A Study of Electric Load Forecasting Technique Using LSTM Model

Electric load forecasting is crucial for efficiently operating and planning electrical power systems. Accurate load forecasts can lead to improved resource management, reduced operational costs, and enhanced reliability of power supply. This study discusses forecasting techniques. Finally, employ a Long Short-Term Memory (LSTM) model, a type of Recurrent Neural Network (RNN), to predict electrical load based on historical load data and additional factors such as temperature, humidity, and public holidays. The results demonstrate the effectiveness of LSTM in capturing the temporal dependencies and trends in load data, leading to high forecasting accuracy. The LSTM model achieves a Mean Absolute Percentage Error (MAPE) of less than 10%, indicating its robustness and reliability in predicting electrical load.