This article proposes a Hermite function-based artificial neural network (HeANN) controller for shunt compensation in photovoltaic (PV) interfaced grid system. Various power quality (PQ) issues such as load change, poor power factor, reactive power demand and current harmonics are experienced by 1; distribution system. The proposed HeANN algorithm is utilized to improve the PQ issues of the distribution system. Shunt active power filter (SAPF) is operated in current control mode and injects the compensating current at the point of common coupling (PCC). The inverter is connected with the green energy resource, that is, PV at its direct current terminals and contributes its power to fulfil the load active power demand. The parameters of HeANN are trained in real time. A prototype hardware of SAPF is developed using sensor circuits and space 1104. The simulation results are validated by experimental results. The comparative analysis of the results establishes the superiority of the proposed control technique to other control techniques such as synchronous reference frame, second order generalized integrator and back propagation neural network in terms of convergence, computational burden and total harmonic distortion of grid current.
Summary
This paper discusses the performance of the Bernoulli Polynomial‐based artificial neural network (BePANN) for the control of a single‐phase grid‐integrated solar photovoltaic (PV) system. A single‐phase, single‐stage topology of a grid‐integrated PV system is utilized to feed nonlinear loads at the point of common coupling. The fundamental load component is extracted from distorted load current using a single‐layer neural network. There are several control techniques mentioned in the literature for load compensation. However, many techniques show slower convergence response, higher oscillations, and a large computational burden. The designed BePANN controller attenuates harmonic components from nonlinear current and improves the power quality (PQ) under normal and distorted grid conditions. The single‐layer BePANN control has a simplified structure based on several polynomial terms; this reduces the computational burden and complexity of the controller. The objective of the designed controller is to fulfill the load's active power demand from the generated solar PV power and feed the excess power back to the grid when surplus. When solar PV is not integrated with the grid, the voltage source converter acts as a distribution static compensator, improving the system's utilization factor. The proposed control technique is simulated in MATLAB Simulink, and results are experimentally verified through laboratory prototype under normal and abnormal grid conditions. The application of higher order polynomials for PV‐integrated systems with multifunctional PQ capabilities has been implemented for the first time in this article. The main outcomes of the proposed control technique are solving current‐related PQ issues and reactive power compensation and providing improved power factor under both normal and distorted polluted grids.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.