Wednesday
Track 1 / Room: Studio
13.40 - 14.10
Unlocking Flexibility with Near Real-Time Building Models: Insights from the TKI Built4Buildings Project
Due to the increasing availability of irregularly generated solar energy and wind power, as well as the rise in electric vehicles and heat pumps, not only is there a growing imbalance in supply and demand, but the peaks are also becoming larger. In the Netherlands, businesses are increasingly hindered in expanding electric vehicle charging, solar panels, and heat pumps on existing company premises due to limited electricity grid capacity. In the Dutch TKI project Brains4Building, numerous companies collaborate on solutions to unlock flexibility in commercial buildings to better balance supply and demand and reduce peak demand. Together with project partners, models are developed for the building and its installations, and these models are calibrated in near real-time using building data. These models are employed to predict energy consumption and local production. Based on these predictions, a controller is being developed to adjust the energy demand accordingly to anticipate grid connection limits and address the supply-demand imbalance. Additionally, several other projects are showcased where similar solutions are applied.
About wouter Borsboom
Wouter Borsboom joined TNO in 2001, where he has been involved in a combination of consultancy, project contributions, and acquisition related to the energy sector in the built environment, ventilation, and model-based data analytics. He actively participates in various national collaboration programs and European projects focused on building digital twins, model-based control and optimization, ventilation, indoor environmental quality, flexibility, and maintenance services. Additionally, he serves as a member of the Steering Group at AIVC and has (co)authored AIVC publications on topics related to ventilation and air infiltratio.
About Brains 4 Buildings
Brains for Building’s Energy Systems (B4B) is a multi-year, multi-stakeholder project focused on developing methods to harness big data from smart meters, building management systems and the Internet of Things devices, to reduce energy consumption, increase comfort, respond flexibly to user behaviour and local energy supply and demand, and save on installation maintenance costs. This will be done through the development of faster and more efficient Machine Learning and Artificial Intelligence models and algorithms. The project is geared to existing utility buildings such as commercial and institutional buildings.