Eaton, a global player in power management, has rolled out a new technology designed to tackle a growing challenge in data centers: identifying large fluctuations in energy demand from artificial intelligence (AI) computing infrastructure. The edge-based solution, available via a firmware update for its Eaton Power Xpert quality (PXQ) event analysis system, is engineered to detect AI power bursts, including potential subsynchronous oscillations (SSO) in data centers.
The update empowers operators to better protect critical infrastructure and bolster resiliency as AI energy needs escalate. The increasing power demands of AI data centers have given rise to “power bursting,” or unforeseen spikes in energy usage due to the intensive computation needs of GPU servers powering AI workloads. SSO can inflict severe, costly damage to both data center infrastructure and the grid, which may not be equipped to handle these large load swings. Therefore, it’s crucial for operators to identify and mitigate SSO bursts before they lead to costly outages due to transformer overheating, ferro-resonant damage, and other impacts on equipment.
Eaton’s PXQ is a versatile power quality meter for switchgear, switchboards, and power distribution units (PDUs) that integrates sophisticated edge analytics to streamline the identification and resolution of power quality events such as sags, swells, transients, and harmonics. Now, through a PXQ meter remote firmware upgrade, customers can leverage their system to reliably detect SSO and allow operators to take preventive actions to resolve issues before they cause lasting damage to data centers and the grid.
“The energy demands of AI workloads surpass anything data centers and the grid have encountered before, with load fluctuations that can exceed the limits of existing infrastructure,” said JP Buzzell, vice president and chief data center architect at Eaton. “By enabling customers to harness their existing PXQ technology in new ways, we’re delivering a market-first capability to effectively respond to AI power bursts. Our SSO detection solution marks a major milestone in our grid-to-chip strategy, which empowers data center operators with innovative tools to address and manage the energy challenges posed by AI.”
Eaton’s grid-to-chip strategy employs intelligent power distribution systems, backup power solutions, digital offers, and other technologies to help operators optimize white and gray space in AI data centers. Other key milestones in this approach include Eaton’s recent announcement of its collaboration with NVIDIA to help lead the transition to 800 VDC power infrastructure to support 1-MW racks and beyond, as well as its collaboration with Siemens Energy for a fast-track approach to build data centers with integrated onsite power.
This development underscores the growing need for advanced power management solutions in the face of burgeoning AI workloads. As AI continues to push the boundaries of computational power, the ability to detect and mitigate power bursts will be crucial for maintaining the reliability and efficiency of data center operations. Eaton’s initiative sets a precedent for other players in the sector, highlighting the importance of proactive power management in the AI era. The collaboration with industry giants like NVIDIA and Siemens Energy further emphasizes the collective effort required to address these challenges and pave the way for more resilient and efficient data center infrastructures.