The Leading News & Information Service For The Facilities, Workplace & Built Environment Community

AI Predicts Building Energy Rates in Less Than A Second

AI Predicts Building Energy Rates in Less Than A Second
11 August 2021

An artificial intelligence system that can predict building emissions rates almost instantly has been created.

Current methods can take days to produce building emissions rates (BERs) and are generated by manually inputting hundreds of variables.

However, this new system can calculate BER values in commercial buildings with 27 inputs with little loss in accuracy.

Computer scientists at Loughborough University and engineering consultancy, Cundall presented their project at The Chartered Institution of Building Services Engineers (CIBSE) Technical Symposium 2021.

The paper is to be published on CIBSE’s website later this year.


“By predicting the energy consumption and emissions of non-domestic buildings quickly and accurately, we can focus our energy on the more important task - reducing energy consumption and reaching net-zero.”

– Edwin Wealend

Head of Research and Innovation, Cundall


Building Emissions Rates Central to Net-Zero Efforts


At a time when the UK is trying to reach net-zero by 2050, the timely, accurate calculation of energy efficiency is a vital component of the design process for new and refurbished buildings.

Dr Georgina Cosma and postgraduate student Kareem Ahmed, of the School of Science, have designed and trained an AI model that can generate a BER value almost instantly.

The proposed model was created with the support of Cundall’s Head of Research and Innovation, Edwin Wealend, and trained using large-scale data obtained from UK government energy performance assessments.

Dr Cosma says the research “is an important first step towards the use of machine learning tools for energy prediction in the UK” and it shows how data can “improve current processes in the construction industry”.


What is a BER? 


In the UK, an EPC must be completed every time a building is sold, rented, or constructed. It provides an indication of the energy efficiency of a building, contains information about the building’s typical energy costs, and recommends ways to make it more energy-efficient.

One of the most useful values returned is the asset rating – a number that gives a simple overall energy rating for a building and the number is banded (A+ to G) and colour-coded for ease of interpretation. 

However, producing this rating can be a slow process as the calculation requires the building emission rate (BER) – which, as mentioned, can take hours to days to generate, depending on the complexity of the building.

Additionally, Minimum Energy Efficiency Standards (MEES) for commercial properties will be expanded in 2023, meaning that buildings with an EPC rating lower than E will not be able to be leased.


The AI model


In their latest paper, Dr Cosma and team show their AI system can generate a BER for non-domestic buildings in less than a second and with as few as 27 variables with little loss in accuracy – making it a much faster and efficient process.

They used a "decision tree-based ensemble’" machine algorithm and built and validated the system using 81,137 real data records that contain information for non-domestic buildings over the whole of England from 2010 to 2019. The data contained information such as building capacity, location, heating, cooling lighting, and activity.

The team focused on calculating the rates for non-domestic buildings – such as shops, offices, factories, schools, restaurants, hospitals, and cultural institutions – as these are some of the most inefficient buildings in the UK in terms of energy use, so understanding how to improve their efficiency can be useful in design and renovation processes.

Dr Cosma commented: “Studies on the applications of machine learning on energy prediction of buildings exist, but these are limited, and even though they only make up 8 per cent of all buildings, non-domestic buildings account for 20 per cent of UK’s total CO2 emissions.”

Cundall’s Edwin Wealend added: “Eventually, we hope to build on the techniques developed in this project to predict real operational energy consumption.

“By predicting the energy consumption and emissions of non-domestic buildings quickly and accurately, we can focus our energy on the more important task - reducing energy consumption and reaching net-zero.”

Picture: a photograph of a large commercial building, illuminated with blue lighting 

Article written by Ella Tansley | Published 11 August 2021


Related Articles

London South Bank University Estates Team Wins CIBSE Award

London South Bank University’s estates and academic environment team has won a CIBSE Building Performance award for efficient facilities management. The team won...

 Read Full Article
UCL Guidelines Win CIBSE Award 

University College London in collaboration with Buro Happold has won the “Learning and Development” award at the 2021 CIBSE Building Performance...

 Read Full Article
Sodexo Commits to Carbon Neutrality by 2025

Sodexo has raised its sustainability targets after cutting its carbon footprint by 34 per cent, ahead of schedule. Sodexo has laid out its net-zero roadmap after...

 Read Full Article
Sustainable Deliveries at 22 Bishopsgate to Lower City Emissions

A sustainable delivery system at 22 Bishopsgate is set to reduce the number of weekly vehicle trips to the building from 1,300 to just 50. AXA IM Alts, developer of...

 Read Full Article
University Researches AI Surveillance for Social Distancing Monitoring 

Researchers at Griffith University, Australia, have developed an AI video surveillance system to detect social distancing breaches in an airport without compromising...

 Read Full Article
Sodexo Launches 2021 Social Impact Pledge

Sodexo UK & Ireland has announced its commitment to a series of pledges forming its ethical manifesto for leading the way to improve quality of life for society and...

 Read Full Article
The UK’s Hydrogen Economy – Industry Reactions

The UK’s first-ever hydrogen strategy launched this week, defining the energy source as critical in the country’s target of net-zero emissions by 2050. The...

 Read Full Article
UhUb Partners with Planet Mark

UhUb, the provider of Education Technology for the cleaning sector, has partnered with Planet Mark, a sustainability certification for every type of...

 Read Full Article
Carbon Savings From One Virtual Conference Could Power 17 Homes For a Year

The carbon saving from just one virtual conference could power 17 homes for a year. Research from Ezra, a provider of digital coaching, has revealed how UK...

 Read Full Article
Sensors to Assist Academic Study on Workplace Occupancy Trends 

Data from Freespace workplace sensors is to support academic research studying worker’s spatial behavioural patterns. Freespace, a workplace technology...

 Read Full Article