Author(s)

A. Boukhtouta & B. F. Lamond

Abstract

A neuro-dynamic programming approach for stochastic reservoir management A. ~oukhtouta' & B. F. Lamond2 Defence Research and Development Canada Valcartiel; Canada ~e'partement Ope'rations et systkmes de de'cision, Universite' Laval, Canada Abstract We propose an approach based on neural networks for optimizing a single hydroelectric reservoir. A stochastic neuro-dynamic programming algorithm is used to approximate the future value function by a neural function. The latter is used in deriving the optimal policy. The approximation architecture, based on the feedforward network, gives very smooth approximate functions even with a coarse discretization of the state and action variables. The hydroelectric reservoir model presented in our study assumes a piecewise linear reward of the electricity produced and takes into account the turbine head effects and the stochastic inflows. The method is illustrated with a numerical example. 1 Introduction We consider a mathematical model for optimizing the e

Keywords