Short term hydro scheduling using two-phase neural network

This paper presents a solution technique based on two-phase neural network for short term scheduling of hydropower generations. The proposed method is based on solution of a set of differential equations realized from transformation of an augmented lagrangian energy function. Here the objective function is to minimize the nonhydraulic power production expenses over the scheduling period. A multi-reservoir cascaded hydroelectric system with a nonlinear power generation function of water discharge rate and storage volume is taken into account for implementation, The water transportation delay between cascaded reservoirs is considered. Results concerning this method are compared with those achieved from successive solution of augmented lagrangian function utilizing familiar conjugate gradient method. It is shown that proposed solution approach with suitable selection of control parameters is capable of generating a good optimal solution. (C) 2002 Published by Elsevier Science Ltd.