Education & Certifications

  • MS, Stanford University, Electrical Engineering (2020)
  • BS, Koç University, Electrical and Electronics Engineering (2016)

Service, Volunteer and Community Work

  • Panel Moderator, The Networking Channel (March 1, 2023)

    How to give an interesting talk for a SIGCOMM/NSDI or similar audience?



  • Shadow PC

    at EuroSys 2021



  • Section Leader, CS Bridge (June 24, 2019 - July 4, 2019)

    A non-profit international program that offers a two-week, intensive residential summer course for 16 and 17 year old high school students.
    The course is based on Stanford’s CS106A Programming Methodology (in Java) course.
    My duty was to help students with their coding projects during lab hours and conduct discussion sections where we review and discuss topics covered in lectures.


    Istanbul, Turkey

Current Research and Scholarly Interests

Network intelligence
There are 2 main aspects of network management:

- Collecting useful and enough amount of information from the network is essential for modern, data-centric decision processes to work well.
Frameworks such as In-band Network Telemetry could be utilized to collect precise information on every single packet in the network.

- Modern data science methodologies allow engineers to infer about the state of the network.
Naturally, the next step is to design tailored control algorithms that would utilize available resources the best.
Potential methods include, but not limited to, machine learning algorithms and control theory.

Work Experience

  • Student Researcher, Google LLC (June 14, 2021 - March 27, 2022)

    Worked with the Congestion Control Team for Google Core Infrastructure Group.
    I designed and developed an extremely low latency congestion control algorithm, published as Bolt, using recent technologies in switching.


    Sunnyvale, CA

  • Software Engineering Intern, Google LLC (June 15, 2020 - 9/27/2020)

    Worked with the Network Data Analytics Team for Google Cloud.
    My job was to develop performance models to improve visibility into the network using telemetry and machine learning.



  • Network Engineer, Vodafone (2016 - 2018)

    - Project Management for Internet Gateway Migration Project
    - Design and development of Data Center Device Status Monitoring Tool
    - Integration and management of Carrier Grade NAT Devices
    - Installation and documentation of the city based policy application via DPI (Deep Packet Inspection) infrastructure


    Istanbul, Turkey

All Publications

  • Bolt: Sub-RTT Congestion Control for Ultra-Low Latency 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23) Arslan, S., Li, Y., Kumar, G., Dukkipati, N. 2023: 17
  • SFC: Near-Source Congestion Signaling and Flow Control Le, Y., Lee, J., Blendin, J., Chen, J., Nikolaidis, G., Pan, R., Soule, R., Akella, A., Segura, P. Y., Singhvi, A., Li, Y., Meng, Q., Kim, C., Arslan, S. Arxiv. 2023 18


    State-of-the-art congestion control algorithms for data centers alone do not cope well with transient congestion and high traffic bursts. To help with these, we revisit the concept of direct \emph{backward} feedback from switches and propose Back-to-Sender (BTS) signaling to many concurrent incast senders. Combining it with our novel approach to in-network caching, we achieve near-source sub-RTT congestion signaling. Source Flow Control (SFC) combines these two simple signaling mechanisms to instantly pause traffic sources, hence avoiding the head-of-line blocking problem of conventional hop-by-hop flow control. Our prototype system and scale simulations demonstrate that near-source signaling can significantly reduce the message completion time of various workloads in the presence of incast, complementing existing congestion control algorithms. Our results show that SFC can reduce the 99th-percentile flow completion times by 1.2−6× and the peak switch buffer usage by 2−3× compared to the recent incast solutions.

  • Trust-free service measurement and payments for decentralized cellular networks HotNets '22 Anand, S., Arslan, S., Chopra, R., Katti, S., Vaddiraju, M. K., Rana, R., Sheng, P., Tyagi, H., Viswanath, P. 2022: 8

    View details for DOI 10.1145/3563766.3564093

  • Enabling the Reflex Plane with the nanoPU Ibanez, S., Mallery, A., Arslan, S., Jepsen, T., Shahbaz, M., Kim, C., McKeown, N. Arxiv. 2022 14


    Many recent papers have demonstrated fast in-network computation using programmable switches, running many orders of magnitude faster than CPUs. The main limitation of writing software for switches is the constrained programming model and limited state. In this paper we explore whether a new type of CPU, called the nanoPU, offers a useful middle ground, with a familiar C/C++ programming model, and potentially many terabits/second of packet processing on a single chip, with an RPC response time less than 1 μs. To evaluate the nanoPU, we prototype and benchmark three common network services: packet classification, network telemetry report processing, and consensus protocols on the nanoPU. Each service is evaluated using cycle-accurate simulations on FPGAs in AWS. We found that packets are classified 2× faster and INT reports are processed more than an order of magnitude quickly than state-of-the-art approaches. Our production quality Raft consensus protocol, running on the nanoPU, writes to a 3-way replicated key-value store (MICA) in 3 μs, twice as fast as the state-of-the-art, with 99\% tail latency of only 3.26 μs. To understand how these services can be combined, we study the design and performance of a {\em network reflex plane}, designed to process telemetry data, make fast control decisions, and update consistent, replicated state within a few microseconds.

  • Updating the theory of buffer sizing PERFORMANCE EVALUATION Spang, B., Arslan, S., McKeown, N. 2021; 151
  • NanoTransport: A Low-Latency, Programmable Transport Layer for NICs SOSR '21 Arslan, S., Ibanez, S., Mallery, A., Kim, C., McKeown, N. 2021: 14

    View details for DOI 10.1145/3482898.3483365

  • The nanoPU: A Nanosecond Network Stack for Datacenters Ibanez, S., Mallery, A., Arslan, S., Jepsen, T., Shahbaz, M., Kim, C., McKeown, N., USENIX ASSOC USENIX ASSOC. 2021: 239-256
  • Using Google Search Trends to Estimate Global Patterns in Learning L@S '20 Arslan, S., Tiwari, M., Piech, C. 2020: 11

    View details for DOI 10.1145/3386527.3405913

  • Switches Know the Exact Amount of Congestion Arslan, S., McKeown, N., ACM ASSOC COMPUTING MACHINERY. 2019