A pioneering collaborative artificial intelligence system designed to revolutionise asset management across the British electricity network has secured Alpha-phase funding. National Grid and Keen AI have been awarded £355,985 from the Strategic Innovation Fund, an Ofgem programme delivered in partnership with Innovate UK, to advance Foundational Shared Model Operations (FoSMo).

The project moves into its Alpha phase following a successful discovery period that proved the concept across participating networks. This next stage unites all three of Great Britain's electricity transmission operators—lead partner National Grid, SSEN Transmission, and SP Energy Networks—alongside distribution operators Electricity North West and UK Power Networks.

Rather than individual operators developing isolated detection systems, FoSMo establishes a shared AI model that standardises the collection, analysis, and execution of visual data from physical assets. By pooling anonymised industry data, the initiative establishes a single, continuously improving foundational model accessible to any participating UK operator.

Overcoming Industry Duplication

The physical electricity network across the UK functions as a single interconnected system, yet the AI technology utilised to monitor it has traditionally been developed independently. Because operators share identical components—such as cables, pylons, insulators, and fittings—they face identical asset health challenges.

However, because specific defects and component failures are rare, individual operators often lack the volume of data required to train a robust model. This lack of shared knowledge has previously forced organisations to build detection tools from scratch, leading to duplicated efforts and delays in identifying high-risk assets.

FoSMo resolves this by creating a shared foundation model that participants can fine-tune for their specific networks. The system utilizes anonymised datasets contributed by the operators under a permissive licence at no additional cost. Keen AI, which has already processed over one billion images for its UK electricity transmission and distribution clients, will act as the technical steward responsible for developing, maintaining, and hosting the models within the UK.

-- Advertisement --

By centralising industry data, the project is projected to generate more accurate models than any single operator could achieve independently, while eliminating redundant expenditures. If fully adopted by all participating operators, this collaborative framework is expected to save the industry approximately £22.6 million over a five-year period starting in 2027, driven by avoided development costs and a reduction in faults through enhanced condition assessments.

Consumer and Expansion Benefits

Though the UK features one of the most resilient energy networks globally with near 100% reliability, faults can still occur across its 500,000 miles of wires and cables. The superior condition assessments provided by FoSMo are intended to minimise the frequency and duration of power disruptions for consumers.

By identifying overhead line component defects prior to failure, the model is projected to avert roughly 85,000 consumer interruptions and 5.2 million minutes of power loss annually once fully implemented.

Furthermore, the technology is built to facilitate the rapid grid expansion needed to achieve the UK's decarbonisation goals. As new substations, overhead lines, and connection points are integrated, FoSMo delivers an immediate, ready-made AI layer to monitor those assets from day one.

Securing Sovereign Capability

The UK government has classified electricity network infrastructure as a "critical national priority" under its revised National Policy Statement for Energy, while Ofgem has characterised the ongoing grid investment programme as "a long-term insurance policy against threats to Britain's energy security."

FoSMo ensures this technological development remains inside the UK, managed by UK operators using domestically held data. By uniting major network operators under one framework, it delivers an industry-owned alternative to fragmented or international solutions, maintaining sovereign control over the technology powering Britain's energy infrastructure. The model operates under stringent data protection standards; necessary data is designed to remain controlled within each asset operator's environment, minimising long-term storage and data collection to protect the security and resilience of the system.

Matthew Ward, Innovation Engineer at National Grid Electricity Transmission (Lead Partner), said: "We recognise the significant value that AI tools can bring to enhancing operational insight and efficiency, so we're very pleased to work with Keen AI on this project.

"By pooling data and expertise, the model has the potential to support our upgrades of the grid while also making considerable cost savings across the industry."

Amjad Karim, CEO and Founder of Keen AI, added: "The UK is investing tens of billions in its electricity network. We can either build the AI that manages it ourselves or hand that capability to someone else. FoSMo keeps it here with AI developed collaboratively, data owned by the industry, and only getting better as the grid expands.

"When every major network operator shares what they know about their assets, we end up with something more robust than any of them could build alone. That's how the UK can future-proof a grid that's about to double in size."