AI’s Impact from the Perspective of a CSO and CTO

Although by no means a silver bullet, AI is having an undeniable impact on the energy industry.
And it's not just technology-focused minds who think and know so.
Sophie Graham is the CSO of software development giant IFS and Kevin Miller is its Americas CTO.
Despite working in different areas of the business, they are united by their common use of AI for the benefit of the energy industry and wider sustainability.
In this roundtable, the two execs explore how AI is enhancing energy infrastructure’s efficiency and reliability, as well as modernising existing infrastructure to enable a more sustainable energy world.
How is IFS leveraging AI to enhance the efficiency and reliability of energy infrastructure?
Sophie: I think one of my favourite examples is predictive maintenance. E.ON did a study where they showed predictive maintenance can actually reduce outages in the grid by 30% compared to conventional approaches.
The majority of maintenance work tends to be one size fits all and is scheduled maintenance that just happens. Predictive maintenance can be much smarter about that and target when and where in particular to extend the asset lifecycle and increase reliability.
If you look at wind turbines for example, 80% of the lost energy from wind turbines is due to poor maintenance of the blades. It's mind-blowing.
So when you start to then leverage predictive maintenance, you can increase the reliability of the asset and that supply of renewable energy. I think that's critical because the unpredictability of renewable energy like wind and solar is a common pain point.
One of our customers, Torresol Energy in Spain, uses IFS’ enterprise asset management (EAM) solution and we’re deploying in tandem with their maintenance partner who uses sensors that are across their assets, totalling 70,000 input points and tags. This gives you, in real-time, data on how the asset is performing, highlighting how and where maintenance may be needed and allowing maintenance to be much more targeted, therefore increasing the reliability of that renewable energy supply.
Kevin: AI has been unfortunately pitched by our industry as this magic box we can open that solves all problems. But at IFS, we have been focusing our messaging on what we call Industrial AI. This means going back to our customer base to ask for some real-world examples so we can help from a tech perspective in managing assets.
It really comes down to a couple of things in my opinion.
One is asking what that customer wants to achieve in terms of uptime and outcomes for their customers. This means less service disruption for utility organisations, more clean energy focus, more reliability and having to keep all of those streams stable.
What IFS has done is built these use cases out to see how we can look at the data we've accumulated for those assets, but more importantly, how we can analyse that data.
Say, from a predictability perspective, we're ingesting sensor data from assets. We might see the temperature rising on a particular component, one degree every hour over the last eight hours. This means we should immediately dispatch someone with the right spare parts, with the right certifications and knowledge so that it's addressed before causing an outage or some other catastrophic event.
In what ways can AI optimise energy consumption and improve grid resilience in industrial settings, particularly with the increasing integration of renewable energy sources?
Sophie: IFS has a tool called What If Scenario Explorer, which helps companies get comfortable with shifting to electric vehicles (EVs) or different sources of energy, for example. It can model what the impact will be on your operational and financial KPIs. I find that interesting because a lot of the time, companies need to get comfortable with change. If I shift to a different energy source, or a different way of working, what's that going to do to my fleet time or engineer? That's typically something that we help them model out.
Copperleaf helps compare apples with elephants, analysing hundreds of thousands of different potential investment cases to see which is the best investment case. Do you upgrade that existing infrastructure? Do you go for something completely new? Do you leave it as is? What does that do in terms of your risk appetite, your operational goals or KPIs, your financial metrics or sustainability goals?
Kevin: One of the best aspects of this example is that IFS contains a lot of data in transactions from our customers throughout the day. IFS has a large amount of data that we're amassing and able to analyse, but one of the key trends right now is that we're able to start looking at what's referred to as unstructured data. Whether that's weather information and weather data for better planning for storms, IFS can help to plan by pre-staging labour, spare parts or different equipment for when a storm comes through.
Additionally, can we also look at consumption rates by provider to guide our customers, perhaps advising that if they consume energy at these hours instead of these hours, we might be able to consume it at off-peak rates or can incorporate more wind or more solar into the consumption mix.
We can look at both the data that the customer is producing from a consumption perspective, but also provider information and other factors to help guide the customer in terms of how to consume that energy and when.
What challenges do you foresee in implementing AI-driven solutions within the energy sector, especially when it comes to infrastructure upgrades and regulatory compliance?
Sophie: In heavily regulated industries, a common challenge is that they tend to be more set in their ways of working because the regulator mandates it and they get used to working in those ways.
I think it’s about behaviour change, being more agile and receptive to different potential use cases of AI and also testing the value AI is bringing.
At IFS, we have a real focus on the time-to-value of AI implementation. How long does it take to start seeing business benefits? There's a lot of hype around things like generative AI, but in many cases, it has yet to prove its benefit. We have a real focus on what that time-to-value looks like so we can help the organisation get comfortable with the investment in AI.
Although we’re now talking a lot about generative AI, some of this industrial AI that the IFS is in has been around for a while. This is not something completely new. We have tried and tested use cases, customer success stories, and can model out what that looks like in terms of the financial benefits, the productivity benefits and the sustainability benefits. I think for me that's where we have some really good tried-and-tested AI use cases and that helps people get comfortable.
Kevin: There are a couple of things that are important to note here. One is that everything hinges on the quality of data. This means we might have mountains of data that we can go through and check for anomalies or guidance, but if that data is not good, the outcome won't be good. The first thing has to be a quality set of data with a true strategy around what outcomes we hope to get from that.
When I look at even IFS’ acquisition of Copperleaf, this gives us the ability to also layer on top of what would be the best approach for our customers in terms of ranking those investments.
There are a lot of things to look at, but data is the key piece here because if we have incorrect data, we can have hallucinations and therefore the wrong recommendations.
The second important thing is that AI offers a lot in terms of automation. It gives us the ability to get rid of some busy work and perform deeper analysis, but if we're removing human components of that, where are the checks and balances to make sure that what we're constantly modelling and tweaking is what we expect and what we want to come out of the system? We must have the availability of checkpoints in that automation to make sure that AI is functioning the way we designed it.
How can AI technologies contribute to predictive maintenance in energy systems? What impact does this have on operational costs and sustainability efforts?
Sophie: Predictive maintenance is top of mind for me. Going back to Torresol as an example, I feel that this is interesting and something that not many people are talking about.
Continuous monitoring of the performance of energy assets is so critical in a world that's diversifying its energy sources and can't compromise on reliability, that's critically important. To be comfortable with the provision and reliability of that energy source means tools like predictive maintenance are critical.
Kevin: Let’s say I want to monitor a transformer in the field. I can say to IFS that we have performed all the preventive maintenance, what's the realistic lifespan and health of this asset at any given point in time? What AI can do to help us there is make sure we're providing the right maintenance, whether it's predictive, proactive or even preventive on schedules that the manufacturer has dictated to us. And if I'm doing those things, am I optimising the efficiency of that asset but also the lifespan of that asset? And that's one of the key differentiators that IFS offers in this space.
The other thing we have when we look at the work that needs to be completed, if IFS ingests a sensor code that says that this is an X alarm fault, we not only know what that means, but we know which technician we should dispatch to it with the right certifications, we also can recommend which spare parts to send because it knows through the analysis of the data we needed these spare parts to fix it. This means technicians don’t need to be making multiple trips out to diagnose and repair. Every one of those pieces in that chain has the ability to either impact positively or negatively on consumption of energy within the sustainability chain.
For example, utility PG&E can, based on prior events, detect certain wind gusts and if they blow above a certain threshold, they turn the power off. This is to prevent fire from wind damage or other things that could potentially cause bad environmental impact and outages.
When they determine the wind has died down and they can turn the power back on, it takes hours for them to survey every line to make sure there's no debris or interference. But if we are even able to dispatch drones for that inspection of the lines, that alone means we’re getting much more efficient in preventing what could be a catastrophic impact. Those are more of the real-world examples that I'm seeing from prospective customers and customers and how they're managing or using technology to prevent issues.
To read the full article in the magazine, click HERE.
Explore the latest edition of Energy Digital Magazine and be part of the conversation at our global conference series, Sustainability LIVE.
Discover all our upcoming events and secure your tickets today.
Energy Digital is a BizClik brand
- How Google’s AI Chips are Boosting Chip Carbon EfficiencyTechnology & AI
- Is AI Data Centre Thirst Contributing to Mass Energy Waste?Technology & AI
- Maersk: Methanol Vessels Pioneer Sustainability Growth & ESGSustainability
- ABB, Sage and Meta: Partnering to Boost Geothermal EnergyRenewable Energy