Real‐Time Incremental Learning Artificial Neural Networks Maximum Power Point Tracking With Raspberry Pi‐Based Meteorological Data Acquisition

ABSTRACT This paper presents a new maximum power point tracking (MPPT) method for photovoltaic (PV) systems based on artificial neural networks (ANNs) models integrated with incremental learning and the capability of real‐time acquiring meteorological conditions by using a Raspberry Pi. The approach uses hourly irradiance and temperature values obtained from the NASA POWER API to dynamically re‐train the ANN model according to weather conditions. Simulation results using MATLAB/Simulink reveal that the proposed system exhibits high precision and robust performance over a range of irradiance (200–1000 W/m 2 ). The system achieved an average PV conversion efficiency of 99.52% and load‐side efficiency of 98.50%, outperforming several conventional and intelligent MPPT techniques reported in the literature. Performance quantification results in an MSE of 0.0024 and an R 2 value of 0.9987, revealing the excellent regression accuracy for the Vmp. Apart from the accuracy, the system exhibits a low response time and good power tracking under various operating circumstances.