A look around the EU project innovation block – How big data & machine learning could pave the way for a broader uptake of PEB solutions

25 September 2023

A look around the EU project innovation block – How big data & machine learning could pave the way for a broader uptake of PEB solutions

Better data for bigger impact of PEB solutions? The EU funded sister projects EXCESS, Syn-ikai and Cultural-E were formed to develop holistic energy concepts turning Nearly Zero Energy Buildings (nZEBs) into affordable Plus Energy Buildings (PEBs) and neighborhood Districts (PEDs) across different contexts, cultures, climates, and markets in Europe. Now, there is a generation of EU big building data projects maturing, whose outcomes could take replication of the PEB solutions developed in EXCESS and its sister projects onto the next stage. 

The installation of smart technologies to optimize and monitor the energy performance of new, as well as existing ones is not only important for improving their energy efficiency but for creating precise demand data. Whereas the energy demand and performance data produced in the process holds apparent value for the operation of the buildings itself, it could hold even greater value for the transition of the European building stock as a whole. 

And this is where the new generation of big building data projects such as MATRYCS come into play: MATRYCS leverages building-related big data through the power of artificial intelligence, employing machine learning and deep learning technologies to establish robust decision support services in one central tool. 

Concretely, applying the MATRYCS toolbox will allow users to access and run data analytics services, focusing on different building lifecycle opportunities and stakeholder perspectives, including digital building twins, improved buildings operation, building infrastructure design, and EU/national policy assessment for energy efficiency investments. These services are to be applicable across different building scales, from buildings as individual entities (building scale), to groups of buildings (district scale), groups of districts (city scale), groups of cities (regional scale), and national and European levels, making the tool useful for individual property managers to European policy makers alike. In other words, MATRYCS is offering different stakeholders in the building sector, from estate managers to building owners, to local and European policy makers to coherently assess the impact and outcomes of individual to public measures, investments and decisions based on the available real-life building related data.  

Any AI-based tools from ChatGPT and beyond remain only as good as the data they are based on. A reality MATRYCS partners are working on with the EU project, BuiltHub - Dynamic EU building stock knowledge hub - and the MATRYCS led Big Data Alliance (BDA). Complementary to that, BuiltHub is working towards the development of a roadmap and an inclusive method for sustained dataflows to the EU Building Stock Observatory (BSO) that could feed tools such as MATRYCS. The BDA provides an additional collaborative space for building stock stakeholders to work together on combining meaningful data sets to allow tools such as MATRYCS to accurately analyse the characteristics of the EU building stock. The calculation here is simple, the better and the more data is available, the more accurate predictive models will be to allow us to trace and predict the impact of policy measures and technology solutions, as well as the assessment of risk and impact of energy investments.

Where EXCESS is taking individual buildings to plus-energy level by building on, amongst others, smart building energy management and optimisation, the data produced in the process, allows big data projects like MATRYCS to develop better decision making services to the users that wish to benefit from it. In reverse, tools like MATRYCS could enable local to European planners to identify cost effective solution scenarios for a broader uptake of nZEB and PEB solutions and standards. 

Find more information about the MATRYCS Toolbox here.

Image , licensed under Image by Gerd Altmann from Pixabay

All news