An Integrated System for Monitoring & Control of Solar Panel using IoT & Machine Learning
The proper monitoring and control of solar panels using IoT and machine learning are discussed in this paper. The use of green energy sources like solar power is expanding due to rising electricity costs and worries about the impact of fossil fuels on the environment. But the static position of the solar panel, improper cleaning system & undetected faults may widely affect the total output generated from the solar panel. The efficiency of an array's energy generation is greatly diminished by the buildup of dust and debris on even an individual panel, emphasizing the necessity of keeping the panel's surface as clean as possible. The intention of our project is to create an extensive structure for performance evaluation, automated cleaning, tracking, and fault detection. The dual-axis trackers can give 40% more electricity than a non-moving solar panel. Automated water jet cleaning keeps panels always clean with regularly scheduled cleanings and requires no human labor after installation. The faults that occur on the solar panel are identified by using image detection techniques, in image detection techniques machine learning algorithms are used. Using machine learning algorithms can detect the presence of faults and causes of faults like micro-cracks, hotspots, dust accumulation, snow covering, shading, and so on. The proposed system can enhance customer satisfaction and will help to improve operational efficiency and more economical and easier to analyze performance.
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.