Low-Code Toolchain Development to Accelerate Data-Driven Energy Modelling

Abstract: Building operations account for 30% of global energy consumption, necessitating performant, multi-scale modelling to optimize carbon reduction. While Machine Learning offers significant promise, significant issues prevent its full adoption. This paper proposes a Low-Code/No-Code (LCNC) approach as a solution to democratize analytics software development, allowing stakeholders to focus on their operation needs while removing the programming syntax barrier. We show how we use the WAVE platform, a cloud-based, collaborative LCNC platform based on formal models, for the graphical composition of workflows for multi-scale energy modelling. A LCNC solution to national scale energy modelling is described and compared to traditional implementations.