Abstract
Continuous commissioning can be implemented through performance testing which analyses a building’s behavior using a set of software-based tests. In this paper, we present a workflow for performance testing in smart buildings, including buildings that lack historical data. The difficulty in assessing behaviors of new buildings is in the lack of historical data to calibrate models that describe future behaviors. The proposed workflow uses a combination of country regulations, data driven, and white box models, to assess the building in various stages after its handover. We validate the workflow by comparing the results from the different models with the observed behavior of a case study building in Denmark. We examine the change in percentage of passed and failed performance tests, based on different thresholds delivered by the models. The results show an increased number of passed performance test for data driven models, and demonstrate the assessment of performance using the proposed workflow, from the beginning of the building’s usage.
Keywords
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Katipamula, S., Brambley, M.R.: Methods for fault detection, diagnostics, and prognostics for building systems—a review, part I. Hvac&R Res. 11, 3–25 (2005)
Markoska, E., Johansen, A., Lazarova-Molnar, S.: A framework for fully automated performance testing for smart buildings. In: Yang, X.S., Sherratt, S., Dey, N., Joshi, A. (eds.) Third International Congress on Information and Communication Technology. AISC, vol. 797, pp. 235–243. Springer, Singapore (2019). https://doi.org/10.1007/978-981-13-1165-9_21
Markoska, E., Lazarova-Molnar, S.: Comparative evaluation of threshold modelling for smart buildings’ performance testing. In: The 9th International Green and Sustainable Computing Conference. IEEE (Submitted)
Li, X., Wen, J.: Review of building energy modeling for control and operation. Renew. Sustain. Energy Rev. 37, 517–537 (2014)
Claridge, D.E., et al.: Is commissioning once enough? Energy Eng. 101, 7–19 (2004)
Markoska, E., Lazarova-Molnar, S.: Towards smart buildings performance testing as a service. In: The International Workshop on Smart Cities Systems Engineering (2018)
Karatasou, S., Santamouris, M., Geros, V.: Modeling and predicting building’s energy use with artificial neural networks: methods and results. Energy Build. 38, 949–958 (2006)
Li, K., Su, H., Chu, J.: Forecasting building energy consumption using neural networks and hybrid neuro-fuzzy system: a comparative study. Energy Build. 43, 2893–2899 (2011)
SBI: The Danish Building Research Institute - BE10 SBI tool, May. https://sbi.dk/beregningsprogrammet/Pages/Aendringer-til-tidligere-versioner-af-Be15-og-Be10.aspx#s=BE10
Crawley, D.B., Pedersen, C.O., Lawrie, L.K., Winkelmann, F.C.: EnergyPlus: energy simulation program. ASHRAE J. 42, 49 (2000)
Pedregosa, F., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Markoska, E., Lazarova-Molnar, S. (2018). A Workflow for Continuous Performance Testing in Smart Buildings. In: Kameas, A., Stathis, K. (eds) Ambient Intelligence. AmI 2018. Lecture Notes in Computer Science(), vol 11249. Springer, Cham. https://doi.org/10.1007/978-3-030-03062-9_4
Download citation
DOI: https://doi.org/10.1007/978-3-030-03062-9_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-03061-2
Online ISBN: 978-3-030-03062-9
eBook Packages: Computer ScienceComputer Science (R0)