2021/04/05 by Ghezlane Halhoul Merabet, Merabet, Ghezlane Halhoul, Mohamed Essaaidi +15
Energy · Engineering · Environmental Science · #Air Quality Monitoring and Forecasting #Artificial Intelligence (cs.AI) #Building Energy and Comfort Optimization #Energy Efficiency and Management #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Smart Grid Energy Management #Systems and Control (eess.SY) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2104.02214
openalex publication_date 2021/04/05 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Building operations represent a significant percentage of the total primary\nenergy consumed in most countries due to the proliferation of Heating,\nVentilation and Air-Conditioning (HVAC) installations in response to the\ngrowing demand for improved thermal comfort. Reducing the associated energy\nconsumption while maintaining comfortable conditions in buildings are\nconflicting objectives and represent a typical optimization problem that\nrequires intelligent system design. Over the last decade, different\nmethodologies based on the Artificial Intelligence (AI) techniques have been\ndeployed to find the sweet spot between energy use in HVAC systems and suitable\nindoor comfort levels to the occupants. This paper performs a comprehensive and\nan in-depth systematic review of AI-based techniques used for building control\nsystems by assessing the outputs of these techniques, and their implementations\nin the reviewed works, as well as investigating their abilities to improve the\nenergy-efficiency, while maintaining thermal comfort conditions. This enables a\nholistic view of (1) the complexities of delivering thermal comfort to users\ninside buildings in an energy-efficient way, and (2) the associated\nbibliographic material to assist researchers and experts in the field in\ntackling such a challenge. Among the 20 AI tools developed for both energy\nconsumption and comfort control, functions such as identification and\nrecognition patterns, optimization, predictive control. Based on the findings\nof this work, the application of AI technology in building control is a\npromising area of research and still an ongoing, i.e., the performance of\nAI-based control is not yet completely satisfactory. This is mainly due in part\nto the fact that these algorithms usually need a large amount of high-quality\nreal-world data, which is lacking in the building or, more precisely, the\nenergy sector.\n