An Improved Voltage Regulation in DC Smart Grid Using Machine Learning

The power generation from solar photovoltaic is variable in nature, and may contain unacceptable fluctuations so in current use the renewable energy is stored in the battery or super capacitors to use it later but it requires high maintenance charge. The main idea for the proposed work is to regulate the renewable power during the fluctuation to give uninterrupted power supply. The continuous monitoring of power generation from solar is carried out by machine learning model using KNN algorithm and simultaneously the load consuming values are again sent to machine learned model to classify the switching status of regulator circuit. Using Thonny software, the dataset is fed to the model and all these AI process is done in Python Platform. Hardware implementation for the same is used with 1200 W solar panel and for the load variation, three LED’s are used. Panel when exposed to sunlight, solar power is utilized using BUCK converter and when no light falls on the panel, the SMPS supply the LED switching from solar power to DC rectifier.