Solar Monitoring and Controlling Application using Light Dependent Resistor
DOI:
https://doi.org/10.57041/mms2rs57Keywords:
Artificial intelligence, machine learning, neural network, image processingAbstract
Highly efficient solar panel operations are possible via a real-time sun-tracking orientation, which always allows and rotates the panels to the sun’s direction. Even though conventional methods trace the sun with microcontrollers and LDR sensors, they perform the function with minimal effectiveness because of low sensitivity and light interference. This paper introduces a new method that couples the principles of sensor systems and image processing, in which an automatic solar tracker is designed. Through using image processing software, the system combines processed sun images with sensor data to bring an effective functionality for solar panel self-orientation. Considering both hardware and system software, this approach is better for the photo voltaic power in terms of reliability and efficiency. It can carry out this task perfectly; it can simply manage different panels within a power plant, while on the other hand, it can ensure the best utilization of energy. Whereas microcontrollers are now being employed and sensors with limited effectiveness as measured by LDR are pervasively used, our proposed method employs the interaction of LDR sensors and image processing in a well-organized and effective manner. Unlike previous systems, this intelligent device provides an improvement on the solar tracking method through the real-time combination with data from sensors and sun images, presenting the flawless guidance of a vast number of solar panels in solar power stations.Downloads
Published
2024-06-28
Issue
Section
Articles
License
Copyright (c) 2024 https://grsh.org/journal1/index.php/jaic/cr
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
How to Cite
Solar Monitoring and Controlling Application using Light Dependent Resistor. (2024). Journal of Artificial Intelligence and Computing, 2(1), 19-22. https://doi.org/10.57041/mms2rs57