Harnessing the sun: Framework for development and performance evaluation of AI-driven solar tracker for optimal energy harvesting
This research explores advanced methodologies to enhance the performance and efficiency of solar tracking systems by developing the Solar Tracking and Analysis Research (S.T.A.R.) framework. The study begins with designing and implementing both open and closed loop solar tracking systems, collecting...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-04-01
|
| Series: | Energy Conversion and Management: X |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2590174525001229 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | This research explores advanced methodologies to enhance the performance and efficiency of solar tracking systems by developing the Solar Tracking and Analysis Research (S.T.A.R.) framework. The study begins with designing and implementing both open and closed loop solar tracking systems, collecting energy generation data over a year with daily measurements spanning ten hours. The second phase involves a comprehensive analysis of these systems under various weather conditions, identifying their strengths and weaknesses to identify potential improvements. The research identifies inefficiencies through rigorous design, testing, and analysis and proposes enhancements, driving optimization. These insights are integrated into a Multi-Objective Genetic Algorithm Adaptive Neuro-fuzzy Inference System (MOGA ANFIS), optimizing the solar tracking process using diverse solar tracking and environmental variables. The critical objective is optimizing the tilt and azimuth angles of solar panels to enhance energy generation potential. The study compares theoretical and experimental energy generation data from the AI-based solar tracker against conventional systems, thoroughly evaluating its effectiveness. Results demonstrate that the AI-based system, guided by MOGA ANFIS, consistently outperforms traditional systems across different weather conditions, with R2 values of 0.989 for azimuth and 0.998 for altitude angle predictions, highlighting its superior adaptability and efficiency. Experimentally, the proposed system can generate 27 % and 20 % more energy than the open and closed loop systems, respectively, and has the potential to generate 57 % more energy than fixed panels. This research significantly contributes to the field of renewable energy, particularly in solar tracking technologies. |
|---|---|
| ISSN: | 2590-1745 |