Abstract

This paper presents a long short-term memory neural network model for forecasting energy consumption based on time series data. The study evaluates the LSTM model's ability to capture temporal dependencies and seasonal patterns in energy usage data collected from smart meters. The proposed model is compared with traditional forecasting methods including ARIMA and linear regression, demonstrating superior performance in terms of prediction accuracy and adaptability to fluctuating consumption patterns. The findings support the use of LSTM networks as an effective tool for energy management and planning in smart grid environments.