An approach for building occupancy modelling considering the urban context

Building occupancy, which reflects occupant presence, movements and activities within the building space, is a key factor to consider in building energy modelling and simulation. Characterising complex occupant behaviours and their determinants poses challenges from the sensing, modelling, interpretation and prediction perspectives. Past studies typically applied time-dependent models to predict regular occupancy patterns for commercial buildings. However, this prevalent reliance on purely time-of-day effects is typically not sufficient to accurately characterise the complex occupancy patterns as they may vary with building's surrounding conditions, i.e. the urban environment. Therefore, this paper proposes a conceptual framework to incorporate the interactions between urban systems and building occupancy. Under the framework, we propose a novel modelling methodology relying on competing risk hazard formulation to analyse the occupancy of a case study building in London, UK. The occupancy profiles were inferred from the Wi-Fi connection logs extracted from the existing Wi-Fi infrastructure. When compared with the conventional discrete-time Markov Chain Model (MCM), the hazard-based modelling approach was able to better capture the duration dependent nature of the transition probabilities as well as incorporate and quantify the influence of the local environment on occupancy transitions. The work has demonstrated that this approach enables a convenient and flexible incorporation of urban dependencies leading to accurate occupancy predictions whilst providing the ability to interpret the impacts of urban systems on building occupancy. •Model of interactions between occupancy behaviour and urban systems is proposed.•Competing risk hazard model is used to operationalise the model using Wi-Fi logs.•The hazard model flexibly captures dependence of transition probability on duration.•The model helps gain insights into exogenous effects on occupancy behaviour.•Compared to MCM, hazard model better predicts occupancy with flexible work agendas.