;With the advancement of smart technologies, AI-powered and IoT-enabled home appliances have been widely adopted, allowing real-time remote control and energy management. These smart devices can be integrated into building energy systems to monitor electricity consumption patterns and promote efficient usage. Given that the building sector accounts for over one-third of global energy consumption and nearly 40% of carbon emissions, reducing household energy demand is a pressing global challenge. This study proposes an energy forecasting framework that combines household electricity data with building energy models. It adoptsFlaskas a lightweight system interface and utilizes TensorFlow deep learning to predict short-term energy usage trends, improving accuracy and operational efficiency over traditional methods. To enhance user engagement and the practicality of predictions, a neighborhood clustering approach is introduced, enabling peer comparison and encouraging energy-saving behavior through social influence. The system supports real-time monitoring and informed energy decisions. This research contributes to smart energy management, facilitates renewable energy adoption, and aims to flatten demand peaks. Ultimately, it supports carbon reduction goals while promoting a sustainable and comfortable living environment.
