Simulation and optimization-based analysis to support the design of life cycle net-zero energy buildings

Description

Obtaining life cycle net-zero energy (or GHG) buildings is vital towards the long-term target of net-zero GHG emissions in Sweden by 2045. Besides passive measures, such as building envelope materials, active and renewable measures (e.g., HVAC systems, solar panels, wind turbines) play a key role to support life cycle net-zero energy buildings due to their potential to offset the surplus energy use in a building life cycle. Many previous research studies have mainly focused on the life cycle analysis of passive measures, without considering how such measures need to be combined with active and renewable measures to ensure life cycle net-zero energy buildings at the lowest costs. Therefore, this study aims to increase knowledge and provide a tool based on genetic algorithms and machine learning for analyzing and optimizing a wide range of measures to eventually support life cycle net-zero energy building design.