IEEE.orgIEEE Xplore Digital Library IEEE Standards IEEE SpectrumMore Sites
T12: Data-driven and Light-weight ML based strategies for smart IoT - VTC2021-Fall

T12: Data-driven and Light-weight ML based strategies for smart IoT

Organizer: Swades De, Indian Institute of Technology Delhi, India

Abstract: In this tutorial we will first give a quick overview of classical approach of analyzing context-specific data traffic and optimizing the system performance. In most of the research studies of communication systems, stationarity of traffic is assumed, and the associated processes are approximated to some known “standard” distributions. We will motivate that, while such assumptions on stationarity and traffic distributions are useful for developing tractable analytical frameworks, at times such assumptions prove to be quite strong and do not necessarily result in predicting accurate performance trends. Next, we will demonstrate through examples that in modern-day IoT communications more precise context-specific optimizations are necessary. From the networked system performance optimization perspective, we will delve into application context-specific supervised as well as unsupervised learning aided dynamic system characterization and optimizations on sensing, processing, and communication strategies. Deep cross-layer interactions will be discussed, and novel research directions will be outlined on incorporating intelligence at the appropriate stages of the IoT networks, involving fog intelligence, multi-access edge computing (MEC), and smart cloud connectivity. Subsequently, from energy sustainability and green perspectives, we will investigate state-of-the-art and future directions on energy harvesting-aided and dual-powered smart IoT communications, towards converged communication and power grid networks. A few example application use-cases, namely, cognitive radio channel access, smart power grid, and smart city monitoring, will be taken to demonstrate how data-driven strategies aid in more precise performance optimization. The presentation will draw lessons from our real-life field experiments and implementations, wherever possible, and outline future research and technology trends.

Bio: Dr. Swades De received his B. Tech degree in radio physics and electronics from the University of Calcutta, Calcutta, India, in 1993, M. Tech degree in optoelectronics and optical communication from Indian Institute of Technology Delhi, New Delhi, India, in 1998, and PhD degree in electrical engineering from State University of New York at Buffalo, Amherst, NY, USA, in 2004. He is currently a full Professor of Electrical Engineering at IIT Delhi (IITD), where he holds an Institute Chair Professor position and leads the Communication Networks Research Group (IITD-CNRG). He was a tenure-track Assistant Professor of Electrical and Computer Eng. at New Jersey Institute of Technology (2004-2007). He worked as a post-doctoral researcher at ISTI-CNR, Pisa, Italy (2004), and has nearly 5 years industry experience in India on telecom hardware and software development (1993-1997, 1999). His research interests broadly in communication networks, with emphasis on performance modeling and analysis. Current directions include energy harvesting communication networks, broadband wireless access and routing, cognitive/white-space access networks, IoT communications, smart grid networks, UAVs and millimeter-wave communications.

Dr. De is a fellow of The National Academy of Sciences (India), Indian National Academy of Engineering, The Institute of Engineers, India, and The Institution of Engineering and Technology, UK, respectively. His recent professional distinctions include Om Prakash Bhasin Award for Science and Technology (2020), Ram Lal Wadhwa Award (2019), Exemplary Editor Award, IEEE Communications Letters (2018), Exemplary Reviewer Award, IEEE Communications Letters (2015). Dr. De serves as an Area Editor for IEEE Communications Letters and Elsevier Computer Communications, and an Associate Editor for IEEE Transactions on Vehicular Technology, IEEE Wireless Communications Letters, and IEEE Networking Letters. He has been involved in organizing several recent conferences in various capacities such as Workshop Co-Chair (IEEE ICDCN 2013), Symposium Chair (NCC 2013), TPC Co-Chair (IEEE ANTS 2014), Symposium Co-Chair (IEEE ICNC 2015), Symposium Co- Chair (IEEE WCNC 2015), General Co-Chair (COMSNETS 2020), Track Chair (IEEE CCNC 2021), and Lead Workshop Co- Chair (IEEE ICC 2021 Workshop on Green Solutions for Smart Environment). Dr. De currently serves as a vice-chair of the SIG on Green Cellular Networks in IEEE ComSoc TCGCC, a member of the IEEE ComSoc Educational Services Board, and a member of the IEEE TV Society ad hoc committee on AI Wireless. He is also on a few upcoming conference committees, namely, Mobile and Wireless Networks Symposium Co-Chair in IEEE ICC 2022, TPC Chair in NCC 2022, and Research Exhibits Co-Chair in IEEE GLOBECOM 2022.