The Department of Energy (DOE) has awarded Argonne National Laboratory and Northwestern University $1.2 million over three years to pioneer new artificial intelligence for 5G-enabled edge computing.
The money will be used to help researchers maximize the scientific data that can be sent over 5G networks.
This new global wireless standard already promises to dramatically enhance efforts in multiple fields, including environmental and atmospheric science.
“By combining the newest breakthroughs in AI learning and low-power AI accelerators … our 5G research project will give scientists new capabilities for adaptive, responsive and smart distributed sensor networks.” — Pete Beckman, Co-Director, Northwestern Argonne Institute of Science and Engineering
The existing 4G network was designed to send information back and forth between a data center and a handset. The new 5G technology, which is currently being rolled out nationally, supports computing within the network, from the edge devices, such as cameras and weather sensors, to the radio towers between the edge and the cloud.
Instead of simply moving data, the new 5G network supports computation at every point along the digital continuum, from a sensor that measures a farmer’s soil moisture or a micro radar unit tracking and predicting the path of a storm to the radio towers where data is aggregated and then sent to the data center.
Argonne has long been a force in this arena. Its edge sensing platform, Waggle, has led the industry in AI-enabled edge sensing for years. It was used by the University of Chicago’s Array of Things project to deploy more than 100 intelligent sensors throughout the city to better understand urban dynamics.
The newest version of Waggle is being used by Northwestern University’s Sage project to understand ecosystems and help predict wildfires in Colorado, California and Oregon.
Argonne’s edge platform will also be a key enabling technology for the laboratory’s 5G research.
“By combining the newest breakthroughs in AI learning and low-power AI accelerators, Wildebeest, the name of our 5G research project, will give scientists new capabilities for adaptive, responsive and smart distributed sensor networks,” said Pete Beckman, Co-Director, Northwestern Argonne Institute of Science and Engineering. “Wildebeest will support advanced AI that can ‘migrate’ across the digital continuum to allow us to start automatically optimizing sensors and instruments in the field to report the most scientifically valuable data in real-time.”
Beckman and his team are excited about the new network’s capabilities: 5G is far more adaptive than the one in use today.
With 4G technology, bandwidth is managed by the provider. With 5G, users can dynamically adjust their requests for the network, from bandwidth to latency.
Scientists also can build out 5G wireless infrastructure in remote areas where no commercial service is available. Users can set up their own towers — small devices that might enable wireless services for several miles — allowing greater access to remote areas, like the far corners of Alaska, rural Oklahoma, or in partnership with tribal communities working on remote ecosystem monitoring.
And, 5G supports dynamic adjustments to the radio frequencies used by the network. Leveraging AI to make real-time decisions, Argonne will explore new techniques for automated radio management that will depend on localized atmospheric conditions and the scientific goals for the distributed sensing.
The goal of Argonne’s 5G project is to develop new algorithms for AI spanning the digital continuum to improve distributed scientific instruments that can use the new network.
By leveraging the latest AI central processing units in Waggle, such as the NVIDIA Xavier NX, Argonne will build a prototype 5G testbed where AI workloads can migrate from edge to cloud, based on the scientific needs.
“With Wildebeest, distributed sensor networks will take a step toward autonomous sensing, automatically finding the most important data and using edge computing to respond hundreds of times faster,” said Nicola Ferrier, Argonne scientist on the Wildebeest project and lead for the AI algorithm research.
Argonne National Laboratory seeks solutions to pressing national problems in science and technology. The nation’s first national laboratory, Argonne conducts leading-edge basic and applied scientific research in virtually every scientific discipline. Argonne researchers work closely with researchers from hundreds of companies, universities, and federal, state and municipal agencies to help them solve their specific problems, advance America’s scientific leadership and prepare the nation for a better future. With employees from more than 60 nations, Argonne is managed by UChicago Argonne, LLC for the U.S. Department of Energy’s Office of Science.
The U.S. Department of Energy’s Office of Science is the single largest supporter of basic research in the physical sciences in the United States and is working to address some of the most pressing challenges of our time. For more information, visit https://energy.gov/science.