Optimization of Smart Home Energy Consumption Using Machine Learning-Based Load Forecasting

The growing demand for energy efficiency in smart homes necessitates accurate short-term load forecasting to enable adaptive scheduling and optimal resource allocation. Traditional forecasting models, such as Random Forest, have demonstrated limited capability in capturing sequential dependencies, especially under fluctuating consumption behaviors typical of residential environments. This study aims to compare the forecasting performance of RF and Long Short-Term Memory (LSTM) models in predicting household energy consumption, to identify the most suitable approach for intelligent energy management systems. A quantitative experimental design was adopted using a publicly available dataset, which underwent preprocessing including time normalization and unit conversion. Both models were evaluated using Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) to assess forecasting accuracy. The LSTM model achieved a lower MAE of 3.2 and RMSE of 4.1, significantly outperforming the RF model, which recorded an MAE of 6.5 and RMSE of 8.4. Additionally, during peak load conditions, LSTM achieved 89.7% accuracy, compared to 72.4% for RF, further emphasizing its superior adaptability to time-sensitive variations. The results confirm that LSTM is more effective in modeling temporal patterns and handling volatility in household energy usage. This research contributes to the field by reinforcing the applicability of deep learning for real-time energy forecasting, offering valuable insights for the development of smart home systems. Future studies may expand this work by integrating hybrid optimization techniques and exploring multi-household scenarios for broader scalability.