Residential building energy performance prediction at an urban scale using ensemble machine learning algorithms

Data-driven building energy performance assessment techniques have proven to be a viable solution at the urban scale and are driven by the availability of consistent, reliable, and heterogeneous building-related data. However, the data-driven performance assessments so far have often been limited in terms of scope, scale and lacked key parameters for predicting the potential building energy performance. This paper proposes a workflow to integrate building archetypes’ simulations, parametric analysis, and ensemble-based machine learning techniques to accurately predict individual building energy performance at an urban level. The result presented focuses on Irish residential buildings by generating a synthetic dataset using parametric analysis of crucial features of semi-detached building archetypes. The results show that the ensemble method gives higher-quality prediction when compared to traditional machine learning algorithms. The proposed study aims to assist stakeholders, including energy policymakers and urban planners, in making informed decisions for the development of long-term renovation strategies.