Fifty shades of grey: Automated stochastic model identification of building heat dynamics

To reach the carbon emission reduction targets set by the European Union, the building sector has embraced multiple strategies such as building retrofit, demand side management, model predictive control and building load forecasting. All of which require knowledge of the building dynamics in order to effectively perform. However, the scaling-up of building modelling approaches is still, as of today, a recurrent challenge in the field. The heterogeneous building stock makes it tedious to tailor interpretable approaches in a scalable way. This work puts forward an automated and scalable method for stochastic model identification of building heat dynamics, implemented on a set of 247 Dutch residential buildings. From established models and selection approach, automation extensions were proposed along with a novel residual auto-correlation indicator, i.e., normalized Cumulated Periodogram Boundary Excess Sum (nCPBES), to classify obtained model fits. Out of the available building stock, 93 building heat dynamics models were identified as good fits, 95 were classified as close and 59 were designed as poor. The identified model parameters were leveraged to estimate thermal characteristics of the buildings to support building energy benchmarking, in particular, building envelope insulation performance. To encourage the dissimination of the work and assure reproducibility, the entire code base can be found on Github along with an example data set of 3 anonymized buildings. The presented method takes an important step towards the automation of building modeling approaches in the sector. It allows the development of applications at large-scale, enhancing building performance benchmarks, boosting city-scale building stock scenario modeling and assisting end-use load identifications as well as building energy flexibility potential estimation.