ACM SIGCOMM 2018, Budapest, Hungary
MENU

ACM SIGCOMM 2018 Afternoon Workshop on Self-Driving Networks (SelfDN 2018)

Workshop Program

  • Friday, August 24, 2018, InterContinental

  • 2:00 pm - 3:15 pm Session I: Another Kind of SDN

    Location: TBA

  • Keynote: Unsafe at Any Speed? Self-Driving Networks without Self-Crashing Networks

    Jeff Mogul (Google, USA)


    Abstract: Just as you wouldn't want to be in a car without seat belts, even if it's a self-driving car, you probably don't want your Self-Driving Network (SelfDN) to rely completely on control-theory or ML, no matter how sophisticated or formally verified. While autonomous systems promise to solve many problems that afflict networks, just as they promise to solve many problems that afflict our roadways, they are not immune from a multitude of practical problems and unexpected consequences. At Google, we have been moving towards highly-automated networking, and along the way we have learned a lot about the risks involved, and how to build robust networks in spite of the wonders of automation. I will talk about some of the problems that are likely to afflict SelfDNs as they enter the real world.

     

    Bio: TBA

     

  • 2:30 pm - 2:45 pm

    On Analyzing Self-Driven Networking: A Systems Thinking Approach

    Touseef Yaqoob, Muhammad Usama, Junaid Qadir (ITU, Pakistan), Gareth Tyson (QMUL, UK)

  • 2:45 pm - 3:00 pm

    Empowering Self-Driving Networks

    Patrick Kalmbach, Johannes Zerwas, Péter Babarczi, Andreas Blenk, Wolfgang Kellerer (TU Munich, Germany), Stefan Schmid (Univie, Austria)

  • 3:00 pm - 3:15 pm

    Refining Network Intents for Self-Driving Networks

    Arthur Selle Jacobs, Ricardo Jose Pfitscher (UFRGS, Brazil), Ronaldo Alves Ferreira (UFMS, Brazil), Lisandro Zambenedetti Granville (UFRGS, Brazil)

  • 3:15 pm - 3:45 pm Tea/Coffee Break (InterContinental Pre-Function Area)

  • 3:45 pm - 5:00 pm Session II: Use Cases

    Location: TBA

  • 3:45 pm - 4:00 pm

    Catching the Microburst Culprits with Snappy

    Xiaoqi Chen, Shir Landau Feibish (Princeton, USA), Yaron Koral (AT&T, USA), Jennifer Rexford (Princeton, USA), Ori Rottenstreich (Technion, Israel)

  • 4:00 pm - 4:15 pm

    Automatic Life Cycle Management of Network Configurations

    Hongqiang Harry Liu, Xin Wu, Wei Zhou, Weiguo Chen, Tao Wang, Hui Xu, Lei Zhou, Qing Ma, Ming Zhang (Alibaba, China)

  • 4:15 pm - 4:30 pm

    Automated Detection and Mitigation of Application-Level Asymmetric DoS Attacks

    Henri Maxime Demoulin, Issac Pedisch, Linh Thi Xuan Phan, Boon Thau Loo (UPenn, USA)

  • 4:30 pm - 5:00 pm Panel and Open Discussion

    Session Chair:

Call for Papers

For at least a decade, networking researchers, equipment vendors, and Internet service providers alike have argued for “autonomous” or “self-managing” networks, where network management and control decisions are made in real time and in an automated fashion. Yet, building such “self-driving” networks that are practically deployable has largely remained unrealized. Recent technological advances and scientific innovations, however, provide exciting new opportunities for finally realizing self-driving networks. These advances and innovations include (1) fully programmable, protocol-independent data planes and languages for programming them; and (2) the emergence of scalable platforms for processing distributed streaming data while leveraging the latest (big) data analysis and machine learning (ML) tools and software.

On the one hand, the feasibility of self-driving networks derives from the control-theoretic principle that relies on closed-loop feedback to mitigate the effects of dynamic uncertainty on a system. At the same time, the coupling of the programmable control of software-defined networking (SDN) with the inference capabilities of ML promises unprecedented opportunities for querying high-volume and high-velocity, distributed streaming data at scale; this new technical capability can provide the necessary information to the many different network management and control tasks that self-driving networks should perform automatically and autonomously.

The design and implementation of self-driving networks is one of the “grand challenges” of networking research today. Realizing this vision will require incorporating the collective expertise and input from the networking research community.

This workshop will provide a forum for networking researchers to present and share their latest research on new technologies that can help realize practical, deployable self-driving networks. This workshop seeks contributions from experts in areas such as network programming, formal methods, control theory, distributed systems, machine learning, data science, data structures and algorithms, and optimization who share in the excitement of realizing the vision of self-driving networks. Of particular interest are original research papers that are informed by control-theoretic findings (e.g., hard limits, unavoidable tradeoffs) or describe use cases of specific network management or control tasks (e.g., as applied to network security or performance) that (1) demonstrate the successful implementation of the different feedback control components so that, together, they can perform the tasks at hand in an automated way and (2) identify bottlenecks in existing technologies or methods that prevent the practical deployment of full-fledged self-driving networks.

Submissions related to all aspects of designing and building self-driving networks are welcome, but innovative work that incorporates all aspects of the control loop is preferred over piecemeal approaches that focus on individual aspects in isolation.

Topics of Interest

  • Predictive machine learning approaches to closed-loop traffic-engineering systems (e.g, traffic prioritization, routing, machine-learned TCP or hypervisor rate controllers)
  • Applications of machine learning to network attack prediction and remediation
  • New machine learning problems and questions that arise from network operations tasks that are related to performance or security
  • Network measurement techniques that adapt collection or measurement based on changing network conditions
  • Query languages that support queries for data-in-motion (i.e., streaming data) and data-at-rest (i.e., offline analysis)
  • Efficient data structures and algorithms for querying (distributed) streaming data
  • New algorithms for performing approximate queries (with accuracy guarantees) and dynamic queries
  • New architectures for fine-grained and programmable network monitoring
  • New optimizations for building smart run-time systems or scalable query engines
  • Design and implementation of closed-loop feedback controls for the combined detection and mitigation of specific cyber attacks, or the detection and resolution of performance impairments
  • Examples of design choices informed by control-theoretic findings (e.g., hard limits, unavoidable tradeoffs)
  • Closed-loop systems that use measurement and inference to drive SDN-based control
  • Provable correctness properties of concurrently running control actions and protocols
  • Closed-loop network management systems that can incorporate human feedback (e.g., from users or operators) to achieve better efficiency, accuracy, or effectiveness.

Submission Instructions

Submissions must be original, unpublished work, and not under consideration at another conference or journal. Submitted papers must be at most six (6) pages long, including all figures, tables, and appendices (but not counting references) in two-column 10pt ACM format. Papers must include authors names and affiliations for single-blind peer reviewing by the PC. Authors of accepted papers are expected to present their papers at the workshop. Please submit your paper at https://sigcomm-sdn18.hotcrp.com/.

Authors Take Note

The official publication date is the date the proceedings are made available in the ACM Digital Library. This date may be up to TWO WEEKS prior to the first day of the conference. The official publication date affects the deadline for any patent filings related to published work.

Registration

Attendance of the workshop is by open registration and subject to the same registration fees and rules as all the other SIGCOMM 2018 workshops. The registrants of the workshop may freely attend any workshop on the same day.

Camera-ready instructions

For the final paper to be published, please refer to Camera-ready instructions for workshops.

Important Dates

  • August 24, 2018

    Workshop

  • Mid-June, 2018

    List of organization details

  • Mid-June, 2018

    Program available online

  • June 10, 2018

    Camera-ready deadline

  • April 30, 2018

    Acceptance notification

  • April 01, 2018

    Paper submission deadline

  • March 25, 2018

    Abstract submission deadline

Committees

  • Workshop Chairs
  • Nick Feamster

    Princeton, USA

  • Jennifer Rexford

    Princeton, USA

  • Walter Willinger

    NIKSUN, USA

  • Program Committee Members
  • Manos Antonakakis

    Georgia Tech, USA

  • Marco Canini

    KAUST, KSA

  • Chen-Nee Chuah

    Davis, USA

  • Arpit Gupta

    Princeton, USA

  • Changhoon Kim

    Barefoot, USA

  • Priya Mahadevan

    Google, USA

  • Ratul Mahajan

    Intentionet, USA

  • Nikolai Matni

    Berkeley, USA

  • Srinivas Narayana

    MIT, USA

  • Matthew Roughan

    Adelaide, Australia

  • Michael Schapira

    HUJI, Israel

  • Vyas Sekar

    CMU, USA

  • Anirudh Sivaraman

    NYU, USA

  • Alex C. Snoeren

    UCSD, USA

  • Renata Teixeira

    Inria, France

  • Ming Zhang

    Alibaba, China

  • Ying Zhang

    Facebook, USA

Contact the SelfDN chairs