Enhancing IAQ, thermal comfort, and energy efficiency through an adaptive multi-objective particle swarm optimizer-grey wolf optimization algorithm for smart environmental control

People in modern societies spend most of their time in buildings, and a considerable amount of energy is used to maintain indoor air quality (IAQ) and thermal comfort levels to ensure people's health and productivity. Thus, to ensure the energy efficiency of buildings, smart environmental control must be implemented through prediction and optimization based on artificial intelligence (AI) algorithms. However, rapid and accurate environmental control based on comprehensive consideration of IAQ, thermal comfort, and energy savings remains to be accomplished. Therefore, this paper describes the development and application of a multi-objective AI algorithm that can be deployed in practical environmental control to rapidly and accurately optimize the IAQ, thermal comfort levels, and energy efficiency of buildings. First, a database of indoor airflow and temperature distribution is established through computational fluid dynamics (CFD) simulations and chamber experiments. Then, with the database, the back-propagation neural network (BPNN) model is created to rapidly predict air pollution concentrations and thermal comfort levels. If these predictions using the BPNN model do not satisfy the setup requirements, an adaptive multi-objective particle swarm optimizer-grey wolf optimization (AMOPSO-GWO) algorithm is used to identify the optimal strategy for maximizing indoor air quality, thermal comfort levels, and energy saving. The results demonstrate that the BPNN-based AMOPSO-GWO algorithm has high predictive accuracy (>90%). The mean reduction in air pollution concentrations, increase in thermal comfort levels, and average energy savings are 31%, 45%, and 35%, respectively.