Integrating artificial intelligence with building information modeling for low-carbon indoor environment optimization

Abstract This research proposes a method that integrates artificial intelligence with building information modeling (BIM) to optimize low-energy indoor environments. Based on heating, ventilation, and air conditioning (HVAC) operational data, an enhanced adaptive neuro-fuzzy inference system (ANFIS), fortified by an improved ant colony optimization (ACO) algorithm, is employed to predict indoor temperature and energy consumption in a library setting. This approach utilizes the ACO algorithm and least squares method for parameter optimization, constructing predictive models for energy consumption and indoor temperature. The effectiveness and superiority of this method in predictive capability are validated through comparisons with traditional models.