FACILITIES MANAGEMENT


BE PART OF THE ENERGY DATA REVOLUTION T


he 1.5 million I&C buildings in England


and Wales currently account for around one third of all UK carbon emissions from total building stock. Incentivising carbon reduction from these premises is therefore a central plank in the government’s Heat Strategy, with an aim to reduce energy usage by at least 20% by 2030. “The question for


“The question for Facilities Managers is: Where best to invest time and resources to bear down on energy consumption and reduce carbon emissions?” said David Sing, group managing director (Assets) of Energy Assets


analysis and spot unusual consumption patterns. “What’s more difficult for


Facilities Managers is assessing the overall performance of a building measured against a benchmark that may itself be based on poor data. And even when data reveals that there is indeed a problem, you still


Facilities Managers is: Where best to invest time and resources to bear down on energy consumption and reduce carbon emissions?” said David Sing, group managing director (Assets) of Energy Assets, a leader in metering systems and data analytics. “While low carbon energy generation will be key


to economic decarbonisation, for most I&C users the immediate focus is on where to invest now to optimise energy efficiency and bear down on cost. At one level, this means optimising energy metering, monitoring and analytics to deliver maximum value; at another it means applying advanced technologies – such as machine learning and artificial intelligence – to drive out waste, develop granular profiles and progressively improve building performance. “Taking control of energy data will also open up


preferential time of use tariffs for I&C users with the arrival of the Ofgem-mandated half-hourly metered data era by 2025.” Sing added: “Getting the fundamentals working well is critical to optimising energy performance.”


SO WHAT DOES THIS MEAN? • Checking effectiveness of automated meter reading systems and sub-metering arrangements to ensure core consumption data is captured in granular detail


• Ensuring half-hourly energy data is collected, monitored and analysed through advanced AM&T portals, such as WebAnalyser


• Establishing ‘standard’ consumption profiles for each building in a portfolio, and setting automated alerts for unusual patterns of behaviour. Getting these basics right will not only bear down


on cost at a time of spiralling energy bills, they will also become increasingly important as enablers for carbon reduction strategies and actions linked to Energy Savings Opportunity Scheme (ESOS) targets. Sing added: “However, the challenge for managers,


and particularly those in medium sized enterprises (SMEs), will be how best to make sense of these huge volumes of data. The good news is automatic monitoring and targeting systems can easily be customised to take this data, provide bespoke


www.energymanagementmag.co.uk ENERGY MANAGEMENT - Spring 2022 29


need to treat the cause, which can be a bit like finding needles in a haystack. That’s why more managers are turning to machine learning, such as AMR DNA, to flag issues and offer a diagnostic route to improvement.”


HOW MACHINE LEARNING CAN HELP Machine learning uses artificial intelligence (AI) to automatically learn about and improve energy consumption. In short, it enables software to access data automatically and, in the case of energy usage, progressively learn what best performance should look like. Machine learning works by:


• Using ‘fingerprints’ of consumption unique to each building to monitor energy usage and spot tell-tale signs of energy waste


• Highlighting areas for potential improvement and providing a checklist of priority actions to drive efficiency and reduce energy costs


• Modelling multiple building occupation/ operation scenarios to enable better forecasting and strategic planning. It does this by assimilating available half-


hourly meter data and interpreting it in the context of operations and external factors


A transformation of building energy efficiency will be


required in the industrial and commercial (I&C) sector if the government is to achieve its target of a 78% reduction in carbon emissions by 2035. Energy Assets


examines how Facilities Managers in I&C settings have a critical role to play in ‘greening’ Britain’s economy…


(weather, occupancy levels). This creates the patterns of consumption from which the fingerprints are established. The system then progressively learns what can


be achieved in terms of energy efficiency and carbon reduction. And, being smart, it can also learn to ignore outcomes that are irrelevant, mistaken or due to bad data. Crunching data on this scale manually would


require an army of analysts – but with machine learning, informed by AI, this can be achieved quickly and lead to a priority list of improvement actions based on real world performance and comparative building analysis. “Often, it’s a question of spotting improvement opportunities hiding in plain sight, such as equipment that is running needlessly or heating controls that are incorrectly set - and machine learning is the perfect tool to do that,” said Sing. “It’s a technology increasingly being applied in multiple I&C sectors, including higher education, retail, local authorities and commerce, helping to identify energy savings opportunities across multi-site portfolios. “As we move forward, data will be both the


measure of sustainability and the means for holding companies to account for their carbon footprint. This new era will also enable Facilities Managers to negotiate best value tariffs with suppliers. “For all these reasons, it is vital that industrial


and commercial users embrace this new data- rich era if we are to succeed in decarbonising our economy in step with Net Zero ambitions.”


Energy Assets www.energyassets.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