PROJECT TITLE :

Artificial Neural Network for Control and Grid Integration of Residential Solar Photovoltaic Systems - 2017

ABSTRACT:

Residential solar photovoltaic (PV) energy is becoming an increasingly vital part of the globe's renewable energy. A residential solar PV array is usually connected to the distribution grid through a single-phase inverter. Control of the one-section PV system should maximize the power output from the PV array whereas guaranteeing overall system performance, safety, reliability, and controllability for interface with the electricity grid. This paper has 2 main objectives. The first objective is to develop a man-made neural network (ANN) vector management strategy for an LCL-filter based mostly single-part solar inverter. The ANN controller is trained to implement optimal control, based on approximate dynamic programming. The second objective is to guage the performance of the ANN-based solar PV system by simulating the PV system behavior for grid integration and most power extraction from solar PV array in a very realistic residential PV application and building an experimental solar PV system for hardware validation. The results demonstrate that a residential PV system using the ANN control outperforms the PV system using the standard customary vector management method and proportional resonant management method in both simulation and hardware implementation. This is additionally true in the presence of noise, disturbance, distortion, and nonideal conditions.