Poster Abstract: Predicting Occupancy Presence in Multiple Resolutions for Commercial Buildings

Providing comfort for occupants in commercial buildings accounts for a large proportion of worldwide energy consumption. There exists an opportunity to reduce energy waste by improving the scheduling of heating, ventilation, and air conditioning to deliver the required level of comfort only when rooms are occupied. However, to enable this potential, we require more flexible learning algorithms for predicting occupancy. This poster discuss design requirements for prediction algorithms and motivate their need to support multiple resolutions. As a case study, we outline the key elements of an algorithm fulfilling these requirements.