Balancing indoor thermal comfort and energy consumption of air-conditioning and mechanical ventilation systems via sparse Firefly algorithm optimization

The issue of diminishing global energy resources has been of significant concern in recent years. One of the most energy hungry components is the Air-Conditioning and Mechanical Ventilation (ACMV) Systems for buildings, which consumes more than 40% of the total building energy consumed on average. Since people are spending more time staying indoor, the indoor environmental conditions have to be taken into special considerations. One of the most important aspects for indoor environmental conditions is occupants' thermal comfort sensations. Occupants will be more productive and healthy with good indoor thermal comfort sensations. In this research, we will introduce the Extreme Learning Machine (ELM) networked models of energy consumption with indoor air temperature and velocity as two main subjects of investigation. Then, a swarm-type sparse Firefly Algorithm (FA-MSE regression) is developed for ACMV optimizations of balancing both thermal comfort sensations and energy consumption. The numerical results show that the recommended optimizations could potentially save up to 16% of energy consumption of an experimental ACMV system in the thermal laboratory of the Nanyang Technological University, Singapore.