5G, Ai, and IoT edge processing drive thermal design priorities
Emerging technologies are pushing the boundaries of design engineers working to deliver products that are safe, powerful, and reliable. Increasingly, concern about thermal applications and the application of thermal analysis are critical parts of the process of designing electronics devices for the IT and data center sectors.
Image: Future Facilities
In the coming year, new thermal design priorities will largely be driven by technologies such as artificial intelligence (AI), the internet of things (IoT), 5G, and edge computing, recent research from Future Facilities, which makes thermal design software, found. “Recent advancements in technology over the past few years have resulted in unprecedented changes in the way engineers view their designs,” said Chris Aldham, product manager at Future Facilities. “The introduction of AI, 5G, edge computing, and the internet of things all have major implications for how — and where — electronics need to operate, and that, in turn, means a whole host of new considerations from a thermal perspective.”
In a digital roundtable event, thermal designers, engineers, and experts from a variety of organizations — including Facebook, HP Enterprise, QuantaCool, Engineered Fluids, CommScope, Vertiv, 6SigmaET, and Binghamton University — gathered to compare notes. The group identified a handful of thermal design priorities, including:
The need for hybrid cooling to cope with new IoT environments
Remote monitoring of cooling systems in edge-computing devices
More accurate monitoring and simulation of energy use in data centers
Thermal cooling solutions for 5G base stations and new AI hardware
Tools that can accurately simulate these new technologies and environments
Design engineers currently understand the complexity of thermal issues relating to these new technologies but are working to understand the nuances. For example, while engineers understand the demands that AI puts on processing power and the vast amounts of data generated, they may not know the best say to cool these systems or how to tackle high power consumption, Aldham explained. IoT, meanwhile, presents other challenges, such as the ways that demand for increased functionality and decreased device size changes how thermal management should be handled. “Both AI and the IoT will drive innovative cooling solutions in the future in order to meet changing thermal demands,” said Ernesto Ferrer, thermal engineer at HP Enterprise. “Components and systems that were air-cooled will need to use evermore innovative cooling techniques — increasingly liquid cooling, hybrid cooling, and full immersion cooling.”
Furthermore, engineers are grappling with the potentially harsher environments that will be present in emerging edge data centers. “Edge computing will mean taking data centers in a telecom-centric direction; this will require a cross-over period between these two industries that tend to cool their systems in completely different ways,” said Tom Craft, director of engineering at CommScope.
Image: Future Facilities
Furthermore, the push for thermal testing is being exacerbated by the ways that emerging technologies are being used in combination. Aldham told EEWeb:
“5G, AI, and edge all need to come together, and it may not be easy to just consider one or the other aspect in isolation. For systems like autonomous vehicle driving, high-speed communication (5G) is necessary to local compute facilities (edge) because transfer of large amounts of data to a centralized data processing plant will take too long, and this facility must use high-power AI algorithms to process the data efficiently and accurately.”
In these new technology frontiers, designers will be tasked with making sure that devices are affordable and easy to maintain. “Thermal engineers must be able to quickly adapt designs for these new technologies,” said Aldham. “As power densities increase, more complex cooling systems must be developed to keep IT equipment operating. Thermal simulation can help develop the complex solution and reduce the development time.”
>> This article was originally published on our sister site, EEWeb: "AI, IoT, 5G, and Edge Computing Shape Thermal Design."
Hailey McKeefry is Editor in Chief of EBN.