Have you taken your energy consumption fingerprints recently?

Have you taken your energy consumption fingerprints recently?

George Catto, Client Services Director for AMR DNA, considers the challenges facing energy managers in adapting building performance in an environment of change…and how machine learning could provide important answers.

Energy managers in industrial and commercial (I&C) settings have a critical role to play in greening Britain’s economy.  This will require a transformation of building energy efficiency, particularly in the I&C sector if the government is to achieve a 78% reduction in carbon emissions by 2035

The good news is that the enabling technologies that can transform energy efficiency in buildings already exist. There are signs, too, that the financing and investment tools needed to drive these changes are gaining traction.

The current situation is particularly difficult for energy managers, because the post-pandemic world will be fraught with uncertainty about building occupancy levels and workplace organisation. So this could be precisely the time when energy managers are empowered to use all the tools at their disposal, and not just because of the drive to bear down on energy cost.

Carbon reduction is increasingly central to Environmental, Social, and Corporate Governance strategies as organisations align themselves with the roadmap to Net Zero. So, management teams will be watching how their energy performance compares with similar organisations and will be alive to any opportunities for carbon reduction enabled by innovation.

In this environment, tracking energy usage data – and the equipment and systems that contribute to a consumption profile – is vital.

Energy managers might not even be aware that a building is performing poorly compared to similar buildings.  And even when data reveals that there is indeed a performance problem, you still 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 to flag issues and offer a diagnostic route to improvement.

The value of machine learning

Machine learning, as applied by AMR DNA, uses artificial intelligence (AI) to automatically learn about and improve energy consumption in industrial and commercial buildings. In short, it is technology that enables software to access data and, in the case of energy usage, automatically and progressively learn what best performance should look like.

With the availability of so much data through half hourly automated meter reads, there is a growing appetite among energy managers to adopt machine learning to find value-adding data easily – and then take action to improve efficiency. 

Hence growing interest in AMR DNA, a kWIQly service provided by Energy Assets. The software applies machine learning to help transform energy performance 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 gas and electricity meter data and interpreting it in the context of operations and external factors (weather, occupancy levels). This creates the patterns of consumption from which the fingerprints are established. 

Then the system progressively learns what can be achieved in terms of energy efficiency and carbon reduction. And because the system is 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, it can take just a matter of hours, even minutes to yield results. The system then provides energy managers with a priority list of actions informed by transparent, independent and authoritative data.

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. In fact, it’s already widely applied in higher education, retail, local authorities and commerce, enabling energy managers to identify energy savings opportunities across multi-site portfolios and to develop accurate scenario planning linked to occupancy levels and building footprints.       

An energy manager lacking answers at their fingertips is doomed to spend time poring over reams of consumption data or simply acting on gut feel. With insufficient insight or irrelevant advice, opportunities will be wasted at a time when machine learning can be applied to deliver tangible value.

TEC Tackles Energy Waste with AI

Among those organisations implementing energy strategies informed by machine learning is The Energy Consortium, which provides energy solutions to their members primarily in the higher and further education sector and the arts.

Stephen Creighton is Head of Member Services at TEC and has been employing machine learning for the last four years to support the drive in energy efficiency and carbon reduction in the higher education sector.

“By applying AMR DNA technology across multi-site campuses, we have been able to support our members in achieving significant improvements in energy efficiency. Diving this deep into the volume of metered data that is now available simply would not have been possible through manual intervention.

“Now though, we have a system that can not only spot areas of concern, but also progressively learn the optimal performance for each building and provide a corresponding list of priority actions to deliver the best outcomes.”

First published Building Services & Environmental Engineer magazine August 2021.


News

Energy Assets Utilities Sharpens Business Development Strategy

Energy Assets Utilities (EAU), one of Britain’s leading utility network design and construction companies, has created two new roles to spearhead its business growth plans.

The company has promoted Gary Smith to Head of Residential Sales and Craig Downie to Head of Commercial Sales to help drive the implementation of a sector-based expansion strategy.

READ MORE
News

Energy Assets Acquires Cortex Metering Solutions

Energy Assets Group has announced the acquisition of Cortex Metering Solutions (CMS) from Macquarie Specialised and Asset Finance, adding more than 600,000 industrial and commercial meters to our growing portfolio of assets. The transaction extends the company’s position as one […]

READ MORE
News

Stewart Focuses on Big Data

Big data is about to transform the energy performance of the I&C sector, according to Stewart Love, Energy Assets’ newly-appointed Director of Strategic Development.

READ MORE
National Gas Emergency ServiceElectricity fault?