Energy management model for HVAC control supported byreinforcement learning

• Pedro Macieira ^[1] ; Luis Gomes ^[1] ; Zita Vale ^[1]
  1. [1] GECAD—Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development, Polytechnic of Porto (P.PORTO), P-4200-072 Porto, Portugal
• Localización: Artificial intelligence in the energy industry / Ana Belén Gil González (ed. lit.) , 2022, ISBN 978-3-0365-4605-6, págs. 83-96
• Idioma: inglés
• Enlaces
  • Texto Completo Libro (pdf)
• Resumen

  • Heating, ventilating, and air conditioning (HVAC) units account for a significant consumption share in buildings, namely office buildings. Therefore, this paper addresses the possibilityof having an intelligent and more cost-effective solution for the management of HVAC units inoffice buildings. The method applied in this paper divides the addressed problem into three steps:(i) the continuous acquisition of data provided by an open-source building energy managementsystems, (ii) the proposed learning and predictive model able to predict if users will be working in agiven location, and (iii) the proposed decision model to manage the HVAC units according to theprediction of users, current environmental context, and current energy prices. The results show thatthe proposed predictive model was able to achieve a 93.8% accuracy and that the proposed decisiontree enabled the maintenance of users’ comfort. The results demonstrate that the proposed solutionis able to run in real-time in a real office building, making it a possible solution for smart buildings.