BauSIM 2014 - Sep, 2014


Title of the Conference/Workshop: BauSIM 2014

Location: Aachen, Germany

Dates: 22nd-24th September, 2014

url: http://bausim2014.ibpsa-germany.org/eng/index.php

 

Brief description of the conference:

BauSIM 2014 conference was held in the Aachen University, Germany, during the days 22nd, 23rd and 24th of September 2014. BauSIM is a regional conference which combines plenary and parallel sessions, as well as wrokshops. The main topic of this year has been "Human-centred buildings" that discusses about the fact of the buildings are neither planned nor built to save energy, but are mainly designed to provide living and working spaces, a healthy indoor environment where people can comfortably live and work together in a productive manner. Nevertheless, it is important to save energy and fossil fuels by means of renewable sources, for instance. For this aim, the humans as occupants play a pivotal role.

 

Campus21 publications


Explore the predictive potential of probabilistic occupancy models

 

Abstract

Building performance is influenced by occupants' presence and actions. Knowledge of occupants' future presence and behavior in buildings is of central importance to the implementation efforts concerning predictive building systems control strategies. Specifically, prediction of occupants' presence in buildings represents a necessary condition for predicting their interactions with building systems. In the present contribution, we focus on evaluation of probabilistic occupancy models to explore the potential of using past monitored data in predicting future presence of occupants. Toward this end, we selected a university campus office area, which is equipped with a monitoring infrastructure and includes a number of open and closed offices. For the purpose of this study, we used monitored occupancy data and two previously developed stochastic occupancy models to predict the occupancy profiles on a daily basis. The predictions were then evaluated via comparison with monitored daily occupancy profiles. To conduct the model evaluation in a rigorous manner, a number of specific evaluation statistics were deployed. Thus, the results facilitate a discussion of the potential and limitations of predicting building occupants' future presence patterns based on past monitoring data.