Abstract
A neural network for the traffic control problem applied to reverse baseline networks has been proposed in this paper. This problem has been first represented by an energy function. A neural network is applied for maximizing the energy of the function under the constraints of the reverse baseline network. The number of iteration steps in our neural network is limited by a performed upper bound O(n), wheren is the size of ann ×n network. The throughputs of our neural network have been shown by the empirical results to be better than the conventional algorithm (modified Bipartite Matching Algorithm) when the packet densities rise higher than 50%.
Similar content being viewed by others
References
Dharma P. Agrawal, Graph theoretical analysis and design of multistage interconnection networks,IEEE Trans. Comp., pp. 637–648, July, 1983.
S. V. B. Aiyer, M. Niranjan, and F. Fallside, A theoretical investigation into the performance of the hopfield model,IEEE Trans. Neural Networks, pp. 204–215, June, 1990.
Bernard Angeniol, Gael De La Croix Vaubois and Jean-Yves Le Texier, Self-organizing feature maps and the travelling salesman problem,Neural Networks, vol. 1, 289–293, 1988.
D. M. Dias and M. Kumar, Packet switching in nlogn multistage networks,Proc. IEEE GLOBECOM'84, pp. 114–120, November, 1984.
Tse-yun Feng, A survey of interconnection networks,IEEE Comp., pp. 12–14, December, 1981.
Hsin Chia Fu and K. T. Sun, Floating-point array processors for microcomputers,Int. J. Mini and Microcomp., vol. 10, pp. 21–26, 1988.
J. J. Hopfield and D. W. Tank, Neural composition of decisions optimization problems,Biol. Cyb., vol. 55, pp. 141–152, 1985.
Clyde P. Kruskal, The performance of multistage interconnection networks for multiprocessors,IEEE Trans. Comp., pp. 1091–1098, December, 1983.
S. Kumpati and Kannan Parthasarathy, Identification and control of dynamical systems using neural networks,IEEE Trans. Neural Networks, pp. 4–27, March, 1990.
H. T. Kung, Why systolic architectures,IEEE Comp., pp. 37–46, January, 1982.
Richard P. Lippmann, Introduction to computing with neural nets,IEEE ASSP Mag., pp. 4–22, April, 1987.
Christos H. Papadimitriou, Algorithms for matching,Combinatorial Optimization: Algorithms and Complexity, pp. 218–246, Prentice-Hall, 1982.
Carsten Peterson and Bo Soderberg, A new method for mapping optimization problems onto neural networks,Int. J. Neural Systems, vol. 1, no.1, pp. 3–22, 1989.
John C. Platt and Alan H. Barr, Constrained differential optimization,Neural Information Processing Systems, New York: American Institute of Physics, pp. 612–621, 1988.
J. Ramanujam and P. Sadayappan, Parameter identification for constrained optimization using neural networks,Proc. Connectionist Models, pp. 154–161, 1988.
Massimo A. Sivilotti, M. A. Mahowald, and C. A. Mead, Real-time visual computations using analog CMOS processing arrays,Advanced Research in VLSI: Proc. 1987 Stanford Conf., pp. 295–312, 1987.
K. T. Sun and H. C. Fu, Solving satisfiability problems with neural networks,Proc. IEEE Region 10 Conf. Comp. Comm. Sys., vol. 1, pp. 17–22, Hong Kong, 1990.
K. T. Sun, H. C. Fu and C. Chen, A neural network for solving Hamiltonian cycle problems, T. Kohonen et al. (eds.),Artificial Neural Networks, Elsevier Science Publishers B.V. (North-Holland), vol. 2, pp. 1797–1800, 1991.
K. T. Sun and H. C. Fu, A neural network algorithm for solving the traffic control problem in multistage interconnection networks,Proc. Int. Jt. Conf. Neural Networks, Singapore, vol. 2, pp. 1136–1141, November 24–28, 1991.
K. T. Sun and H. C. Fu, An O(n) parallel algorithm for solving the traffic control problem on crossbar switch networks, vol. 1, no. 1,Parallel Processing Letter, pp. 51–58, 1991.
K. T. Sun and H. C. Fu, A neural network for traffic control problem on crossbar switch networks,under revision in Int. J. Neural Syst., 1992.
INMOS, Transputer,The Transputer Databook, Redwood Bum Ltd., Trowbridge, 1989.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Sun, K.T., Fu, H.C. A neural network approach to the traffic control problem in reverse baseline networks. Circuits Systems and Signal Process 12, 247–261 (1993). https://doi.org/10.1007/BF01189876
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/BF01189876