Alessandro Pongelli

This paper presents an innovative methodology for enhancing energy efficiency assessment procedures in the built environment, with a focus on the Switzerland’s Energy Strategy 2050. The current methodology necessitates intensive expert surveys, leading to substantial time and cost implications. Also, such a process can’t be scaled to a large number of buildings. Using machine learning techniques, the estimation process is augmented and exploit open data resources. Utilizing a robust dataset exceeding 70’000 energy performance certificates (CECB), the method devises a two-stage ML approach to forecast energy performance. The first phase involves data reconstruction from online repositories, while the second employs a regression algorithm to estimate the energy efficiency. The proposed approach addresses the limitations of existing machine learning methods by offering finer prediction granularity and incorporating readily available data. The results show a commendable degree of prediction accuracy, particularly for single-family residences. Despite this, the study reveals a demand for further granular data, and underlines privacy concerns associated with such data collection. In summary, this investigation provides a significant contribution to the enhancement of energy efficiency assessment methodologies and policy-making.

The building stock is responsible for 24% of carbon emissions in Switzerland and 44% of the final energy use. Considering that most of the existing stock will still be in place in 2050, it becomes essential to better understand this source of emissions. Although the Swiss Cantonal Energy Certificate for Buildings (CECB) database has been used in previous research, no comprehensive characterization of the buildings can be found. This data paper presents an analysis and classification of the Swiss building stock based on the data found in the database. The objective is to create a knowledge foundation that can be used in future research on the performance of existing buildings. Using a sample of almost 50,000 buildings and a Python script, datasheets were created for single-family houses and multi-family houses for nine construction periods. These archetypes are described through selected available energy-related parameters, such as energy reference area, U-values, and energy source with indicators such as median, 25th percentile, and 75th percentile or distributions. The resulting data can be used for different purposes: (1) to calibrate energy models; (2) for analysis that requires scaling-up strategies to the whole stock; and (3) to identify weak and/or relevant classes of buildings throughout the stock.