Applying Robust Intelligent Algorithm and Internet of Things to Global Maximum Power Point Tracking of Solar Photovoltaic Systems

Abstract

The important dare in the solar photovoltaic (PV) system is to investigate the performance under partial shading conditions. A robust intelligent algorithm (RIA) connected with internet of things (IoT) is developed to offer the real-time monitoring of solar PV systems, thus ensuring global maximum power point tracking (MPPT). The RIA comprises a limited-time terminal sliding-mode control (LTTSMC) and a quantum particle swarm optimization- (QPSO-) radial basis function (RBF) neural network. The LTTSMC creates a quick limited-system-state convergence time and allows for singularity avoidance. However, if the system ambiguity is overrated or underrated, the tremble phenomenon or steady-state error probably occurs around the LTTSMC. The QPSO-RBF neural network is integrated into LTTSMC to handle plant parameter variations and external load perturbations, thus reducing tremble and steady-state errors. With the aggregation of the RIA and the IoT, the remote monitoring in the solar PV system yields faster convergence to nonsingular points, and it also introduces neural network method to achieve more accurate ambiguity estimation. Experimental results show the mathematical analysis and performance enhancement of a prototype algorithm-controlled solar PV system based on digital signal processing under transient and steady-state loading conditions. Because the proposed solar PV system has notable advantages over the classical terminal-sliding solar PV system in terms of tracking accuracy and robust adaptation, this paper is worthy of reference to designers of relative robust control and neural network learning algorithm.