Experimental Study on AI-Based Optimal Flow Control for the PVT-Integrated ASHP System

This study examines the use of an AI-based optimal flow control model to improve the energy efficiency of heating and cooling systems in modern buildings. Traditional flow control methods, such as On/Off control, are unable to adapt dynamically to changing environmental conditions, resulting in excessive energy consumption and inconsistent performance. To overcome this limitation, we developed and tested an AI-driven control system on a PVT-Integrated Air Source Heat Pump (PVT-ASHP) hybrid system in Busan, South Korea. Our real-scale experiments compared the performance of the AI-based control with conventional methods, focusing on key performance indicators such as cooling coefficient of performance (COP), energy savings, and system stability. The results showed that the AI-based model effectively optimized flow rates based on real-time environmental data, leading to a 12% reduction in energy consumption and a 14% improvement in cooling COP compared to traditional methods. These findings underscore the potential of AI-driven control strategies to enhance energy efficiency in buildings, contributing to the goals of carbon neutrality and zero-energy structures. Future research will aim to expand the adaptability of the AI model to various climate conditions.