Simulated annealing-reinforcement learning algorithm for ABR traffic control of ATM networks

For the congestion problems in asynchronous transfer mode (ATM) networks, a hybrid intelligent controller based on simulated annealing (SA) and reinforcement learning (RL) algorithm is proposed. The SA algorithm is a powerful way to solve hard combinatorial optimization problems, which is used to adjust the parameters of the controller. The RL algorithm shows the particular superiority in ATM networks, which is independent of the mathematic model and just needs simple fuzzy information obtained through trial-and-error and interaction with the environment. With the advantages of the two algorithms, the proposed controller forces the queue size in the multiplexer buffer to the desired value by adjusting the source transmission rate of the available bit rate (ABR) service. Simulation results show that the proposed method can promote the performance of the networks and avoid the occurrence of congestion effectively.

[1]  Kao-Shing Hwang,et al.  A REINFORCEMENT LEARNING APPROACH TO CONGESTION CONTROL OF HIGH-SPEED MULTIMEDIA NETWORKS , 2005, Cybern. Syst..

[2]  A.G. Parlos,et al.  A reinforcement learning method based on adaptive simulated annealing , 2003, 2003 46th Midwest Symposium on Circuits and Systems.

[3]  Anil Nerode,et al.  Asynchronous, distributed, decision-making systems with semi-autonomous entities: a mathematical framework , 2000, IEEE Trans. Syst. Man Cybern. Part B.

[4]  James M. Tien,et al.  A knowledge-base generating hierarchical fuzzy-neural controller , 1997, IEEE Trans. Neural Networks.

[5]  Kao-Shing Hwang,et al.  Reinforcement learning congestion controller for multimedia surveillance system , 2003, 2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422).

[6]  Chris Heegard,et al.  Bounding the Capacity of Saturation Recording: The Lorentz Model and Applications , 1992, IEEE J. Sel. Areas Commun..

[7]  Huanwen Tang,et al.  An improved simulated annealing for solving the linear constrained optimization problems , 2006, Appl. Math. Comput..

[8]  Günhan Dündar,et al.  Hierarchical neuro-fuzzy call admission controller for ATM networks , 2001, Comput. Commun..

[9]  Shie-Jue Lee,et al.  A neural-fuzzy system for congestion control in ATM networks , 2000, IEEE Trans. Syst. Man Cybern. Part B.

[10]  Sarangapani Jagannathan,et al.  Predictive congestion control of ATM networks: multiple sources/single buffer scenario , 2000, Proceedings of the 39th IEEE Conference on Decision and Control (Cat. No.00CH37187).