SMART ENERGY OPTIMIZATION IN URBAN BUILDINGS USING AI AND IOT SENSOR ANALYTICS

Abstract

Smart homes, equipped with intelligent sensors and automation systems, offer substantial opportunities to optimize energy usage while enhancing occupant comfort. This study explores the influence of external weather conditions on energy consumption patterns in smart residential environments. The dataset spans 4.5 months and includes temperature and humidity readings captured via ZigBee-based wireless sensor networks, alongside energy usage data collected through m-bus energy meters. Supplementing this with meteorological data from Chievres Airport in Belgium allows for a comprehensive analysis of the correlation between environmental factors and household energy behavior. Traditional energy management systems typically operate on static schedules and historical usage patterns, making them ill-equipped to adapt to real-time weather fluctuations, which often results in suboptimal energy efficiency and increased operational costs. To address these challenges, this research proposes a data-driven approach using regression analysis to model the dependency between weather parameters and energy consumption. By leveraging predictive modeling, the system aims to forecast energy demand in response to changing weather conditions, enabling dynamic control of HVAC and other high-consumption appliances. This adaptive strategy enhances energy efficiency, reduces waste, and supports sustainable urban living. The findings from this study contribute to the advancement of intelligent energy management in smart homes, offering scalable solutions for future eco-friendly residential infrastructure.