Huawei is betting that the future of AI infrastructure will depend as much on energy systems as on computing power
Updated
May 19, 2026 5:43 PM
Blue light painting with a lightbulb. PHOTO: UNSPLASH
As AI companies build larger models and deploy more AI agents, the industry is running into a new constraint: electricity. The challenge is no longer just about computing power. It is increasingly about how to supply, manage and sustain the energy needed to run AI infrastructure at scale.
That was the central argument behind Huawei’s latest AI data center strategy unveiled at its Global AIDC Industry Summit in Dongguan.
The company introduced what it calls a grid-interactive AIDC strategy, focused on redesigning AI data centers around power supply, cooling systems and energy management. AIDC refers to AI data centers built specifically for large-scale AI computing workloads.
The announcement reflects a broader shift happening across the industry. As AI systems grow larger, data centers are consuming more electricity and generating more heat than traditional computing infrastructure was designed to handle. Companies are now being forced to rethink not just chips and servers, but the physical systems supporting them.
Huawei argues that future AI infrastructure will need closer coordination between computing systems and energy grids. The company says traditional data center designs are struggling to keep up with fluctuating AI workloads, rising power density and the growing use of renewable energy sources.
Hou Jinlong, Director of the Board of Huawei and President of Huawei Digital Power, said: "The booming AI industry, widely adopted large models, and numerous AI agents are creating huge energy demands, set to boost the global AIDC capacity. Electricity is essential for computing; energy is the foundation for AI long-term development. Computing and electricity will deeply synergize and empower each other, progressively building an integrated framework that brings together new power systems and AI infrastructure."
A large part of Huawei’s strategy focuses on power architecture. AI workloads can create sudden spikes in electricity demand, especially in high-density computing environments. To manage that, Huawei says it plans to develop new power systems that combine grid-friendly UPS infrastructure with energy storage technologies.
Cooling is becoming another major pressure point. AI servers generate significantly more heat than traditional enterprise systems and Huawei says liquid cooling is now becoming essential for large-scale AI deployments. The company introduced a liquid cooling system designed to improve long-term thermal management inside high-density AI environments.
Huawei is also pushing modular construction methods to reduce deployment times for AI data centers. Instead of building infrastructure entirely onsite, parts of the system can be prefabricated and tested in factories before installation.
Bob He, Vice President of Huawei Digital Power, said: "The global AI industry is booming, and the token demand surges. As such, the AIDC industry is entering the Token era."
As part of that shift, Huawei introduced a proposed measurement system called the TokEnergy Index. The company says the metric is designed to measure the relationship between energy consumption and AI computing output, rather than relying only on traditional data center efficiency metrics such as PUE.
The broader message behind the strategy is that AI infrastructure is becoming an energy engineering problem as much as a computing problem. As global demand for AI continues to rise, companies across the sector are beginning to realise that the future of AI may depend not only on better models, but also on whether power grids and data centers can keep up with them.
Keep Reading
The quiet infrastructure shift powering the next generation of data centers
Updated
February 12, 2026 1:21 PM
Peripheral Component Interconnect Express (PCIe) port on a motherboard, coloured yellow. PHOTO: UNSPLASH
Modern data centers operate on a simple yet fundamental principle: computers require the ability to share data extremely quickly. As AI and cloud systems grow, servers are no longer confined to a single rack. They are spread across many racks, sometimes across entire rooms. When that happens, moving data quickly and cleanly becomes harder.
Montage Technology, a Shanghai-based semiconductor company, builds the chips and connection systems that help servers exchange data without delays. This week, the company announced a new Active Electrical Cable (AEC) solution based on PCIe 6.x and CXL 3.x — two important standards used to connect CPUs, GPUs, network cards and storage inside modern data centers.
In simple terms, Montage’s new AEC product helps different parts of a data center “talk” to each other faster and more reliably, even when those parts are physically far apart.
As data centers grow to support AI and cloud workloads, their architecture is changing. Instead of everything sitting inside one rack, systems now stretch across multiple racks and even multiple rows. This creates a new problem: the longer the distance between machines, the harder it is to keep data signals clean and fast.
This is where Active Electrical Cables come in. Unlike regular copper cables, AECs include small electronic components inside the cable itself. These components strengthen and clean up the data signal as it travels, so information can move farther without getting distorted or delayed.
Montage’s solution uses its own retimer chip based on PCIe 6.x and CXL 3.x. A “retimer” refreshes the data signal so it arrives accurately at the other end. This allows servers, GPUs, storage devices and network cards to stay tightly connected even across longer distances inside large data centers.
The company also uses high-density cable designs and built-in monitoring tools so operators can track performance and fix issues faster. That makes large data centers easier to deploy and maintain.
According to Montage, the solution has already passed interoperability tests with CPUs, xPUs, PCIe switches and network cards. It has also been jointly developed with cable manufacturers in China and validated at the system level.
What makes this development important is not just speed. It is about scale. AI models, cloud services and real-time applications demand massive amounts of data to move continuously between machines. If that movement slows down, everything else slows with it.
By improving how machines connect across racks, Montage’s AEC solution supports the kind of infrastructure that next-generation AI and cloud systems depend on.
Looking ahead, the company plans to expand its high-speed interconnect products further, including work on PCIe 7.0 and Ethernet retimer technologies.
Quietly, in the background of every AI system and cloud service, there is a network of cables and chips doing the hard work of moving data. Montage’s latest launch focuses on making that hidden layer faster, cleaner and ready for the scale that modern computing now demands.