10x the capacity with half the energy: Site-specific deep learning for 6G

Abstract: The key requirements for the 6G era are 10x the capacity of 5G with roughly half the power consumption, while achieving global connectivity and enabling new network services such as sensing and compute. It is a daunting needle to thread, and this talk argues that a key tool will be site-specific deep learning (SSDL). We first show the immense and perhaps underappreciated potential of SSDL, with a focus on two ongoing research projects in my lab. The first shows how order of magnitude improvements in coverage and energy consumption at millimeter wave can in principle be achieved with SSDL. The second shows how FR3 spectrum (7-15 GHz) can use SSDL, focusing on increased capacity with decreased overhead in the context of multiuser MIMO. Next, we consider the “how” of SSDL for 6G: how to train and bring these ML models online in 6G networks, which is a major open challenge. We discuss offline initial training via digital twins and other ray tracing based tools, as well as incremental online training using noisy real world measurements and generative AI.

This work is supported by and done in collaboration with NSF, Nokia, Samsung, Nvidia, and Keysight.

Speaker Biography:
Jeffrey Andrews (S’98, M’02, SM’06, F’13) received the B.S. in Engineering with High Distinction from Harvey Mudd College, and the M.S. and Ph.D. in Electrical Engineering from Stanford University. He is the Truchard Family Chair in Engineering at the University of Texas at Austin where he is Director of the 6G@UT research center. He worked at Qualcomm (1995-97) on CDMA and Globalstar, and has served as a consultant to Samsung, Nokia, Qualcomm, Apple, Verizon, AT&T, Intel, Microsoft, and NASA. His former students include 12 faculty members, 5 IEEE Fellows, and several leading innovators on LTE and 5G on which they collectively hold over 1,000 US Patents.

Dr. Andrews is an IEEE Fellow and ISI Highly Cited Researcher. He is the co-author of four books, and his papers have received 16 best paper awards including the 2016 IEEE Communications Society & Information Theory Society Joint Paper Award, the 2014 IEEE Stephen O. Rice Prize, the 2014 and 2018 IEEE Leonard G. Abraham Prize, the 2011 and 2016 IEEE Heinrich Hertz Prize, and the 2010 IEEE ComSoc Best Tutorial Paper Award. His other major awards include the 2015 Terman Award, the NSF CAREER Award, the 2021 Gordon Lepley Memorial Teaching Award, the 2021 IEEE ComSoc Joe LoCicero Service Award, the 2019 IEEE Wireless Communications Technical Committee Recognition Award, and the 2019 IEEE Kiyo Tomiyasu Award.