论文信息 - Neural Network Implementation of Admission Control

Neural Network Implementation of Admission Control

A feedforward layered network implements a mapping required to control an unknown stochastic nonlinear dynamical system. Training is based on a novel approach that combines stochastic approximation ideas with backpropagation. The method is applied to control admission into a queueing system operating in a time-varying environment.

Isabelle Guyon | Sara A. Solla | Rodolfo A. Milito

[1] Arthur W. Berger. Overload control using rate control throttle: selecting token bank capacity for robustness to arrival rates , 1991 .

[2] Geoffrey E. Hinton,et al. Learning representations by back-propagation errors, nature , 1986 .

[3] Harold J. Kushner,et al. wchastic. approximation methods for constrained and unconstrained systems , 1978 .

[4] Leonard Kleinrock,et al. Theory, Volume 1, Queueing Systems , 1975 .

[5] Geoffrey E. Hinton,et al. Learning representations by back-propagating errors , 1986, Nature.

[6] Arthur W. Berger. Overload control using rate control throttle: selecting token bank capacity for robustness to arrival rates , 1989, Proceedings of the 28th IEEE Conference on Decision and Control,.