A Novel Hybrid Training Method for Hopfield Neural Networks Applied to Routing in Communications Networks

Efficient routing algorithms are very important for the operation of communication networks, including the Internet. This article proposes a novel hybrid intelligent method for routing which combines Hopfield neural networks (HNN) and simulated annealing (SA). The proposed method introduces a modified version of the discrete-time equation used by Bastos-Filho et al [1]. The novel version of the equation aims to improve the HNN convergence, thereby decreasing the computation cost. In our method, the SA algorithm is used to obtain the optimal parameters of the HNN. Simulations reported in this paper shows that the proposed method outperforms the method of Bastos-Filho et al [1], by computing routes using smaller number of iterations and smaller error.

[1]  E. Bonabeau,et al.  Routing in Telecommunications Networks with “ Smart ” Ant-Like Agents , 1998 .

[2]  Faouzi Kamoun,et al.  Neural networks for shortest path computation and routing in computer networks , 1993, IEEE Trans. Neural Networks.

[3]  C. D. Gelatt,et al.  Optimization by Simulated Annealing , 1983, Science.

[4]  Mario Ventresca,et al.  Simulated Annealing with Opposite Neighbors , 2007, 2007 IEEE Symposium on Foundations of Computational Intelligence.

[5]  Xiaohong Jiang,et al.  Dynamic RWA Based on the Combination of Mobile Agents Technique and Genetic Algorithm in WDM Networks with Sparse Wavelength Conversion , 2005, IPDPS.

[6]  E. Fontana,et al.  Novel routing algorithm for transparent optical networks based on noise figure and amplifier saturation , 2003, Proceedings of the 2003 SBMO/IEEE MTT-S International Microwave and Optoelectronics Conference - IMOC 2003. (Cat. No.03TH8678).

[7]  H.E. Rauch,et al.  Neural networks for routing communication traffic , 1988, IEEE Control Systems Magazine.

[8]  Edsger W. Dijkstra,et al.  A note on two problems in connexion with graphs , 1959, Numerische Mathematik.

[9]  N. Metropolis,et al.  Equation of State Calculations by Fast Computing Machines , 1953, Resonance.

[10]  J. J. Hopfield,et al.  “Neural” computation of decisions in optimization problems , 1985, Biological Cybernetics.

[11]  Adriano Lorena Inácio de Oliveira,et al.  A Novel Approach for a Routing Algorithm Based on a Discrete Time Hopfield Neural Network , 2007, 2007 IEEE Symposium on Foundations of Computational Intelligence.

[12]  Rubén M. Lorenzo,et al.  Dynamic Routing and Wavelength Assignment in Optical Networks by Means of Genetic Algorithms , 2004, Photonic Network Communications.

[13]  B. Reljin,et al.  Neural network for finding optimal path in packet-switched network , 2004, 7th Seminar on Neural Network Applications in Electrical Engineering, 2004. NEUREL 2004. 2004.

[14]  S.C.A. Thomopoulos,et al.  Neural network implementation of the shortest path algorithm for traffic routing in communication networks , 1989, International 1989 Joint Conference on Neural Networks.

[15]  Marco Dorigo,et al.  AntNet: Distributed Stigmergetic Control for Communications Networks , 1998, J. Artif. Intell. Res..