Arvin Ghavidel

Ph.D. Student, NSL@USC

  • (2023 - ) Ph.D. in Electrical and Computer Engineering, University of Southern California, Los Angeles, USA.
  • (2017 - 2022) B.Sc. in Electrical Engineering, Sharif University of Technology, Tehran, Iran.

Sketch

I am a ECE Ph.D. student at the University of Southern California and a member of Networked Systems Lab, very fortunate to be advised by Prof. Ramesh Govindan. My research focus is very broadly on the design of distributed systems and their management. This could either be a focus on how to manage them or why they should be like that. With practicality in mind, I try to combine theoretical methods like convex programming or formal verification to attack these problems.

Before joining USC, I completed my B.Sc. in Electrical Engineering at the Sharif University of Technology in 2022.

Feel free to contact me via email (I rarely miss them, but please feel free to send reminders if I take more than a few days to respond).

Work Experience

Graduate Research Assistant (Jan. 2023 - present)
University of Southern California, Los Angeles, CA

Research Intern & Student Researcher (May 2026 - Aug. 2026)
Microsoft Research, Redmond, WA
Mentors: Behnaz Arzani, Pooria Namyar and Konstantina Mellou.

Publications

  1. SIGCOMM
    Near-optimal Online Traffic Engineering
    Arvin Ghavidel, Pooria Namyar, Nikolai Matni, Walter Willinger, and Ramesh Govindan
    In Proceedings of the ACM SIGCOMM 2026 Conference 2026
  2. SIGCOMM
    ZENITH: Towards A Formally Verified Highly-Available Control Plane
    Pooria Namyar, Arvin Ghavidel, Mingyang Zhang, Harsha V. Madhyastha, Srivatsan Ravi, Chao Wang, and Ramesh Govindan
    In Proceedings of the ACM SIGCOMM 2025 Conference 2025
  3. NSDI
    Enhancing Network Failure Mitigation with Performance-Aware Ranking
    Pooria Namyar, Arvin Ghavidel, Daniel Crankshaw, Daniel S. Berger, Kevin Hsieh, Srikanth Kandula, Ramesh Govindan, and Behnaz Arzani
    In 22nd USENIX Symposium on Networked Systems Design and Implementation (NSDI 25) Apr 2025

    Cloud providers install mitigations to reduce the impact of network failures within their datacenters. Existing network mitigation systems rely on simple local criteria or global proxy metrics to determine the best action. In this paper, we show that we can support a broader range of actions and select more effective mitigations by directly optimizing end-to-end flow-level metrics and analyzing actions holistically. To achieve this, we develop novel techniques to quickly estimate the impact of different mitigations and rank them with high fidelity. Our results on incidents from a large cloud provider show orders of magnitude improvements in flow completion time and throughput. We also show our approach scales to large datacenters.