A three-phase NPC grid-connected inverter for photovoltaic applications using neural network MPPT. (September 2015)

• Record Type: Journal Article
• Authors: Boumaaraf, Houria; Talha, Abdelaziz; Bouhali, Omar
• Is Part Of: Renewable & sustainable energy reviews. Volume 49(2015:Sep.)
• Page Start: 1171
• Page End: 1179
• Publication Date: 2015-09
• Subjects: MPPT -- Buck-Boost -- Grid -- Multilevel -- Neural network; Renewable energy sources -- Periodicals; Power resources -- Periodicals; Énergies renouvelables -- Périodiques; Ressources énergétiques -- Périodiques; 333.794
• DOI: 10.1016/j.rser.2015.04.066
• Languages: English
• ISSNs: 1364-0321

Abstract

Abstract: The overall efficiency of a grid-connected photovoltaic power generation systems depends on the efficiency of the DC-into-AC conversion. This paper presents a comparative study of the performances of a photovoltaic (PV) system connected to the grid using two different inverters namely the two-level inverter and the three-level Neutral Point Clamped (NPC) Voltage Source Inverter (VSI). For the grid connected it is desirable to provide the unity power factor and a less output harmonic voltage. To generate the maximum power from a photovoltaic generator in the environmental changes, a new Neural Network Maximum Power Point Tracking 'NN-MPPT' controller is developed. The fuzzy logic controller MPPT is used to generate the training data bases of the NN-MPPT. Simulation results carried out using Matlab-Simulink to highlight the performance of the proposed scheme based on a three-level NPC-VSI and the proposed NN-MPPT controller.