Abstract:
Energy is now becoming one of the key factors of modern civilization. In
our daily lives, it enables comfort and sustainability, despite the electricity
demand still facing challenges in generation. Machine learning (ML) techniques
are becoming crucial for optimizing the performance of solar energy harvesting
systems to overcome this problem. The main purpose is to develop a model for a
supervised ML-based maximum power point tracking (MPPT) control system
utilizing a neutral point clamped (NPC) converter, ensuring a reliable power
supply under varying operational and environmental conditions. This study
investigates a neural network (NN) based Levenberg-Marquardt (LM) train
algorithm to extract the MPPT power generation in the grid-connected solar
photovoltaic (PV) system with the NPC converter model and explore the
performance of energy management systems. Utilizing MPPT, we enhance the
efficiency of the proposed solar system. It investigates the battery operation
strategies under different loading conditions. To evaluate the NPC converter, we
suggested a space vector pulse width modulation (SV-PWM) technique of 15%
to enable control of the DC link neutral point voltage, thereby adjusting
switching states and reducing operational loss. The system performance
demonstrates high tracking efficiency, reduces oscillation, facilitates smooth load
switching, and improves power quality with an effective energy storage system.
The results indicate that the Hybrid (P&O, NN) MPPT is superior (96% efficiency)
at energy harvesting, while the outperformed LM-based NN MPPT is better
(SOC range ~ 45.0042%) at energy storage. The proposed framework offers a
reliable and efficient solution for modern grid-connected PV systems with energy
storage.
