Optimization of air supply parameters for predicting indoor temperature and humidity under indoor mold index constraints

Abstract

This study introduces a framework for optimizing MVAC air supply settings to reduce mold growth, improve energy efficiency, and maintain occupant comfort. It combines a predictive model for indoor temperature and humidity with a Non-dominated Sorting Genetic Algorithm III (NSGA-III) for optimization. Historical data is used to predict conditions at ceiling points, while the optimization process considers energy consumption, PMV (Predicted Mean Vote), and the VTT mold index. Comparing the ideal point method and the TOPSIS method, the former proves more effective for air supply optimization. The study highlights the importance of including the VTT mold index in optimization strategies, achieving an 88% improvement in mold control and a 74.74% improvement in thermal comfort. This framework offers a more sustainable and efficient approach to building management through data-driven optimization.