Enhancement of Power Quality of PV-Interfaced Distribution System Using Adaptive Backpropagation

There has been a significant increase in the level of worry regarding a degradation in the quality of the electricity that is supplied as a result of the growing integration of solar photovoltaic (PV) energy sources into the utility, particularly in the context of an inadequate distribution infrastructure. This concern has been brought about by the growth in the use of solar energy sources. As a consequence of this, the implementation of a reliable control mechanism is very important in order to improve the power quality of the solar energy conversion system that is linked to the grid. This work also addresses a adaptive backpropagation control for efficiently managing the system by supplying active power to the loads and leaving power to the grid. This is accomplished by feeding the active power to the loads. The control approach provides the capability to make adjustments to the weights in an autonomous and adaptive manner. As a consequence of this, it provides relief in model complexity, which is often present while dealing with irregular grid situations, in addition to a reduction in the amount of computation time that is required. In addition, the neural network-based control technique offers greater accuracy as a result of the use of combinational neural structures during the estimation process. This is made possible by the fact that the approach is based on neural networks (NNs). In order to maximize the efficiency with which the solar photovoltaic array is used, an incremental conductance-based maximum power point tracking technique is utilized. In order to verify the functioning of the system, the results of simulations are used to assess the performance of the recommended system.