Document Type : Research Article
Authors
1
Department of Electrical and Electronics Engineering, Mother Theresa Institute of Engineering and Technology, Chittoor, Andhra Pradesh - 517408, India
2
Professor, Department of Electrical and Electronics Engineering, Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences (SIMATS), Thandalam, Chennai, Tamil Nadu - 602105, India.
3
Department of Electrical and Electronics Engineering, Velammal Institute of Technology, Panjetty, Chennai, Tamilnadu - 601204, India
10.22059/jser.2026.414342.1740
Abstract
Grid-connected photovoltaic (PV) systems require accurate maximum power point tracking (MPPT), stable direct-current (DC)-link voltage regulation, and improved grid power quality under variable irradiance and temperature. Conventional MPPT methods often exhibit tracking delays and steady-state oscillations and have a limited ability to maintain low harmonic distortion in the grid current under dynamic operating conditions. This simulation-based work develops an artificial neural network (ANN)-based MPPT control strategy for improving power extraction, DC-link stability, and grid-current quality in a single-phase grid-connected PV system. The ANN controller uses irradiance, cell temperature, PV voltage, current, and power as input variables to estimate the voltage reference corresponding to the maximum power point. The error between the predicted reference voltage and the measured PV voltage is used to adjust the duty cycle of the DC–DC boost converter, while the regulated DC-link supports synchronized inverter operation. Under the simulated operating conditions, the system attained a PV voltage of 192 V, a PV current of 0.308 A, and an output power of 59.17 W, a duty cycle of 0.55, a DC-link voltage of 426 V, a switching frequency of 25 kHz, an RMS grid voltage of 230 V, and a grid-current THD of 3.42%.
Keywords
