MONITORING & METERING TRANSFORMING SUSTAINAB The University of Wales


Trinity Saint David (UWTSD) aims high with renewable energy investments and machine learning analytics


T


he University of Wales Trinity Saint David (UWTSD) is investing in machine learning


technology to support its ambitious plans to be a leading university for energy sustainability. UWTSD, which has campuses in Swansea, Carmarthen, Lampeter, Cardiff, London and Birmingham, is already reaping the benefits of a solar power strategy. Now, however, it is turning to artificial intelligence (AI) to transform energy efficiency across its entire estate. The University is using AMR DNA, an Energy Assets service, to apply AI-informed machine learning analytics to drive out energy waste, optimise efficiency, reduce consumption, and make significant steps toward Net Zero carbon emissions. The AMR DNA software, powered by kWIQly, progressively learns what best energy performance looks like in each building, and automatically flags up in near real-time unusual spikes in energy usage, which can be quickly addressed by the University. “Our vision is to build on our existing position as


a leading UK university for energy sustainability,” said Dan Priddy, finance and business performance manager at UWTSD. “We’re taking real actions that will reduce Scope 1 (direct) and Scope 2 (indirect) greenhouse gas emissions by 95% by 2030. “This will be made possible by infrastructure upgrades, more investment in renewable energy, the adoption of Net Zero construction standards on new buildings and, critically, by applying machine learning technologies.” He added: “We’re already seeing the benefits of


this approach. Thanks to the installation of solar panels, the electricity demand at the Dynevor building, home to UWTSD’s Swansea Art College, is significantly met by renewables generation. Now, with the move to machine learning, we aim to ensure that our entire estate is optimised for energy efficiency and emissions reduction.”


IDENTIFYING THE FINGERPRINTS OF CONSUMPTION Working with the University, AMR DNA analysed years’ worth of historical meter data to identify the unique ‘fingerprints’ of consumption that would provide an energy benchmark for each of the UWTSD buildings. The software models what ‘normal’ consumption looks like, taking account of multiple factors, such as occupancy levels and operating hours, and ‘learns’ what optimal performance should look like. Using pattern recognition linked to key performance indicators, the system interrogates metered data to spot tell-tale signs of energy waste. This waste can result from something as simple as equipment running needlessly or


36


lights being left on overnight, or might be linked to incorrect heating timeclock controls, over- compensation for ambient weather conditions, or high summer base loads. “We operate six campuses covering everything


from student accommodation, libraries, teaching spaces and offices, to engineering workshops, manufacturing units and sports facilities,” explained Priddy. “This creates an estate with a lot of nuances, which makes the manual tracking of energy consumption very difficult and time consuming. “But with machine learning, we not only see the big trends, but we also pick up on smaller issues that we would never have identified in the grand scheme of things… but they all add up. The amount of manual resource you would need to capture this level of detail would be


ridiculous, but now we can, using AI.” UWTSD started using the system in the


latter part of 2023 and has already seen some significant benefits. For example, when heating had been inadvertently left on in an unattended building, the machine learning system flagged this, and it was fixed almost immediately. “Of course, some spikes are easily explained, for


example if a 3D printer is working overnight,” said Priddy. “But where there is nothing obvious, we see the AMR DNA alert and ask the site teams to investigate. It means we have a clearer picture of energy consumption across the entire estate, with a greater ability not only to spot consumption spikes more easily but also to address them quickly.” AMR DNA currently tracks performance across gas services but is about to be trialled at UWTSD to monitor efficiency in electricity


TEC PARTNERSHIP WITH AMR DNA


UWTSD is benefiting from a framework agreement across the higher education sector between AMR DNA and The Energy Consortium (TEC). TEC is a Contracting Authority owned by its members which delivers a wide range of services in energy procurement, data reporting, risk management and cost reduction on a not-for-profit basis. In 2023 alone, this partnership identified and stopped 101 significant energy waste events on university


campuses with a notional value of £345,000. In addition, 14 new non-waste KPIs, tracking measures such as high summer base loads, poor timeclock control and overcompensation for weather variation, were incorporated by AMR DNA into BMS strategies, resulting in a further £325,000 of waste addressed. As a result, campuses adopting this AI-informed machine learning approach have seen a 30%


decline in the average duration of major energy waste incidents and a 60% reduction in total energy waste per month over the last two years. George Catto, client services director for AMR DNA, commented: “Our experience is that energy


waste can often be hiding in plain sight because it would take an army of analysts to pore over thousands of bits of historical data to spot anomalies. Machine learning can do this heavy lifting of data analysis, enabling organisations such as UWTSD to adopt a forensic approach to improving energy efficiency and reducing carbon emissions.” Energy Assets is one of Britain’s leading independent metering, data, asset management


and utility network construction companies. The Group offers utility suppliers, third party intermediaries, developers, contractors, and industrial and commercial end-users a broad spectrum of multi-utility metering and energy-related services. This includes enabling customers to collect and analyse energy consumption data.


ENERGY & SUSTAINABILITY SOLUTIONS - Autumn 2024


www.essmag.co.uk


Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36  |  Page 37  |  Page 38  |  Page 39  |  Page 40