Five smart energy AI innovations
Image: DNV
AI and its spin-off generative AI have been making headlines almost daily, for both the innovations that it is bringing but also for its growing energy consumption.
Here are five projects and initiatives that over the past year have highlighted the increasing role of AI as a key tool in the evolving energy sector and the energy transition.
Paris Olympics taps AI cloud solution to measure power consumption
The Paris Olympics International Olympic Committee (IOC) deployed the ‘Energy Expert’ data-driven and cloud-based solution to help measure and analyse smart meter-gathered power consumption data from across all 35 competition venues of the Paris 2024 Olympics Games.
According to Alibaba Cloud, which owns Energy Expert, migrating intelligence on power consumption and demand of the competition venues will enable more accurate analysis and better-informed power consumption planning for future Olympic Games.
AI subsurface sensor investigated for powerline undergrounding in US
In the aftermath of Hurricane Beryl, which highlighted the vulnerability of overhead powerlines in the face of extreme weather, researchers in the US are looking to develop a state-of-the-art subsurface sensor system with AI and drones to guide safe and efficient underground powerline installation.
The project aims to create a subsurface, real-time, high-resolution look-ahead sensor system to detect underground obstacles in front of a drill bit.
Iberdrola looks to generative AI to drive energy sector innovation
Iberdrola is partnering with Amazon Web Services to use technologies including AWS Lambda and Amazon Bedrock and SageMaker to develop generative AI applications to support customer engagement and drive efficiencies in energy production and within the wider business.
Earlier this year, Iberdrola established a generative AI ‘centre of excellence’ with AWS to develop more than 100 generative AI applications that enhance the customer experience, support employees and improve business processes.
Quantum AI framework to reduce data centre energy consumption
A new quantum computing-based optimisation framework developed by researchers at Cornell University could reduce energy consumption in large AI workload data centres by up to 12.5%.
The framework aims to address the challenge by integrating variational quantum circuits with classical optimisation to enable efficient and uncertainty-aware control of energy systems and includes uncertainties associated with weather conditions and renewable energy generation while optimising the energy consumption in the AI data centres.
Electricity grid patents surge with AI solutions review finds
Grid related patenting has grown seven fold over the last 20 years with the largest growth in the period 2009-2013, attributed to a period of intense industrial interest in a new suite of smart grid technologies.
However, while the growth has continued more recently but at a slower rate it is now being driven by grid-related AI patenting, which has grown by over 500% in the five years to 2022 and is now the most active area of patenting among enabling digital technologies.
