Big Data End-to-End: from System Management to Emerging Edge Devices

Dr. Bingzhe Li
Postdoctoral Associate, Department of Computer Science and Engineering
University of Minnesota, Twin Cities
ECSE Topical Seminar
JEC 3117
Mon, March 02, 2020 at 11:00 AM

With the rapid growth of data generated from the Internet of Things (IoT) devices, edge devices and sensors, etc., a vast amount of research challenges have been raised in this area. For example, how to store this huge amount of data? How to manage them? How to analyze them for the benefits of our daily lives? To meet these challenges, an entirely new set of approaches for low-cost processing and efficient storing/managing data are called for.

In this talk, I will cover two research topics. One will focus on how to efficiently manage big data in a cloud environment or datacenter storage systems with respect to performance improvement. I will introduce a Machine Learning (ML) based scheme to improve the performance of tier storage systems. The other will target on developing cost-efficient computing paradigms for edge computing or IoT devices. I will present stochastic computing based neural network implementations to achieve low-cost hardware designs.

Dr. Bingzhe Li currently is a postdoctoral associate in the Department of Computer Science and Engineering at the University of Minnesota, Twin Cities, advised by Prof. David Du. He received his Ph.D. degree in Electrical Engineering from the University of Minnesota, Twin Cities in 2018, under the supervision of Prof. David Lilja. His research focuses on two major directions. One lies in intelligent computer systems, including memory/storage systems, systems architecture, and storage system security. The other focuses on cost-efficient computing architecture for edge computing and IoT devices.