Optimizing an HVAC System with AI Integration and Phase Change Materials for Sustainable Energy Performance

This paper presents the design and the implementation of a self-regulating HVAC system that integrates Artificial Intelligence (AI) with Phase Change Materials (PCMs) to improve the energy efficiency and occupant comfort in buildings. The system dynamically adjusts the HVAC load by processing real-time environmental data, including indoor temperature, relative humidity, CO2 concentration, and external weather conditions. A supervised machine learning model was developed and trained to predict the optimal HVAC power levels while reducing unnecessary energy consumption. The integration of PCMs in building envelopes contributes passively by storing and releasing thermal energy, thereby lowering peak heating and cooling demands. Simulations were conducted using Energy Plus to compare three configurations: a traditional system, a PCM-enhanced system, and the proposed AI+PCM integrated system. Results showed a 30% marked reduction in annual energy consumption for the AI-controlled system, confirming its effectiveness in balancing comfort and efficiency.