A Neural-Network Based Maximum Power Point Tracker for Improved Dynamics of Variable DC-Link GRid Connected Photovoltaic Power Plant

"This paper proposes a maximum power point tracking algorithm based on neural networks to improve the dynamic performance across the dc capacitor utilized in the power converter that serves as an interphase to connect photovoltaic power plants into the ac grid. Traditional maximum power point tracking algorithms such as “perturb & observe” and “incremental conductance” are able to track the point of maximum power in most cases. However, in architectures with a power converter operated at variable dc link they provide a step-like voltage reference which translates into a repetitive overshoot across the dc capacitor, which may negatively affect the lifespan of the capacitor and affect the overall dynamic of the system. This paper develops a neural network algorithm that not only tracks the maximum power point in real time, but also provides a smooth reference for the dc link voltage control loop and hence eliminates overshoots. The approach is validated via detailed PSCAD\/EMTDC computer simulations. . .