WolfPack: Application-Network Co-Design for Edge Resource Provisioning

This project is supported by NSF CAREER Award #2045539 (2021/07/01-2026/06/30):

This project is recruiting undergraduate students interested in edge computing, microservices, and machine learning applications.

Selected students will be developing microservice-based applications and measurement frameworks for testing the performance of microservices under different computing and network configurations, under guidance by current graduate students. Students can receive CSC 498/499 credits, and/or NSF REU funding from one of the PI’s NSF projects.

An ideal candidate may have (or is en route learning) skills for network programming (socket, TCP/IP, etc.). Experiences with Linux containers and Kubenetes are a plus. Expected level of efforts is 10 to 15 hours a week for the project. To receive NSF REU funding, a student is required to be a US citizen or a permanent resident.

Project Description
Modern distributed computing applications have extremely complex structures. Examples include microservice-based applications such as Twitter, Netflix, Uber, and IoT, which can consist of thousands of microservices, loosely coupled through API calls. Such structural complexity poses significant challenges when these applications are looking to leverage edge computing, our next-gen computing paradigm, which provides low-latency and high-throughput computing proximal to end users. This project addresses the performance issue of large-scale distributed applications by employing an application-network co-design approach: simultaneously configuring computing and networking resources for end-to-end performance guarantee. Two developments will result from this project: the WolfPack, a theoretical framework for app-network co-design optimization; and the WolfBench, a systematic benchmark for app-network co-designed applications in realistic edge computing environments.
Personnel

Dr. Ruozhou Yu
PI@NCSU		 Zhouyu Li (PhD student @ NCSU)
Fangtong Zhou (PhD student @ NCSU)
Xiaojian Wang (PhD student @ NCSU)
Huayue Gu (PhD student @ NCSU)
Publications and Pre-prints
  • VeriEdge: Verifying and Enforcing Service Level Agreements for Pervasive Edge Computing
    Xiaojian Wang*, Ruozhou Yu, Dejun Yang Huayue Gu*, Zhouyu Li*,
    Accepted by IEEE International Conference on Computer Communications (INFOCOM), 2024.
  • Thor: A Virtual Payment Channel Network Construction Protocol over Cryptocurrencies
    Qiushi Wei, Dejun Yang, Ruozhou Yu, Guoliang Xue
    Accepted by IEEE International Conference on Computer Communications (INFOCOM), 2024.
  • Fence: Fee-based Online Balance-aware Routing in Payment Channel Networks
    Xiaojian Wang*, Ruozhou Yu, Dejun Yang, Guoliang Xue, Huayue Gu*, Zhouyu Li*, Fangtong Zhou*
    Accepted by IEEE/ACM Transactions on Networking (ToN), 2023.
  • FENDI: High-Fidelity Entanglement Distribution in the Quantum Internet [arXiv]
    Huayue Gu*, Zhouyu Li*, Ruozhou Yu, Xiaojian Wang*, Fangtong Zhou*, Jianqing Liu
    under review, 2023. (Gu and Li contributed equally to this paper)
  • INSPIRE: Instance-level Privacy-preserving Transformation for Vehicular Camera Videos
    Zhouyu Li*, Ruozhou Yu, Anupam Das, Shaohu Zhang, Huayue Gu*, Xiaojian Wang*, Fangtong Zhou*, Aafaq Sabir, Dilawer Ahmed, Ahsan Zafar
    Accepted by IEEE International Conference on Computer Communications and Networks (ICCCN), 2023.
  • EA-Market: Empowering Real-Time Big Data Applications with Short-Term Edge SLA Leases
    Ruozhou Yu, Huayue Gu*, Xiaojian Wang*, Fangtong Zhou*, Guoliang Xue, Dejun Yang
    Accepted by IEEE International Conference on Computer Communications and Networks (ICCCN), 2023.
  • Principles and Practices for Application-Network Co-Design in Edge Computing
    Ruozhou Yu, Guoliang Xue
    Accepted by IEEE Network Magazine, 2022.
  • Data-Driven Edge Resource Provisioning for Inter-Dependent Microservices with Dynamic Load
    Ruozhou Yu, Szu-Yu Lo*, Fangtong Zhou*, Guoliang Xue
    In IEEE Global Communications Conference (GLOBECOM), 2021.
  • Edge-Assisted Collaborative Perception in Autonomous Driving: A Reflection on Communication Design
    Ruozhou Yu, Dejun Yang, Hao Zhang
    In ACM/IEEE Symposium on Edge Computing (SEC) Workshops, 2021.
Datasets and Artifacts
  • C-V2X NS-3 simulator with collaborative perception [GitHub]
  • Other code and datasets will be available once cleaned and documented.