Abstract
Internet-of-Things (IoT) has widely permeated our daily lives and is used for various applications ranging from agriculture to industrial IoT. Yet, IoT deployments are inherently asymmetric where more resourceful base stations and cloud infrastructure lie on the other side of a IoT clients’ bandwidth starved link. This precludes the possibility of data-driven applications on IoT deployments for large scale sensing such as smart agriculture, automated traffic signals and micro-climate monitoring. While some smart-home sensors can communicate large amounts of data to enable low-latency complex inference applications, the big data revolution has eluded low-power IoT sensors from realizing their true potential.
In this talk, I will show how we can overcome these fundamental limitations of IoT wireless technologies and build systems that enable such data driven applications at scale. First, I will show how we can reduce the latency for large-scale inference queries (from several hours to a few milliseconds) by designing a new approach for clients to work together for overcoming the bandwidth-bottlenecks of individual wireless links. Next, I will talk about how we can push the wireless and compute operations from these low-power IoT clients to the much more powerful base stations to improve client throughput and battery life. Finally, I will showcase how we can leverage a similar approach for improving the capabilities of small satellites (called CubeSats) operating in low-earth orbit. I will conclude my talk with a discussion about how IoT will transform new domains in the coming years and how my research will attempt to address the challenges in these areas.
Bio
Akshay is an Assistant Professor at the Electrical and Computer Engineering department of University of Washington. He recently received his Ph.D in ECE at Carnegie Mellon University where his research operated at the intersection of wireless, mobile and cyber-physical systems with special focus on empowering the low-power Internet-of-Things devices deployed on earth and space. He has published at premier cyber-physical systems and mobile systems venues like IPSN, NSDI, MobiCom, and ICC. His work has received the Best Paper Awards at IPSN 2018 and IPSN 2020, and he was awarded the Best Presentation Award at the IPSN PhD Forum 2020. He was also awarded the ACM SIGBED-SIGSOFT Frank Anger Memorial Award 2021 for his cross-disciplinary research across embedded systems and software engineering. His work on IoT security and privacy was recognized with the CyLab Presidential Fellowship 2020-21.