Towards a general framework for an observation and knowledge based model of occupant behaviour in office buildings

TL;DR

This paper introduces a Bayesian network-based framework to model occupant behavior in office buildings, integrating expert knowledge and observations to improve co-simulation accuracy of indoor CO2 levels.

Contribution

It presents a novel probabilistic approach combining expert knowledge and observational data within Bayesian networks for occupant behavior modeling.

Findings

Effective co-simulation of building physics and behavior

Improved accuracy in CO2 concentration prediction

Integration of probabilistic cause-effect relations

Abstract

This paper proposes a new general approach based on Bayesian networks to model the human behaviour. This approach represents human behaviour withprobabilistic cause-effect relations based not only on previous works, but also with conditional probabilities coming either from expert knowledge or deduced from observations. The approach has been used in the co-simulation of building physics and human behaviour in order to assess the CO 2 concentration in an office.