SUSTAINABILITY SOLUTIONS
CAN MACHINE LEARNING TRANSFORM SUSTAINABILITY IN EDUCATION?
George Catto, client services director at AMR DNA, an Energy Assets service, examines why machine learning and AI are fast emerging as a favoured route to energy efficiency and energy waste eradication across the higher (HE) and further (FE) education sectors
I
n the Department for Education’s recently updated sustainability and climate change strategy for England, building adaptation and decarbonisation is promoted as a key contributor to Net Zero. Moreover, the impact on young people on seeing sustainability brought to life across the education landscape is also cited as a transformational learning opportunity, enabling students to contextualise the environmental benefits of improving energy efficiency. This is important because government analysis shows that schools and universities represent 36% of total UK public sector building emissions. So, a key aim of the strategy is to reduce direct and indirect emissions from education and care buildings, and to drive innovation to meet legislative targets. So, the question for premises and energy
managers in education is how best to deliver these much-prized energy efficiency gains? In part, this can be achieved by the installation of renewable power generation and storage but, even then, such investment needs to be accompanied by a process to eradicate energy waste – which can often be hiding in plain sight.
SPOTTING SIGNS OF ENERGY WASTE The good news is that just such a programme is already underway in the higher (HE) and further (FE) education sectors, thanks to the foresight of The Energy Consortium (TEC), 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. TEC is working with AMR DNA, an
Energy Assets machine learning and artificial intelligence data analytics service, to improve energy efficiency across a number of university campuses. In 2023 alone, this partnership
identified and stopped 101 significant energy waste issues with a notional value of £345,000. In addition, 14 new non- waste KPIs, covering issues such as high summer base loads, poor timeclock
www.essmag.co.uk
control and overcompensation for weather variation, were incorporated into BMS strategies, resulting in a further £325,000 of waste addressed. Of course, energy monitoring and reporting platforms that assimilate half hourly data from automated meter reading systems are not new. These systems, such as WebAnalyser, provide a convenient way of comparing actual consumption versus benchmark parameters, enabling managers to measure the impact of efficiency programmes. However, extracting maximum value pre- supposes that the underpinning energy performance profiles for each building possess the necessary accuracy to act as benchmarks. This is why machine learning and AI are fast
emerging as a favoured route to energy efficiency and energy waste eradication across the HE and FE sectors. AMR DNA crunches years’ worth of metered energy data in short order and then progressively ‘learns’ what optimal performance looks like for each building. The system then applies pattern recognition to
consumption models to spot tell-tale signs of energy waste unique to each building. These events can result from something as simple as equipment running needlessly or heating controls being incorrectly set. The system continuously monitors meter data to identify waste energy and creates a checklist of priority remedial actions. As such, machine learning can be a complementary tool to traditional monitoring and reporting platforms.
ELECTRIFYING BEST PRACTICE TEC has adopted this approach to support its risk management of a portfolio comprising 11TWh of gas and power across 10,500 meters. AMR DNA, powered by kWIQly, creates data-driven consumption insights that it would take an army of analysts to deliver manually. As Stephen Creighton, head of member services at TEC, states: “The system looks at past performance to see whether a building is deviating from its usual performance; reviews whether energy efficiency is on a par with peer buildings; and assesses whether building management systems could be improved.” “Often, it’s a question of spotting improvement opportunities hiding in plain sight, but sometimes these can be the hardest to identify because they are ingrained in a building’s legacy performance and can be easily overlooked.” By using machine learning, campuses in the scheme 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. Historically, AMR DNA has been applied to gas consumption, but there are equally positive results emerging for electricity. “We are currently trialling over 600 electricity
meters for eleven TEC members where we are seeing very promising early results,” said Creighton. “We are also running an electrical sub-meter trial which involves 95 meters, fitted across a TEC member estate and resulting in the identification of savings potential of more than £100,000 in waste.” Data from electricity meters and sub-meters has been around for longer than AMR on gas but forensic analysis is in its infancy. As such, the opportunity for identifying waste and optimising energy performance continues to broaden.
Energy Assets
www.energyassets.co.uk/service/amr-dna/
ENERGY & SUSTAINABILITY SOLUTIONS - Spring 2024 13
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 |
Page 41 |
Page 42 |
Page 43 |
Page 44
