This study focuses on the development of an electrical demand forecasting model using machine learning techniques, specifically Long Short-Term Memory (LSTM) and eXtreme Gradient Boosting (XGBoost), and uses data collected from wireless sensors installed in the city.
This study focuses on the development of an electrical demand forecasting model using machine learning techniques, specifically Long Short-Term Memory (LSTM) and eXtreme Gradient Boosting (XGBoost). The objective is to provide accurate forecasts for microgrids to prepare for upcoming loads due to temperature changes in the city. The study uses data collected from wireless sensors installed in the city. The LSTM and XG Boost models were trained and tested using historical data, and the results were compared to select the best-performing model. The chosen model was then used to forecast the electrical demand for the upcoming period.