Enhancement of solar energy utilization through an artificial neural network controller featuring a dynamic learning rate in conjunction with an ultra-lift Luo converter
Department of Electrical and Computer Engineering, Prairie View A&M University, Prairie View, TX, USA.
Research Article
World Journal of Advanced Engineering Technology and Sciences, 2024, 12(02), 751–761.
Article DOI: 10.30574/wjaets.2024.12.2.0346
Publication history:
Received on 03 July 2024; revised on 13 August 2024; accepted on 15 August 2024
Abstract:
With the growing need for sustainable energy solutions, optimizing photovoltaic (PV) systems becomes crucial. PV systems, while effective, are subject to efficiency fluctuations due to varying irradiance and temperature, posing significant challenges in maintaining optimal performance. This study explores the enhancement of PV systems by integrating an Ultra Lift Luo (ULL) converter with an Artificial Neural Network (ANN) controller using a dynamic learning rate. The ULL converter, known for its high voltage conversion gain, is suitable for various load requirements in PV systems. The ANN controller, equipped with a dynamic learning rate, adapts in real-time to changes in environmental conditions, ensuring superior performance compared to static learning rate methods. This dynamic approach allows the ANN to efficiently manage non-linear and variable inputs from the PV cells, optimizing the Maximum Power Point Tracking (MPPT) process. Our research involved simulating the PV system model using MATLAB/Simulink, incorporating the ULL converter and ANN controller using dynamic learning rate. The study compared the performance of the ANN controller with dynamic learning rate against a static learning rate approach, using 201 data samples for training. The dynamic learning rate not only enhances adaptability but also provides more stable voltage and power outputs under varying irradiance and temperature conditions. These results demonstrate the potential of dynamic learning rates in optimizing PV system performance, highlighting their role in advancing renewable energy technologies.
Keywords:
Artificial neural network; Dc-dc Ultra lift luo converter; Dynamic learning rate; Maximum power point tracking; photovoltaic system; Static learning rate
Full text article in PDF:
Copyright information:
Copyright © 2024 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0