← Innovations

Artificial intelligence

AI for the power grid

High-voltage transmission pylons — the physical grid that optimization software sits on
Image: Bidgee ( CC BY-SA 3.0 )
Artificial intelligence Pilot

What it is

Grid operators already use optimization. Machine learning adds faster forecasts of wind, solar, and demand, and sometimes suggests dispatch. DeepMind’s 2017–2019 work with National Grid ESO in Britain reported improved wind-forecast skill for that system — a useful increment, not a new grid. Other ISOs trial similar tools.

Problem it targets

Variable renewables need better prediction and faster control or we burn more gas “just in case.” Congestion and inverter-based stability are separate, harder problems.

How it works

Models ingest weather and SCADA-like histories and output a tighter forecast or a recommended set-point. Humans and existing energy-management systems stay in the loop. A blackout is not an acceptable training run.

Status and players

National Grid ESO / DeepMind collaboration (public 2017–2019); various U.S. ISO/RTO pilots; vendors of renewable forecasting. ENTSO-E and IEA digitalization reports survey the field.

Risks and limits

Cybersecurity, hidden bias when the weather is new, and vendors claiming an “AI grid.” Physics of inverters and protection still rules.

Sources

DeepMind blog and National Grid notes on wind-forecast collaboration (2017–2019); IEA “Digitalisation and Energy”; ENTSO-E research reports.