SAM based Computational Analysis of Root Mean Square Error for SPES Using LR, RF & ARIMA Machine Learning Models

Renewable energy is crucial in addressing various global challenges like climate change, global warming, human development index, etc. To address these challenges, wind and solar energy are the mature technologies to harness green power. Integrating machine learning into the renewable energy sector can lead to more efficient, reliable, and sustainable energy systems. The work proposed for the solar photovoltaic energy system. The solar photovoltaic system of 500kW AC is simulated in the System Advisor Model (SAM). The data for annual energy generation is fetched to form the dataset. This dataset from SAM contains the hourly energy generation data for a particular year. The comparative analysis is proposed after mining the dataset. The machine learning algorithms are Linear Regression, Random Forest and ARIMA. To evaluate the performance of these algorithms, the statistical measure, namely Root Mean Square Error (RMSE), was used. The comparative analysis shows the effectiveness of the proposed work and its dataset for the machine learning algorithms.