Long-Term Solar Power Generation Forecasting at Eastern West Large Scale Solar (LSS) Farm using Random Forest Regression (RFR) Method

Abstract

Precise forecasting of power generation and demand is essential for effective resource allocation and energy trading in contemporary energy systems. Power forecasting accuracy has increased dramatically since Random Forest Regression (RFR) techniques were used. The study's primary objective is to forecast electricity generation in Malaysia's Eastern West region, with a concentration on solar energy. The research process entails gathering and examining pertinent factors, weather information, and historical power data. To evaluate the accuracy and predictive potential of RFR models, a specific power grid is used for training, validation, and testing. One of the anticipated results is the creation of an accurate model for power generation predictions, which will help to optimise energy operations and smoothly incorporate renewable sources. The paper examines the advantages, disadvantages, and best practices related to RFR-based power forecasting. The dataset, which spans the years 2019 to 2023, includes 30-minute interval records for the following variables: average output power, ambient temperature, PV module temperature, global horizontal irradiance, and wind speed. Using the RandomForestRegressor class from the scikit-learn library, the RFR model is implemented. In order to assess the model's overall fit, average deviation, and sensitivity to outliers, measures such as root mean square error (RMSE), mean square error (MSE), and mean absolute error (MAE) are used on the test set. The temperature, irradiance, and AC power output of PV modules are found to be strongly correlated.