BESOS: a Python']Python library that links EnergyPlus with optimization and machine learning tools

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.