Efficient energy management in smart home environments has become an important issue due to the increasing use of electrical devices and the demand for sustainable energy utilization. This study aims to predict household energy consumption using the Random Forest algorithm based on weather-related variables and historical energy usage data. The proposed model analyzes the relationship between environmental conditions, such as temperature and humidity, and energy consumption patterns to produce accurate predictions. Data preprocessing was conducted to improve data quality, followed by model training and performance evaluation using standard regression metrics. The experimental results indicate that weather factors significantly influence energy consumption and that the Random Forest model is capable of providing reliable prediction performance. In conclusion, the proposed approach can support the development of intelligent energy management systems in smart homes by providing predictive information that helps optimize energy usage and improve overall efficiency.
Copyrights © 2025