Affiliations: [a]
Department of ECE, Saveetha School of Engineering, Saveetha Institute of Medical and Technical Science, Chennai, India
| [b]
Department of Electrical and Electronics Engineering at V.S.B. Engineering College, Karur | [c]
Electrical Engineering Department, King Khalid University, Abha, Saudi Arabia
| [d]
Department of Electrical and Electronics Engineering, Koneru Lakshmaiah Education Foundation, Vaddeswaram, AP, India
Correspondence:
[*]
Corresponding author. Dr. B. Jegajothi, Assistant Professor, Department of ECE, Saveetha School of Engineering, Saveetha Institute of Medical and Technical Science, Chennai-605102, India. E-mail: jegajothisudhakar@gmail.com.
Abstract: Because of environmental issues and energy crises, significant attention has been received in the domain of renewable and clean energy systems. Solar energy is the most effective source of renewable energy technologies. Recently, photovoltaic (PV) system have become common in grid-linked applications and plays a vital part in power production. MPPT algorithms enable PV systems to capture the maximum available power from the solar panels, regardless of variations in solar irradiance, temperature, and other environmental factors. By continuously tracking the MPP, MPPT techniques ensure that the PV system operates at its highest efficiency, resulting in increased energy harvesting and improved overall performance. Meanwhile, the frequent modifications in irradiance and temperature pose a major challenging issue which can be resolved by the use of artificial intelligence MPPT methodologies like artificial neural networks (ANN), fuzzy logic (FL), and metaheuristics systems. In this aspect, this work presents a new quasi-oppositional artificial algae optimization (QOAAO) with an adaptive neuro-fuzzy inference system (ANFIS) technique, named QOAAO-ANFIS for maximum efficiency MPPT technique for minimizing the present ripple and power oscillations over the MPP. The presented QOAAO-ANFIS model mainly depends upon the integration of the ANFIS and QOHOA techniques. In addition, the presented QOAAO-ANFIS model involves optimal MF selection of the ANFIS model to estimate the irradiation level and compute PV voltage equivalent to maximal power point. The QOAAO model can be utilized for enhancing the optimization process of membership function variables under varying conditions and awareness of global optima. The simulation result analysis of the QOAAO-ANFIS model takes place in terms of different evaluation measures. Extensive comparative results reported the better performance of the QOAAO-ANFIS model with maximum tracking efficiency of 99.89% and a minimum convergence time of 13.51 ms.
Keywords: Membership function, photovoltaic systems, maximum power point tracking, artificial intelligence, fuzzy logic controller
