: Duman, E., Atiya, A. (eds.) Use of Risk Analysis in Computer-Aided Persuasion, vol. 88. NATO Science Sub-Series E, Chapter 20–Part III. The IOS Press, Amsterdam, Berlin Tokyo Washington DC, pp. 281–303 (2011)
Gevros, P., Crowcoft, J., Kirstein, P., Bhatti, S.: Congestion control mechanisms and the best effort service model. IEEE Netw. 15(3), 16–26 (2001)
Imer, O.C., Compans, S., Basar, T., Srikant, R.: ABR congestion control in ATM networks. IEEE Control Syst. Mag. 21(1), 38–56 (2001)
Jing, Y.-W., Li, X., Dimirovski, G.M., Zheng, Y., Zhang, S.-Y.: Nash Q-learning multi-agent flow control for high-speed networks. In: Proceedings of the 28th American Control Conference, St. Louis, MO, USA, 10–12 June, pp. 3304–3309. The IEEE Press, Piscataway, NJ, USA (2009)
Lestas, M., Pitsillides, A., Ioannou, P., Hadjipollas, G.: Adaptive congestion protocol: A congestion control protocol with learning capability. Comput. Netw. Int. J. Comput. Telecommun. Netw. 51(13), 3773–3798 (2007)
Li, X., Dimirovski, G.M., Jing, Y.-W., Zhang, S.-Y.: A Q-learning model-independent flow controller for high-speed networks. In: Proceedings of the 28th American Control Conference, St. Louis, MO, USA, 10–12 June, pp. 1544–1548. The IEEE Press, Piscataway, NJ, USA (2009)
Li, X., Zhou, Y.C., Dimirovski, G.M., Jing, Y.-W.: Simulated annealing Q-learning algorithm for ABR traffic control of ATM networks. In: Proceedings of the 27th American Control Conference, Seattle, WA, USA, 11–13 June, pp. 4462–4467. The IEEE Press, Piscataway, NJ, USA (2008)
Li, X., Shen, X.J., Jing, Y.-W., Zhang, S.-Y.: Simulated annealing-reinforcement learning algorithm for ABR traffic control of ATM networks. In: Proceedings of the 46th IEEE Conference on Decision and Control, New Orleans, LA. USA, 12–14 Dec, pp. 5716-5721. The IEEE Press, Piscataway, NJ, USA (2007)
Ren, T., Zhu, Z., Yu, H., Dimirovski, G.M.: Integral sliding-mode controller for congestion problem in ATM networks. Int. J. Control 86(3), 529–539 (2013)
Ren, T., Wang, C., Luo, X., Jing, Y., Dimirovski, G.M.: Robust controller design for ABR traffic control of ATM networks with time-varying multiple time delays. Int. J. Innovative Comput. Inf. Control 5(8), 68–74 (2009)
Ren, T., Gao, Z., Kong, W., Jing, Y., Yang, M., Dimirovski, G.M.: Performance and robustness analysis of a fuzzy-immune flow controller in ATM networks with time-varying multiple time-delays. J. Control Theory Appl. 6(3), 253–258 (2008)
Aizerman, M.A., Breverman, E.M., Rosonoer, L.I.: Theoretical foundation of the potential function method in pattern recognition learning (in Russian). Avtomatika i Telemechanika 25, 821–837 (1964)
Aizerman, M.A., Breverman, E.M., Rosonoer, L.I.: The probability problem of pattern recognition learning and the potential function method (in Russian). Avtomatika i Telemechanika 25, 821–837 (1964)
Chatovich, A., Okug, S., Dundar, G.: Hierarchical neuro-fuzzy call admission controller for ATM networks. Comput. Commun. 24(11), 1031–1044 (2001)
Cheng, R.G., Chang, C.J., Lin, L.F.: a QoS-provisioning neural fuzzy connection admission controller for multimedia high-speed networks. IEEE ACM Trans. Netw. 7(1), 111–121 (1999)
Harmer, P.K., Williams, P.D., Gunsh, G.H., Lamont, G.B.: An artificial immune system architecture for computer security applications. IEEE Trans. Evol. Comput. 6(2), 252–280 (2002)
Hsiao, M.C., Tan, S.W., Hwang, K.S., Wu, C.S.: a reinforcement learning approach to congestion control of high-speed multimedia networks. Cybern. Syst. 36(2), 181–202 (2005)
Hwang, K.S., Tan, S.W., Hsiao, M.C., Wu, C.S.: Cooperative multi-agent congestion control for high-speed networks. IEEE Trans. Syst. Man Cybern. Part B: Cybern. 35(2), 255–268 (2005)
The MathWorks Laboratory: Matlab: Control Toolbox, Fuzzy Toolbox. LMI Toolbox, The MathWorks Inc, Natick (1991)
The MathWorks Laboratory: Matlab: Simulink – Dynamic System Simulation Software. The MathWorks Inc, Natick (1996)
Dimirovski, G.M.: Lyapunov stability in control synthesis design using fuzzy-logic and neural-networks. In: Proceedings of the 17th IMACS World Congress, Paris, 11–15 July. The IMACS and Ecole Centrale de Lille, Villeneuve d’Ascq, FR, Paper T5-I-01-0907, pp. 1–8 (2005)
Marinos, P.N.: Fuzzy logic and its applications to switching systems. IEEE Trans. Comput. 18(4), 343–348 (1969)
Palm, R., Driankov, D.: Fuzzy switched hybrid systems – Modelling and identification. In: Proceedings of the 1998 IEEE International Conference on Fuzzy Systems, Gaithersburg, MD, pp. 130–135. The IEEE Press, Piscataway, NJ, USA (1998)
Tanaka, K., Masaaki, I., Wang, H.O.: Stability and smoothness conditions for switching fuzzy systems. Proceedings of the 19th American Control Conference, pp. 2474–2478. The IEEE Press, Piscataway, NJ, USA (2000)
Wang, H.O., Tanaka, K., Griffin, M.: An approach to fuzzy control of nonlinear systems: Stability and design issues. IEEE Trans. Fuzzy Syst. 4(1), 14–23 (1996)
Ye, H., Michael, A.N.: Stability theory for hybrid dynamical systems. IEEE Trans. Autom. Control 43(4), 464–474 (1998)
Zhao, J., Dimirovski, G.M.: Quadratic stability for a class of switched nonlinear systems. IEEE Trans. Autom. Control 49(4), 574–578 (2004)
Yang, H., Dimirovski, G.M., Zhao, J.: Switched fuzzy systems: representation modelling, stability, and control design. In: Chountas, P., Petrounias, I., Kacprzyk, J. (eds.) Studies in Computational Intelligence Volume 109 – Intelligent Techniques and Tool for Novel Systems Architectures, Chapter 9, pp. 169–184. Springer, Berlin Heidelberg (2008)
Yang, M., Jing, Y., Dimirovski, G.M., Zhang, N.: Stability and performance analysis of a congestion control algorithm for networks. In: Proceedings of the 46th IEEE Conference on Decision and Control, New Orleans, LA. USA, 12–14 Dec, pp. 4453–4458. The IEEE Press, Piscataway, NJ, USA (2007)
Jing, Y. W.: A Study on Advanced Fuzzy and Learning Controls for Communication Netwroks and Effects of Their Applications. Private Communication Report CCN-2007-2008-Shenyang-Skopje, College of Informations Science and Engineering, Northeastern University, Shenyang, PR China (2009).
Watkins, C.J.C.H., Dayan, P.: Q-learning. Mach. Learn. 8(3), 279–292 (1992)
Kaelbling, L.P., Littman, M.L., Moore, A.W.: Reinforcement learning: a survey. J. Artif. Intell. Res. 4(1), 237–285 (1996)
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. The MIT Press, Cambridge, MA, USA (1998)
Littman, M.L.: Value-function reinforcement learning in Markov games. J Cogn. Syst. Res. 2(1), 55–66 (2001)
Szepesvari, C., Littman, M.L.: a unified analysis of value-function-based reinforcement-learning algorithms. Neural Comput. 11(8), 2017–2060 (1999)
Hu, J., Wellman, M.P.: Nash Q-learning for general-sum stochastic games. J. Mach. Learn. Res. 4, 1039–1069 (2003)
Jing, Y.W., Dimirovski, G.M.: Multimedia transfer over the internet: a control based improvement of the AIMD algorithm. In: Proceedings of the 3rd IEEE International Conference on Information and Communication Technologies: From Theory to Applications, Damascus, Syria, 24–28 April. The IEEE Press, Piscataway, NJ, USA and ENST Brest, Bretagne, FR, Paper SEN06-1/1-6 (2006)
Dimirovski, G.M.: Complexity versus integrity solution in adaptive fuzzy-neural inference models. Int. J. Intell. Syst. 23(5), 556–573 (2008)
Nash, J.F.: Non-cooperative games. Ann. Math. 54(2), 286–295 (1951)
Bishop, C.M.: Pattern Recognition and Machine Learning. Springer, London, UK (2006)
Chiu, D.M., Jain, R.: Analysis of the increase decrease algorithms for congestion avoidance in computer networks. Comput. Netw. ISDN Syst. 17, 1–14 (1989)
Bradtke, S.J., Ydstie, BE., Barto, A.G.: Adaptive linear quadratic control using policy iteration. In: Proceedings of the 13th American Control Conference, Chicago, IL, 13–15 June, pp. 3475–3479. The IEEE Press, Piscataway, NJ (1994)
Haykin, S.: Neural Networks and Learning Machines, 3rd edn. Pearson Prentice Hall, Upper Saddle River (2009)
Ljung, L.: System Identification—Theory for the User, 2nd edn. Prentice Hall PTR, Upper Saddle River (1999)
Acknowledgments
The author has the honour to acknowledge and point out that this research was accomplished due to his collaboration with the young Dr. Xin Li and Dr. Yan Zheng, their mentor Prof. Yuan-Wei Jing from the Northeastern University, Shenyang, P.R. of China. Furthermore, special thanks are due to Academician Si-Ying Zhang, our common advisor and teacher, whose guidance has been instrumental. The author acknowledges their crucial merits, respectively, for fruitful carrying out this joint research endeavour.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Dimirovski, G.M. (2016). Learning Intelligent Controls in High Speed Networks: Synergies of Computational Intelligence with Control and Q-Learning Theories. In: Sgurev, V., Yager, R., Kacprzyk, J., Jotsov, V. (eds) Innovative Issues in Intelligent Systems. Studies in Computational Intelligence, vol 623. Springer, Cham. https://doi.org/10.1007/978-3-319-27267-2_4
Download citation
DOI: https://doi.org/10.1007/978-3-319-27267-2_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-27266-5
Online ISBN: 978-3-319-27267-2
eBook Packages: EngineeringEngineering (R0)