AI-Driven Climate Based Control and Energy Analytics for Smart Buildings

With the ever-increasing demands on energy usage in modern buildings, there has emerged the need for intelligent and efficient energy management systems that will be able to optimize resource use without compromising occupant comfort. This study introduces a novel framework for climate-based control and energy analytics in smart buildings using Internet of Things sensors and AI-based predictive analytics for adaptive energy management. Real-time environmental data collection and intelligent decision support were used to optimize lighting, ventilation, and climate control systems' operations in dynamic environments. In this regard, the proposed framework applied a hybrid control approach that integrated automatic control based on sensor readings and predictive analytics to minimize unnecessary operation of appliances, hence promoting energy efficiency. Performance evaluation using traditional Full Load Mode and AI-Based Mode revealed that the proposed solution was more efficient in energy utilization compared to the existing systems. It was able to conserve about 30% of energy consumption, reducing power usage from 4311 mW to 2874 mW. Additionally, the proposed predictive analytics model showed an estimated operational efficiency of 85.51%.