Low-cost Pyranometer-Based ANN Approach for MPPT in Solar PV Systems
By: Luiz Fernando M. Arruda, Moises Ferber, Diego Greff
Potential Business Impact:
Makes solar panels work their best.
This article presents a study on the application of artificial neural networks (ANNs) for maximum power point tracking (MPPT) in photovoltaic (PV) systems using low-cost pyranometer sensors. The proposed approach integrates pyranometers, temperature sensors, and an ANN to estimate the duty cycle of a DC/DC converter, enabling the system to consistently operate at its maximum power point. The strategy was implemented in the local control of a Cuk converter and experimentally validated against the conventional Perturb and Observe (P&O) method. Results demonstrate that the ANN-based technique, leveraging affordable sensor technology, achieves accurate MPPT performance with reduced fluctuations, enhancing the responsiveness and efficiency of PV tracking systems.
Similar Papers
Temporal Graph Neural Networks for Early Anomaly Detection and Performance Prediction via PV System Monitoring Data
Machine Learning (CS)
Predicts solar power and finds problems in solar panels.
Improvement and Stabilization of Output Voltages in a Vertical Tidal Turbine Using Intelligent Control Strategies
Networking and Internet Architecture
Makes ocean power more steady and useful.
Market-Oriented Flow Allocation for Thermal Solar Plants: An Auction-Based Methodology with Artificial Intelligence
Systems and Control
Makes solar power plants work better.