Artificial Neural Networks in MPPT Algorithms for Optimization of Photovoltaic Power Systems: A Review.

César G Villegas-Mier,Juvenal Rodriguez-Resendiz,Omar Rodríguez-Abreo,Hugo Rodriguez-Resendiz,José M Álvarez-Alvarado,Ana Marcela Herrera-Navarro

doi:10.3390/mi12101260

César G Villegas-Mier, Juvenal Rodriguez-Resendiz + Show 4 more

Open Access

https://doi.org/10.3390/mi12101260

Copy DOI

Journal: Micromachines	Publication Date: Oct 17, 2021
Citations: 74	License type: CC BY 4.0

Affiliation: Autonomous University of Queretaro

Abstract

The use of photovoltaic systems for clean electrical energy has increased. However, due to their low efficiency, researchers have looked for ways to increase their effectiveness and improve their efficiency. The Maximum Power Point Tracking (MPPT) inverters allow us to maximize the extraction of as much energy as possible from PV panels, and they require algorithms to extract the Maximum Power Point (MPP). Several intelligent algorithms show acceptable performance; however, few consider using Artificial Neural Networks (ANN). These have the advantage of giving a fast and accurate tracking of the MPP. The controller effectiveness depends on the algorithm used in the hidden layer and how well the neural network has been trained. Articles over the last six years were studied. A review of different papers, reports, and other documents using ANN for MPPT control is presented. The algorithms are based on ANN or in a hybrid combination with FL or a metaheuristic algorithm. ANN MPPT algorithms deliver an average performance of 98% in uniform conditions, exhibit a faster convergence speed, and have fewer oscillations around the MPP, according to this research.

Highlights

Published: 17 October 2021The consumption of electrical energy has intensified significantly due to the massive increase in the world population
There is no significant difference between the two algorithms, a slightly higher amount of power is delivered to the battery by the Perturbation and Observation (P&O) algorithm than that supplied by the Artificial Neural Networks (ANN)
Neuro-control is nothing new, it continues to have a powerful impact in recently booming areas such as renewable energy, with a particular emphasis on PV

Summary

Introduction

The consumption of electrical energy has intensified significantly due to the massive increase in the world population. The use and application of renewable energy solve one of the concerns of the global community. Photovoltaic (PV), in particular, generates light and electricity from the sun’s energy [4], is expanding rapidly due to supportive policies by governments and, recently, the drastic reduction in its cost [5]. It is a reliable and commercially available technology with significant long-term growth potential in almost all world regions. The Organisation for Economic Co-operation and Development (OECD) estimates that by 2050, PV systems could provide about 12% of global electricity production and avoid emitting 2.3 Gigatonnes of carbon dioxide into the atmosphere each year [6,7]

Objectives

Findings

Discussion

Conclusion