GHI Prediction Based on Weather Data Using Machine Learning

The proposed model aims to predict Global Horizontal Irradiance (GHI) by using various environmental factors and several Machine Learning algorithms like Linear Regression, Decision Tree, Recurrent Neural Network (RNN), Random Forest, Long Short Term Memory(LSTM), Support Vector Machine(SVM), and Light Gradient Boosting Machine(GBM). The dataset is preprocessed, and relevant features are selected for the model. The linear regression model is implemented using gradient descent to optimize the weights and bias without importing it from Python libraries. The cost function is minimized over multiple epochs, and the convergence is visualized. The trained model is then used to make predictions on a test set. Several performance metrics, such as MSE, RMSE, and
$\mathbf{R}^{2}$
, are calculated to evaluate the model's accuracy. The code combines data preprocessing, model training, and evaluation, providing a comprehensive overview of the predictive modeling process for solar irradiance.