There’s probably never been a more important time for industry to get ‘energy fit’, both to bear down on cost and also to contribute to the UK’s wider sustainability goals. Although the last year has seen some rowing back on the speed of the roadmap to net zero, the aim remains to reach this objective by 2050. This target is enshrined in law, so what does it mean for industrial and commercial (I&C) enterprises?
Aside from increasing pressure from customers, stakeholders and suppliers to demonstrate their sustainability credentials, it remains to be seen whether businesses will be subject to additional reporting regimes measuring their carbon footprint and proving progress on emissions. So where to start? At a high level, there are some freely available tools to help businesses assess their greenhouse gas emissions, such as the Business Carbon Calculator, because like every improvement process, defining the start point is the first critical step. However, what’s already clear for most organisations is that their carbon output will be largely determined by their energy consumption.
As a result, energy managers have a critical role in influencing progress towards net zero – and many are turning to advanced metering technologies, analytics and machine learning to make a difference. Moreover, the value of data will only grow with the onset of the Market-wide Half-Hourly settlement (MWHH) reform due by 2025, which, for I&C users, will likely create opportunities for demand side response incentives and preferential time of use tariffs.
Monitoring and measuring energy usage is already a routine business function, with automatic monitoring and targeting (aM&T) systems widely in use to collect and report on meter data to identify trends and unusual spikes. What’s changing is the emergence of machine learning, informed by artificial intelligence (AI), which is capable of turning years’ worth of half-hourly gas and electricity meter reads into value-adding, granular energy consumption data for entire building portfolios.
DEVELOP A METERING STRATEGY
Whatever the analytical tools adopted by companies, core to energy efficiency progress is an automated meter reading (AMR) system and a metering strategy.
One area often overlooked in energy optimisation is sub-metering. Despite the sophistication of aM&T systems, many industrial and commercial settings overlook the value that electricity sub-metering can deliver in understanding consumption – and saving money.
For larger single site operations sub-metering provides the ability to monitor energy usage by floorplate or function. It also enables the collection of data linked to carbon reduction obligations and the Energy Savings Opportunities Scheme (ESOS).
In multi-occupancy settings, such as retail centres, service stations or transport hubs, sub-metering enables businesses to monitor their energy usage much more accurately – and make positive changes – rather than being charged on a broader measure such as the footprint.
Sub-metered data can feed into an aM&T dashboard, such as Energy Assets’ WebAnalyser, alongside master meter readings, giving organisations much greater clarity of their consumption profiles. This type of platform helps make sense of half-hourly data delivered via AMR systems and enables organisations to identify ways to reduce energy costs, pinpoint energy waste and flag up unexpectedly high consumption. Bespoke reports can also be tailored to single site or multi-site operations.
These monitoring systems can also inform robust and long-term energy management practices that, according to the Department for Business Energy and Industrial Strategy (BEIS), can lead to average energy savings of 10-15%.
INVESTIGATE AI AND MACHINE LEARNING
Machine learning is enabling energy managers to go even further, dive deeper into data and apply dynamic learnings to optimise building performance. The core data informing these models comes from historic half hourly meter readings. Analysing such data manually would require an army of analysts – but with the Energy Assets AMR DNA machine learning system, it’s possible to assimilate two years’ worth of half-hourly gas and electricity meter data quickly and to create an energy performance model that can identify waste.
Firstly though, it’s worth focusing attention on what we mean by energy ‘waste’ because it comes in many forms:
Precedent waste: where a building does not perform as well as it has in the past (and noting that operational contexts and use-cases of a building will change and must be re-learned); Routine waste: where a building can be shown to systematically use energy that cannot be necessary or comfortable (if heating is maximised at +5°C, since colder weather requires more heating; a combination of discomfort or waste exists at all temperatures between -5°C and +5°C, for example);
Peer or benchmarked waste: where a building does not comply with its peers (for example, sets of comparable buildings are expected to have similar balance temperatures, night-setback loads and apparent occupancy patterns).
The analytics engine inherent in AMR DNA has several report modes to save energy managers’ time. These include: establishing achievable targets by KPI and weather condition for each meter; forecasting future use and identifying where changes have taken place – and diagnosing the priority and cause of savings opportunities.
The major benefit of machine learning, informed by AI, is that the platform will progressively learn what benchmark performance looks like, fine-tuning the effectiveness of the established building management system (BMS). It can also take account of variables such as weather, occupancy level and operating patterns and be integrated with building management systems.
This capability enables energy managers to model multiple energy performance scenarios using rock-solid data, to spot and fix consumption anomalies quickly.
CREATE AND ENERGY HIERARCHY
You’ve got the data, so what next? Machine learning tools can help create a consumption hierarchy to prioritise the actions that will deliver the fastest payback, whether on cost or for carbon reduction. For example, government research suggests that a reduction of 1% in average heating temperatures can lead to around an 8% cost saving.
Any successful plan will likely include a mix of practical steps, such as adjusting and tailoring heating to match occupancy levels, installing low-energy lighting etc, along with behavioural change.
One Energy Assets customer uses operational data to drive its ESOS actions and measure the contribution to efficiency of its investment in renewable energy. At the same time, staff engagement around energy efficiency is encouraged through a culture of shared ownership and individual responsibility. This includes nominating an ‘energy champion’ to undertake a daily energy walk to help to eradicate waste, identify inefficient equipment usage and flag poor energy habits.
Often, it’s a question of spotting improvement opportunities hiding in plain sight, but sometimes these can be the hardest to spot because they are ingrained in a building’s legacy performance and can be overlooked. However, with granular energy performance data – made possible by effective metering, automatic monitoring and advanced analytics – managers now have the information at their fingertips to eradicate waste and to optimise energy performance across their entire building portfolio.