Abstract:

Forecasting household energy consumption is challenging due to the diverse patterns of energy use. However, accurate predictions are essential for optimizing energy production and distribution in a sustainable and efficient manner. Researchers have developed artificial intelligence-based models to forecast energy demand, including Long Short-Term Memory (LSTM) models. With its capacity for accurately and quickly forecast load capacity, the LSTM model is useful for the early detection and handling of power system fault emergencies. The LSTM model is a promising approach that has the potential to improve the performance of power systems. In this paper, three houses consumption data of the January month has been considered and analysed by using LSTM. The results of actual consumption and predicted consumption are drawn by matplot in python which describes the effectiveness of the LSTM.

Description:

Load Forecasting, Long Short Term Memory, Time Series, Neural Network, Recurrent Neural Network