NEURAL NETWORKS AND PSEUDO-MEASUREMENTS FOR REAL-TIME MONITORING OF DISTRIBUTION-SYSTEMS

A state estimation scheme for power distribution systems, based on Art ificial Neural Networks (ANN's), is proposed, Despite the influence of measurement uncertainties, it allows quantities describing the distri bution system operation to be identified on-line, thereby constituting neural ''pseudo-instruments''. Details of the design and optimization of such a neural scheme are discussed, underlining the importance of ANN tuning to achieve greater levels of accuracy, The performance obta ined in a study case, for different types of operating conditions, was analyzed and confirmed the feasibility and the robustness of the prop osed approach, This neural estimation scheme proves to be preferable t o traditional mathematical approaches whenever there are online requir ements, due, of course, to the typically high operating speed of ANN's .