A schematic of the Danish grid exploded into color-coded zones. The Esbjerg industrial cluster went dark—a satisfying, violent grey. Then the eastern suburbs of Aarhus. But the core—the data centers, the hospital, the airport—stayed a steady, pulsing green.

Outside, a faint wind began to blow again. The turbines turned, slowly at first, then with more purpose. In the digital twin inside the machine, the world was still broken. But on the ground, the lights stayed on.

“Lena, I need you to call the HVDC station in Sweden. Tell them to prepare for a forced rectifier shutdown in ten minutes. Not a trip—a controlled separation.”

The software was a beast. But the 2021 version had a secret weapon: an AI-assisted grid splitting tool. It could predict the exact moment and location to island parts of the network, sacrificing some zones to save the core. Aris’s fingers flew across the keyboard. He imported live SCADA data into Powerfactory’s state estimator. The software chewed on it, then spat out a probability:

And in the corner of the Powerfactory window, a small green notification blinked:

Lena came closer. “That’s just a simulation model. We never field-tested it.”

“We are now.”

“It’s the frequency,” Aris muttered, not looking away. “49.2 Hz and dropping. The inertia from the gas plant is gone. The wind turbines are trying to compensate, but their power electronics can’t mimic real spinning mass.” He tapped a command into the Powerfactory model. On the screen, a dynamic simulation of the entire North Sea grid unfolded like a nervous system. Green lines of healthy flow turned orange, then red. A cascading failure propagation algorithm was already running.