A Critical Analysis of The Application of Artificial Neural Network (ANN) in the Field of DC to DC Converters.

Because of the fast advancement of renewable energy technologies, the idea of microgrid (MG) is becoming more commonly adopted in power systems. DC MG is gaining popularity due to the benefits of the DC distribution system, including as easier integration of energy storage and lower system loss. The linear controller, such as PI or PID, is established and widely used in the power electronics sector, but its performance degrades as system parameters change. In this paper, an artificial neural network (ANN)-based voltage control technique for a DC- DC boost converter is developed. The model predictive control (MPC) is employed as an expert in this study, providing data to train the suggested ANN. Because ANN is highly adjusted, it is used directly to regulate the step-up DC converter. The key benefit of the ANN is that it reduces the inaccuracy of the system model even with erroneous parameters and has a lower computing overhead than MPC owing to its parallel nature. Extensive MATLAB/Simulink simulations are run to validate the performance of the proposed ANN. The simulation findings reveal that the ANN-based control method outperforms the PI controller under various loading situations. The trained ANN model has an accuracy of roughly 97%, making it acceptable for DC microgrid applications.. Index Terms—ANN, DC Microgrid, DC/DC boost converter, MPC, Primary control.