Soudeh Ghorbani

About Me

Since 2017, I’ve been a postdoc working with Aditya Akella at UW-Madison. I got my Ph.D. in Computer Science from University of Illinois at Urbana-Champaign working with Brighten Godfrey, was an exchange Ph.D. student at Princeton University working with Jennifer Rexford, got my M.Sc. from University of Toronto working with Yashar Ganjali, and my B.Sc. from Sharif University of Technology.

During my grad studies, I interned at Microsoft Research and Max Planck Institute, and won the VMware Graduate Fellowship (one of the three winners worldwide, 2015), the HotSDN best paper award, the Feng Chen Memorial Award, the Gottlieb Fellowship, and the Wolfond Fellowship. You can find my list of publications here.

I serve as a board member and the co-chair of the Mentoring Program of N2Women, a community of over 1,200 Networking researchers with the mission to create a culture that embraces diversity and fosters inclusiveness.

I am looking for a tenure-track Assistant Professor position.

I design and build reliable networked systems with provable guaratees, drawing techniques from formal methods, distributed systems, and control theory. Recent projects:

Micro Load Balancing in Datacenters


Paper | Slides


Paper | Slides

Microbursts, the main culprit of packet loss in datacenters, last for a few microseconds -- a time period orders of magnitude shorter than the control loop of fastest existing load balancers.

We design DRILL, a datacenter fabric that performs micro load balancing to distribute load despite microbursts via employing per-packet decisions based on queue occupancies and randomized algorithms.

Our design addresses the resulting key challenges of packet reordering and topological asymmetry. DRILL outperforms the state of the art load balancers especially for bursty workloads, e.g., it results in 2.1x improvement in the average flow completion time in an incast scenario compared to CONGA.

Seamless Scale-out of Network Elements


Paper | Slides

Naively scaling networks can cause incorrect behaviors, e.g., we show that scaled-out firewalls erroneously and permanently block hosts. We design and build COCONUT, a system that leverages vector clocks for efficient seamless network scale-out of networks.

HotSDN’14, CCR'14
Best Paper Award

Paper | Slides

We show that the state distribution techniques in existing network virtualization systems can cause incorrect application-level behavior. We also show that that the incorrect behaviors occur while the pervasive correctness invariants are preserved throughout, and that the techniques designed to preserve such invariants can themselves occasionally break the otherwise correct behavior.

Liveness Verification of Stateful Networks



Modern networks rely on a variety of stateful network functions to implement rich policies. Correct operation of such networks relies on ensuring that they support a diverse set of properties including liveness properties. Unfortunately, despite exciting recent work on network verification, no existing approach is practical for, or applicable to, validating liveness.

We develop novel encodings of the behavior of network programs under dynamic events such as network state changes using Boolean formulas that can capture rich semantics such as packet counters. We prove that our encodings are equivalent to the program and show experimentally that they can succinctly express a variety of network functions and are orders of magnitude more scalable to verify than naive encodings.

Complete list of papers

Our proposal with Aditya and Kausik was a winner in the Barefoot​ ​Networks​ ​University​ ​Research​ ​Program, 2017.

NSF Support Grant for Junior Researchers, 2016.

VMware Graduate Fellowship, 2015-2016. One of the Three Winners Worldwide!

Feng Chen Memorial Award, University of Illinois at Urbana-Champaign, 2015.

Best Paper Award, HotSDN 2014.

Qualcomm Innovation Fellowship Finalist, with Cole Schlesinger for our proposal on Malleable Virtual Networks, 2013.

Board Member and Menotring Co-Chair: N2W 2018-2020

Program Committee: APNet 2018

ACM/IEEE Transactions on Networking 2017
IEEE Transactions on Network and Service Management 2017
IEEE Access 2017
IEEE Transactions on Services Computing 2017