Feature: Power


Rethinking the power architectures for AI factories


By Maurizio Di Paolo Emilio, Director of Global Marketing Communications, Efficient Power Conversion (EPC)


R


apid growth of artificial intelligence (AI) is forcing a rethink of data centre power architectures. Legacy server designs were never intended to support the


extreme power densities of modern AI workloads. Tese facilities are increasingly becoming “AI factories”, where the primary goal is to optimise compute capability in a constrained physical footprint. AI hardware evolution has shattered


the traditional power scaling path of data centres. Earlier computing platforms saw incremental increases in power consumption, but today’s AI clusters – especially those with tightly interconnected GPU fabrics – show much steeper growth curves. Availability of electrical power and physical proximity between compute elements are both critical system constraints that have a strong impact on performance. GPUs are made of billions of transistors


that are compacted on a silicon substrate with features as small as 20Å. Te power needed to turn on these billions


of processing agents is growing as fast as their computing power. Tus, the rack-level power density is no longer increasing linearly. Instead, each new generation of AI hardware can cause dramatic jumps in the amount of power required, oſten multiplying previous levels. Te resulting shiſt emphasizes power delivery infrastructure more than ever, fast becoming a critical consideration in overall system performance and layout.


Step changes in power density A key enabler for this transition is the 800VDC distribution. Te high-voltage approach allows power scaling at the rack level from lower levels to the megawatt range, which is essential for next generation accelerator platforms. Te application of 800V high-voltage


DC distribution is an attractive solution to these challenges. Higher distribution voltage directly translates into lower conduction losses, less complicated interconnect design, less copper and, therefore, lower power levels for a given power. Tis architecture dramatically


24 July/August 2026 www.electronicsworld.co.uk


enhances the power delivery efficiency and space utilisation compared with the traditional AC-based systems or low- voltage DC buses. Te other advantage is the flexibility of


the architecture. Power conversion stages with high power density can be located outside of tightly packed compute zones, freeing up valuable space for processing hardware. However, delivering 800VDC to


compute subsystems introduces new challenges in insulation coordination and device stress. Te AI workloads cause large and


rapid changes in power demands, which propagate across the entire system. To alleviate these impacts, distributed energy storage systems are increasingly used to smooth transient behaviour and maintain stability. In this sense, 800VDC is not just an optimisation but an enabling technology for the next generation of high density computing environments. It also presents an opportunity to rethink how isolation is implemented. Here, input-series output- parallel (ISOP) converter topologies


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