College of Information and Computer Sciences
140 Governors Dr.
RM A313 (LGRC)
Amherst, MA 01003
Hello and welcome! I am Abel Souza, a Postdoctoral Researcher in the College of Information & Computer Sciences at the University of Massachusetts Amherst. I work with Prof. Prashant Shenoy in the Laboratory for Advanced System Software.
Prior to joining UMass, I was a PhD student in the Department of Computing Science at Umeå University (Sweden). I worked in the Autonomous Distributed Systems Lab. under the guidance of Dr. Johan Tordsson and Prof. Erik Elmroth. The topic of my research was Data Analytics for Resource Management in High Performance (HPC) and Cloud datacenters.
Today, my research predominantly focuses on distributed and data-intensive systems that support AI, Machine Learning, and web workloads. Recently, my work has extended to address sustainable and efficient approaches for designing, architecting, and managing both cloud and edge platforms with the aim of achieving zero-carbon emissions. A key theme in my research explores the efficient application of predictive analytics methods to process and model vast amounts of data, tailoring resource management holistically to applications. This involves determining the optimal quantity and type of resources to allocate, as well as the most effective deployment times and locations.
I am in the 2023-2024 job market looking for faculty positions. Find my materials here.
|Feb 12, 2024
|Paper SLO-Power accepted!
|Feb 7, 2024
|Paper On the Limitations of Carbon-Aware Temporal and Spatial Workload Shifting in the Cloud accepted!
|Nov 23, 2023
|A new website is launched!
|Oct 31, 2023
|CASPER got the best runner-up paper!
|Oct 1, 2023
|Human-Centered Carbon Management paper accepted!
EuroSysOn the Limitations of Carbon-Aware Temporal and Spatial Workload Shifting in the CloudIn Proceedings of the 19th European Conference on Computer Systems (EuroSys), 2024
SoCCEnabling sustainable clouds: The case for virtualizing the energy systemIn Proceedings of the ACM Symposium on Cloud Computing, 2021
ASPLOSEcovisor: A virtual energy system for carbon-efficient applicationsIn Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2, 2023