Skip to main content

How AI is accelerating the transition to renewable energy

artificial intelligence
(Image credit: Image Credit: Geralt / Pixabay)

Offshore wind power has fast become one of the most promising renewable sources of energy. Its growth is expected to continue, with generation capacity predicted to soar from 35GW to 234GW over the next 10 years, according to the Global Wind Energy Council (GWEC), which ranks the UK, Germany, and China as the largest national markets. 

The sector is a particular focus in governments’ energy strategies, given the plummeting costs and the fact turbines can now be placed ever further from coastlines. Boris Johnson has even stated that he wants the UK to become the ‘Saudi Arabia of wind power’. The GWEC predicts significant growth over the next five years, with an estimated compound annual growth rate of nearly 32 percent, compared to just 0.3 percent with land-based turbines.

The transition away from fossil fuels and towards cleaner renewable sources of energy is critical to the decarbonization agenda and efforts to prevent runaway global warming. However, while that is widely accepted, few realize that the energy transition business also has areas that need to be carefully managed to ensure they don’t have a negative environmental impact. In much the same way as energy companies operate and maintain oil and gas subsea assets, wind farm cables, foundations, and all other components of the turbines also need continuous monitoring and maintenance. 

In order to access, monitor, and maintain offshore wind farms, cables, and pipes, energy companies send out large vessels that use vast quantities of fuel, are incredibly expensive to run, and are often crewed by up to 60 people, from engineers and robot drivers to cooks and cleaners. The vessels, which cost £1m to £10m a month to operate, depending on the job, will emit 275,000 tonnes of carbon over their lifetimes. 

The work is necessary and unavoidable, however innovative technologies are enabling energy companies to improve their processes and reduce the burden on the environment. By leveraging sophisticated robotics, AI, machine learning, and autonomy energy companies can significantly reduce their environmental impact and make important strides to become more sustainable. 

AI for sustainability 

It’s in the area of sustainability that AI may help reap the best rewards. Marine robotics using autonomy and machine learning technologies are pivotal in improving efficiencies and easing the transition to renewable energy sources, and ways of working in offshore environments.

While the energy industry is a relatively early adopter of robotics, the use of more advanced technologies, such as simultaneous localization and mapping (SLAM), machine learning, and increasingly autonomous ROVs (Remotely Operated Vehicles), presents an opportunity that too few are seizing. 

Seabed surveys, used to maintain wind farm assets below the surface, are carried out from vessels deploying sonars that map the seabed. For closer inspections, the majority of companies are using manually operated ROVs collecting video data. With each ROV needing at least two pilots to operate it. And then the data collected is inspected manually by an additional team. The more people you need, the bigger the ships you then require. 

While an ROV would normally run on a predefined path that the operator would follow, autonomy technology allows it to take the SLAM information and analyze “on the go”, presenting alternative options to the operator to complete its strategy whilst navigating obstacles, or course-correcting for currents. The operator can then make informed, one-touch decisions.

By enabling autonomy, fewer pilots are needed, and they can be located onshore, in a supervisory role, thereby reducing the need for bigger vessels offshore.

AI and data 

Another challenge is capturing and managing the vast quantity of unique data required for managing offshore assets. The data quantities involved in this process are huge, think 4K video streamed continuously by more than 10 cameras for one to three months - plus position, plus multibeam sonar data, plus every other data stream on the vessel and robots of which there are 20-30+ updating at least once per second, some hundreds of times per second. It can take hundreds of hours to review and analyze video images collected. Manually interpreting potential risk factors and recognizing changes in the seabed has, to date, only been done by placing tens of people offshore on each vessel to do this work.

The asset data collected from the remotely operated underwater vehicles (ROVs) is too large to be transmitted via satellites. Typically, it is manually analyzed aboard the vessels, to determine issues and potential threats, such as damage or marine growth, which can take many hours. Hours where the survey vessel remains at sea.  

However, by sharing video feeds into discrete frames and running them through Vaarst’s platform, surveyors can speed things up significantly by using ML technologies to recognize key features and abnormalities and categorize them, – enabling human operators to check the work simply to confirm the findings. This technology makes it possible to reduce not only the time needed to carry out this task but the need to take these crew members on the vessels at all, enabling the work to be done on-shore – lowering the costs significantly and preventing needless carbon emissions.

Building for the future 

By incorporating AI technology into current processes, energy companies are already aiding the transition to renewable sources of energy but in the future, we can expect to see this go further. By the year 2026 Vaarst technology alone will have enabled the removal of 75 of the large vessels currently used for offshore maintenance work. This will effectively reduce the carbon dioxide pollution in the industry by 825,000 tonnes per year. 

As the industry continues to build and innovate, there is no doubt that the lessons we learn on the seabed will drive innovation in AI into new and exciting territories. Autonomy technology along with analysis platforms can be applied to any robotics, not just undersea ROVs. It can be utilized in any environment, from the deepest sea trenches to hostile environments such as nuclear facilities, in the air using drones, or even in interplanetary discovery!

Brian Allen, Chief Executive Officer, Vaarst

Brian Allen, Chief Executive Officer, Vaarst.