Carlee Joe-Wong
Assistant Professor at CMU ECE
research group website

Abstract

Many applications today require access to computing or network resources in real-time: video calls, for instance, require a minimum bandwidth to support reasonable performance. While mechanisms exist to provision resources according to these needs, some resource requirements are hard to predict, e.g., if a web server must immediately scale to support an influx of visitors to a shopping site. Even when resource requirements are relatively predictable, such as the constant bitrate required by Skype calls, current mechanisms cannot provide resource or performance guarantees. This talk will explore recently proposed mechanisms to provide such guarantees. First, we consider the newly introduced “burstable” instances for cloud resources. We develop the first theoretical model for burstable instance performance in different service classes, as a function of the resources provisioned to these classes. We show that this model can be used to optimally price users’ access to these service classes, maximizing provider revenue while guaranteeing expected user performance. We then turn to real-time provisioning in wireless networks. We show how the recently proposed paradigm of real-time network slicing can be exploited to conduct repeated auctions for flow-specific performance guarantees. Though the resulting determination of auction winners is generally an NP-hard problem, we derive modified Vickrey-Clarke-Groves mechanisms that efficiently solve the auction and provide several desirable auction properties, such as user truthfulness.

Bio

Carlee Joe-Wong is an Assistant Professor of Electrical and Computer Engineering at Carnegie Mellon University. She received her A.B. degree (magna cum laude) in Mathematics, and M.A. and Ph.D. degrees in Applied and Computational Mathematics, from Princeton University in 2011, 2013, and 2016, respectively. Dr. Joe-Wong’s research is in optimizing networked systems, particularly on applying machine learning and pricing to resource allocation in data and computing networks. From 2013 to 2014, she was the Director of Advanced Research at DataMi, a startup she co-founded from her Ph.D. research on mobile data pricing. Her research has received several awards, including the ARO Young Investigator Award in 2019, the NSF CAREER Award in 2018, the INFORMS ISS Design Science Award in 2014 and the Best Paper Award at IEEE INFOCOM 2012.

Host

Professor Mario Di Francesco
Department of Computer Science, Aalto University