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

A two-phase neural network based optimisation method for short-term Schedul ing 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 hydroel ectric system with a nonlinear power generation function of water discharge rate and storage volume is considered for implementation. The water transp ortation delay between cascaded reservoirs is taken into account. Results f rom this method are compared with those obtained from the augmented lagrang ian method. It is shown that the proposed solution technique is capable of yielding good optimal solution with proper selection of control parameters.