A NEURAL NETWORK OPTIMIZER FOR SCHEDULING HYDROPOWER GENERATIONS

Abstract

An approach based on neural network optimizer is proposed for determining the optimal short-term scheduling of multi-reservoir hydropower system. The proposed method is based on the Lagrange multiplier theory and search for solutions satisfying the necessary conditions of optimality in the state space. The equilibrium point of the network optimizer corresponds to the Lagrange solution of the problem and satisfies the Kuhn-Tucker condition for the problem. Here the main objective is to determine the optimal amounts of water to be released from each reservoir during each interval so as to minimize the overall energy shortages over the complete planning horizon. The method takes into account the water transportation delays between upstream and downstream reservoirs and a nonlinear hydropower generation function. An algorithm based on the proposed neural network optimizer has been developed and implemented on a multi-chain cascade of reservoir type hydropower system. Results so achieved have been compared with those obtained using conventional augmented Lagrange multiplier method. From the results, it is concluded that the proposed method is very effective in providing a good optimal solution along with constraint satisfaction.