China’s AI just mapped its entire renewable energy grid. Here’s why the rest of the world should pay

Every major economy is staring at the same problem right now. Artificial intelligence is consuming electricity at a pace that grids were never designed to handle. In the US, capacity market prices in PJM, the country’s largest grid operator, have risen more than tenfold in two years, with data-centre growth identified as a primary driver.

In Europe, utilities are scrambling to upgrade transmission infrastructure fast enough to keep pace with hyperscalers’ demand. The International Energy Agency (IEA) projects global data-centre electricity consumption could approach 1,000 TWh by the end of this decade. Renewable energy is largely there, but the ability to coordinate it, through AI energy grid mapping at national scales, is what most countries still lack. A study published in Nature this week by researchers from Peking University and Alibaba Group’s DAMO Academy has produced something that no country has managed before: a complete, high-resolution, AI-generated inventory of an entire nation’s wind and solar infrastructure, with the analytical framework to coordinate it as a unified system. Using a deep-learning model trained on sub-metre satellite imagery, the team identified China’s 319,972 solar photovoltaic facilities and 91,609 wind turbines, processing 7.56 terabytes of imagery to do so. Prior research into solar-wind complementarity – the idea that two sources can offset each other’s variability in time and geography – has largely relied on hypothetical or modelled deployment scenarios. How complementarity manifests under real-world infrastructure, and how it shapes system-level integration outcomes, has until now remained unclear. The researchers show that solar-wind complementarity substantially reduces generation variability, with effectiveness increasing as the geographic scope of pairing expands. In practical terms, the further apart the facilities being coordinated are, the more reliably they achieve balance. A cloud that covers solar farms in Gansu does not darken wind corridors in Inner Mongolia, for example. The study’s findings point to a structural inefficiency in how China currently manages its grid: coordination happens at a provincial rather than national level. Transitioning to a unified national scale, the researchers argue, would make it easier to pair complementary energy sources, stabilise the grid, and avoid curtailment – the wasting of generated renewable power that has long been one of China’s most costly clean-energy problems.

Key points

• In Europe, utilities are scrambling to upgrade transmission infrastructure fast enough to keep pace with hyperscalers’ demand.
• The International Energy Agency (IEA) projects global data-centre electricity consumption could approach 1,000 TWh by the end of this decade.
• Renewable energy is largely there, but the ability to coordinate it, through AI energy grid mapping at national scales, is what most countries still lack.
• A study published in Nature this week by researchers from Peking University and Alibaba Group’s DAMO Academy has produced something that no country has managed before: a complete, high-resolution,…
• Using a deep-learning model trained on sub-metre satellite imagery, the team identified China’s 319,972 solar photovoltaic facilities and 91,609 wind turbines, processing 7.56 terabytes of imagery…