Two-phase neural network based solution technique for short term hydrothermal scheduling

A two-phase neural network based optimisation method for short-term scheduling of a hydrothermal power system is proposed. The method is based on the solution of a set of differential equations obtained from transformation of an augmented Lagrangian energy function. A multireservoir cascaded hydroelectric system with a nonlinear power generation function of water discharge rate and storage volume is considered for implementation. The water transportation delay between cascaded reservoirs is taken into account. Results from this method are compared with those obtained from the augmented Lagrangian method. It is shown that the proposed solution technique is capable of yielding a good optimal solution with proper selection of control parameters