search.noResults

search.searching

saml.title
dataCollection.invalidEmail
note.createNoteMessage

search.noResults

search.searching

orderForm.title

orderForm.productCode
orderForm.description
orderForm.quantity
orderForm.itemPrice
orderForm.price
orderForm.totalPrice
orderForm.deliveryDetails.billingAddress
orderForm.deliveryDetails.deliveryAddress
orderForm.noItems
THERMAL MANAGEMENT


The rise of dual systems thinking in power and thermal strategy


By Dominik Dziarczykowski, market development manager, high density & liquid cooling at Vertiv


F


or years, power and thermal planning have operated as separate disciplines in data centre design. Cooling was a mechanical issue. Power, an electrical one. Engineers might share blueprints, but rarely strategies. Now, as AI workloads drive up densities and volatility, that separation is breaking down. A new model is emerging - one built not around individual systems, but around synergy. Known as dual systems thinking, this approach recognises that no single component can be optimised in isolation. Instead, resilience and performance are achieved through pairing: air and liquid cooling working in tandem; uninterruptible power supply (UPS) systems matched precisely with battery chemistries; software orchestration tightly integrated with hardware infrastructure.


The limits of bolt-on thinking The legacy model relied heavily on bolt-on upgrades; add liquid cooling to an air-


optimised build; stack in more batteries; use software to patch the gaps. The method was clear. However, today these workarounds are reaching the edge of their usefulness. AI workloads do not just increase density, they introduce volatility. Racks go from idle to full load in seconds, thermal spikes can be immediate and severe, power draw is unpredictable and often exceeds the assumptions built into traditional designs.  air-optimised system, for example, might help temporarily - but it doesn’t resolve the underlying disconnect. Air and liquid interact differently with hardware. Each responds to load in different ways, and each affects the performance of the other. Without integration, they compete rather than complement. The same holds true for power. A UPS designed for long outages may be poorly suited to the fast-switching needs of AI processing. Batteries chosen for runtime might underperform in environments where stability


30 JULY/AUGUST 2025 | ELECTRONICS FOR ENGINEERS


and rapid cycling matter more and yet, many facilities are still making these decisions independently.


Instead, what works is design that starts with integration. That means planning liquid and air cooling together, pairing power delivery with software that can anticipate and respond  systems with batteries - not just by capacity  thermal behaviour.


Pairing up: What dual systems look like


Vertiv’s work with key partners like NVIDIA has highlighted what dual systems thinking looks like in practice. The shift is not theoretical, it is architectural.


Rather than choosing between liquid and air cooling, facilities are planning systems


Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36  |  Page 37  |  Page 38  |  Page 39  |  Page 40  |  Page 41  |  Page 42  |  Page 43  |  Page 44  |  Page 45  |  Page 46