Jodie Eaton, CEO of Shell Energy UK, explores the opportunities presented by smart technologies and artificial intelligence (AI) as businesses navigate the complex landscape of renewables, storage and onsite generation to achieve their decarbonisation goals.
According to the latest progress report to parliament from the Climate Change Committee (June 2023), the UK’s industrial emissions fell by 3% in 2022 to 63 million tonnes of carbon dioxide equivalent (MtCO2e).[1] While positive, the pace of industrial decarbonisation will need to accelerate over the next decade to meet ambitious government targets.
The government’s Carbon Budget Delivery Plan (CBDP)[2] requires industrial emissions to fall by 8% on average annually between 2022 and 2030.[3] It also says that there continues to be a lack of available data in the industrial sector, which limits monitoring, evaluation and policy implementation.
Good data is crucial to drive strategic decision-making, especially when it comes to improving business performance and costs. From gathering market trends, to optimising the operational efficiency of production processes or finding ways to control energy spending, accurate and timely data has the potential to deliver significant rewards,
However, accessing the right data can be operationally complex. In fact, the most prevalent obstacle to reducing carbon emissions is a lack of sufficient data to baseline and monitor energy emissions. This insight was revealed in a recent survey commissioned by Shell Energy, where 69% of respondents indicated that access to accurate data was their most significant challenge.[4]
Smart technologies and AI have the potential to provide businesses with access to the kind of data that can unlock opportunities to drive efficiency, plan investment and resolve issues to enhance performance in real time.
A crucial role for smart technologies and AI
Smart technologies can be found on a range of systems including air conditioning units, lighting and energy storage systems, enabling them to both communicate and optimise local energy consumption in response to demand. These enhancements can have a positive impact on energy savings, CO2 emissions, asset life cycle and/or operation and maintenance costs.
As society becomes more reliant on intermittent renewable energy sources, the need to match demand with supply requires accurate forecasting. This has a vital role to play in delivering supply security and identifying how to deploy new technologies effectively to drive efficiencies and optimise performance.
This is where AI comes in. By harnessing big data to quickly analyse past patterns, current conditions and future predictions, AI algorithms can inform generation forecasting by predicting when (and how much) energy is likely to be produced from resources such as wind and solar. This, in turn, can be used to inform future energy management decisions – maximising efficiencies and helping to balance supply and demand.
AI already supports smart grids and demand side response, by monitoring and diagnosing system problems to avert blackouts, as well as balancing intermittent resources and leveraging load flexibility through curtailment (a deliberate reduction in output below what could have been produced in order to balance energy supply and demand). It also plays a crucial role in optimising the operation of onsite energy storage systems, ensuring the efficient utilisation of stored energy during periods of limited renewable generation, enabling a continuous supply of low carbon energy when needed.
Companies across the manufacturing and construction industries harnessing this capability most effectively, with the former using it to autonomously optimise efficiencies and guarantee backup power in times of peak demand, and the latter to operate seamlessly in harsh environments.[5] Elsewhere, AI is being used to improve wider energy consumption efficiencies. The Google DeepMind project, for example, saw historical data used alongside machine learning capability to accurately predict exacting upcoming requirements, rather than estimated. This, in turn, prevented over-cooling and enabled savings of 40%.[6]
Another area where AI is able to offer significant value is through predictive maintenance in industries including automotive, oil and gas, chemicals and aerospace.[7] Data can be harnessed to proactively flag equipment service requirements ahead of time, rather than waiting for problems to occur and reactively fixing them. This, in turn, helps to optimise the efficiency of equipment and mimimises downtime.
At a Shell refinery in the Netherlands, for example, AI is used to detect valve control issues. With thousands of data points captured every minute, anomalies are spotted and alerts triggered so that further investigation can take place. This not only alleviates the risk of equipment failure, but also prevents parts from being preemptively changed while still in good condition.[8]
Another area where AI can support decarbonisation is through Carbon Capture and Storage (CCS), where it has the ability to improve the efficiency of CCS processes by optimising the capture of carbon dioxide from the atmosphere or emission sources.[9] For instance, machine learning (ML) and deep learning (DL) can be harnessed to identify the most suitable methods for using captured carbon, whether for industrial processes or safe long-term storage.
Smart technologies working with AI are helping to create intelligent, responsive energy systems. They see a myriad of variables plugged in to provide information not just on energy consumption in real-time, but also on factors that can influence energy use, from external temperatures to the availability of onsite generation or stored energy. This can give businesses far greater control over how they buy, use, store and – in some cases – generate their energy to meet fluctuating demand.
The combination of real-time information and forecasting capabilities helps businesses to strike the right balance between load curtailment and operational needs. With advanced knowledge of the expected timing of peak events and energy prices, customers are able to strategically respond in ways that deliver cost as well as energy savings.
Grid optimisation, optimal use of intermittent renewable energy sources and flexible load management are just a few of the ways in which AI can help energy users to adapt to a rapidly changing landscape. By embracing the potential of smart technologies and AI, businesses can navigate the challenges of decarbonisation with confidence and accelerate the transition towards a sustainable and resilient future.
For more information on how Shell Energy can support your business visit www.uk.shellenergy.com.
[1] https://www.theccc.org.uk/wp-content/uploads/2023/06/Progress-in-reducing-UK-emissions-2023-Report-to-Parliament-1.pdf
[2] https://www.gov.uk/government/publications/carbon-budget-delivery-plan
[3] Progress in reducing UK emissions – 2023 Report to Parliament (theccc.org.uk)
[4] Survey of 100 decision makers spending more than £250K a year on energy (June 2023)
[5] https://www.startus-insights.com/innovators-guide/applications-of-energy-storage/#:~:text=Manufacturing%20and%20construction%20industries%20leverage,environments%20and%20provide%20backup%20power.
[6] https://deepmind.google/discover/blog/deepmind-ai-reduces-google-data-centre-cooling-bill-by-40/
[7] https://www.startus-insights.com/innovators-guide/emerging-predictive-maintenance-startups/#:~:text=That%20is%20why%20the%20automotive,their%20infrastructures%20and%20remote%20assets.
[8] https://www.shell.com/energy-and-innovation/digitalisation/digitalisation-in-action/industry/_jcr_content/root/main/section/simple/list/list_item/links/item0.stream/1650525120832/dabc9c17a2c9a00d39cb4f442e75d667920c8562/the-shell-journey-towards-global-predictive-maintenance-velthuis.pdf
[9] https://www.sciencedirect.com/science/article/abs/pii/S0048969723025342
