Funding has been awarded by The Data Lab to a research project on Artificial Intelligence (AI) in energy efficiency building simulation. Experts from arbnco (formerly known as CO2 Estates) will be working alongside academics from the University of Strathclyde to explore how AI can be combined with data to create more accurate and robust simulations.
The nine-month project will be focused on the Arbn Consult platform software which provides the ability to quickly and accurately assess the EPC rating of a commercial property, producing bespoke and fully costed retrofit packages for delivering improvements in energy performance.
The team of researchers have combined expertise in machine learning, automation and construction, software and building simulation. Over the course of the project they will explore ways that back-end machine learning AI can mine data from the building simulation software to make quicker, more informed decisions.
Parag Rastogi, Lead Building Physicist at arbnco, explained:
“Currently, users are given a list of options by our platform that could potentially improve energy efficiency, from which they select individual refurbishments or their combinations to improve the building’s EPC rating.
Given the limited time that consultants have to complete a job, it would be impossible for them to manually go through every possible combination of suggested actions, so beneficial improvements could potentially be missed. We believe that utilising machine learning could make the process smoother, as the system would give optimum recommendations, taking into account factors such as finance constraints.”
Darran Gardner, The Data Lab Business Development manager said: This project is yet another demonstration of how use of data science can make a real, tangible difference to real world challenges. By bringing the specialists from Strathclyde University together with arbnco the use of Artificial Intelligence (AI) will ensure energy assessments derived from building simulations are as robust as possible. With increasing importance placed on energy efficiency there is no doubt of the potential for such a tool.
As well as making the platform more scalable and robust, it is hoped that the project will make energy efficiency improvements accessible for more users. For example, a facilities manager may not have as much knowledge in this subject as an energy assessor, but the machine learning will guide them through the process and potential options, offering suggestions they may not have thought of.
To date, very little research has been done on AI in building simulation. It is expected that outcomes from the project will be revealed when the machine learning is rolled out on the Arbn Consult platform.