Prediction of Voltage Generation in Triboelectric Nanogenerator Using Machine Learning Algorithms

The rapid evolution of solar panels towards greener energy has paved the way for eco-friendly renewable energy generation. However, the effective management of disposed solar cells is an important factor to consider in reducing adverse environmental and health consequences. Hence, the novel based Triboelectric Nano generators are fabricated from waste solar cells and waste chocolate wrappers. The TENG harnesses frictional energy from the contact between the materials, converting it into useful electrical power. This innovative system promotes the efficient utilization of discarded resources, contributing to both renewable energy generation and waste reduction. As a result, the current work offers a realistic technique for gathering electricity and represents a major step in mitigating the difficulties associated with disposing of solar cell waste. The output voltage generation by the TENG is predicted using various Machine learning algorithms. The predictive model performance is also analyzed through various metrics such as Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE).