Skip to main content

Machine Learning Methods in Building Energy Modelling

Innosuisse innovation project with industry partner E4Tech (CHF 170k)


Buildings are responsible for up to 40% of energy consumption and CO2 emissions, making energy efficiency crucial in achieving climate goals. To address this, the Energy Strategy 2050 set by the Federal Council aims to improve energy consumption in buildings. However, global warming presents challenges in maintaining thermal comfort due to rising temperatures.

Building Energy Modeling (BEM) is a necessary tool for analyzing and making decisions to reduce energy consumption and emissions. An intelligent decision-support system is introduced to calculate solutions that optimize multiple objectives simultaneously, resulting in a handful of feasible solutions in a reasonable timeframe.

This system reduces errors, proposes better solutions, and allows engineers and architects to select the best option for their customers' needs. The project is projected to have a high return on investment and will lead to an increase in customers and employees for E4tech Software.

Hochschule für Architektur, Bau und Geomatik FHNW

Fachhochschule Nordwestschweiz FHNW Hochschule für Architektur, Bau und Geomatik Hofackerstrasse 30 4132 Muttenz
Diese Seite teilen: