An Artificial Neural Network Based MPPT Control of Modified Flyback Converter for PV Systems in Active Buildings
S. V. Gul, Sarmad Majeed Malik, Yingyun Sun, Faisal Alsaif
Abstract
As the world moves towards an increased penetration of renewable energy, the importance of photovoltaic systems (PV) cannot be denied as these networks are deployed at rooftops of active buildings and provide power to local loads. The performance of this system is dependent on the MPPT algorithm and step-up DC–DC converter for maximum power utilization at varying operating conditions. This paper proposes an ANN-based modified flyback converter scheme for linking PV panels to dc loads. In the proposed design, the secondary side diode is replaced by a MOSFET which offers several advantages such as reduced voltage stress, improved efficiency and positive output voltage. Moreover, the large voltage and current spikes at primary side switch is reduced which increases the lifetime of MOSFET. The system performance is analyzed in Simulink through variations in load, temperature and irradiance. A comparative analysis with P&O-PSO controller shows that the proposed control and topology gives an improved transient response, making it an ideal choice for future PV systems. • ANN-based MPPT controller operates the modified flyback converter at maximum power. • Secondary side diode is replaced by a MOSFET which improves efficiency. • The large voltage and current spikes at primary side switch are also reduced. • Comparative analysis highlights improvement in dynamic response of flyback converter.