Electricity Demand Forecasting Using LightGBM Machine Learning Algorithm
Authors/Creators
- 1. 1 #1 Jharkhand University of Technology, Ranchi, India,
Description
ABSTRACT
Accurate electricity demand forecasting plays a crucial role in modern power system operation and planning. Reliable predictions enable utilities to optimize power generation scheduling, reduce operational costs, and improve grid stability. However, electricity demand patterns are highly dynamic and influenced by factors such as weather conditions, seasonal variation, population growth, and consumer behavior. Traditional statistical forecasting models often struggle to capture complex nonlinear relationships present in electricity consumption data. Machine learning techniques have recently gained popularity due to their ability to analyze large datasets and model nonlinear patterns effectively. This study proposes an electricity demand forecasting model using the Light Gradient Boosting Machine (LightGBM) algorithm. LightGBM is an efficient gradient boosting framework that provides high prediction accuracy with faster training speed. Historical electricity demand data along with weather variables are used to train the model. The forecasting performance is evaluated using Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE). The results demonstrate that the LightGBM model provides accurate and reliable electricity demand predictions and can support intelligent energy management systems.
Key words: Electricity Demand Forecasting, LightGBM, Machine Learning, Smart Grid, Energy Prediction.