Power system unit commitment using genetic-based neural networks

A new approach using genetic algorithms based neural networks and dynamic programming (GANN-DP) to solve power system unit commitment problems is proposed in this paper. A set of feasible generator commitment schedules is first formulated by a genetic-enhanced neural network. These pre-committed schedules are then optimized by the dynamic programming technique. With the proposed approach, the learning stagnation is avoided. The stability and accuracy of the neural network are significantly increased. The computational performance of unit commitment in a power system is therefore highly improved. The proposed method is tested using the utility data. The results demonstrate the feasibility and practicality of this approach.