Paper Conference

Proceedings of Building Simulation 2021: 17th Conference of IBPSA


Besos: a python library that links energyplus with energy hub, optimization and machine learning tools.

Theodor Victor Christiaanse 1,2, Paul Westermann 1,2, Will Beckett 1,2, Gaelle Faure 1,2, Ralph Evins 1,2
1 Energy in Cities group, Department of Civil Engineering, University of Victoria, BritishColumbia, Canada
2 Institute for Integrated Energy Systems, University of Victoria, British Columbia, Canada

Abstract: This paper presents the besos Python library, which can parameterize EnergyPlus models and integrate these with the Python ecosystem of tools including machine learning and optimization libraries. This library underpins the BESOS (Building and Energy Simulation, Optimization and Surrogate-modelling) platform. The need for a flexible Python-based library that integrates these domains is outlined. A case study is presented to demonstrate the benefits of this integrated approach, and an overview is given of research works that have leveraged these benefits. We also discuss lessons learned while developing, deploying and documenting this open-source library.
Keywords: machine learning, building modelling, energy hub modelling, energyplus
Pages: 1951 - 1958