LT-Set: A Surrogate Model-Based Decision Tool for Low-Temperature District Heating Refurbishment

Abstract

The Netherlands aims to reduce greenhouse gas emissions by 49% before 2030, with the built environment contributing 15% of these emissions largely due to the heavy reliance on natural gas to meet space heating demands. To phase out natural gas, alternatives such as heat pumps and district heat networks are being considered. However, adapting existing buildings to lower supply temperature district heating requires effective refurbishment to maintain thermal comfort for occupants. The challenges hindering this process include i) addressing multiple housing typologies at the neighbourhood scale, ii) complexity of evaluating refurbishment measures by decision-makers, iii) uncertainty due to lack of consideration of life cycle costs and occupancy behaviour pre and post-refurbishment leading to performance gaps in energy savings and iv) current computationally demanding and inaccessible tools to assess refurbishment measures. Therefore, this thesis proposes a method to develop a surrogate model-based decision-making tool that can help homeowners efficiently assess optimal, combined refurbishment measures to help homeowners transition to low-temperature district heating. In order to develop this tool, the study examines literature studies that help define the input parameters for the underlying parametric simulation including. This also helped define the key performance indicators including energy savings, hours too cold and global cost. Furthermore, the underlying simulation model with 13 input parameters provides the synthetic training data with 2000 design samples using the uniform Latin hypercube sampling method for each of the three housing archetypes including i) terraced, ii) detached and iii) Portiek apartments. The best-performing model in this instance included artificial neural networks with an R-squared above 0.95. The surrogate model is then integrated into the optimization workflow that forms the framework for an interface decision-making tool that users can use to generate optimal low-temperature ready refurbishment packages. The common low-temperature ready refurbishment packages include maximum airtightness, type C2 CO2 control ventilation system, cavity wall insulation, triple glazing, and internal roof insulation. Furthermore, it can be concluded that its more financially feasible to maintain existing radiators when transitioning to low-temperature heating instead of replacing the radiators with higher capacity. This is because the initial investment in other refurbishment measures not only improves comfort but also delivers significant energy savings that help reduce global costs in the long term.