Research

My research at VU Amsterdam focuses on:

  • Edge inference serving
  • In-network computing
  • Edge operating systems
  • Intermittent computing for cyber-physical systems

Some highlighted projects are listed below:

DNNCare is an edge inference serving runtime framework which aims to enable automatic, adaptive mobile/edge resource provisioning for deep learning based mobile applications (e.g., augmented reality, video analytics). Our goal is to achieve resource efficiency while meeting performance goals such as latency service-level agreements (SLAs).

INC is a new computing paradigm that leverages programmable network devices (e.g., P4 switches, SmartNICs) to accelerate application-specific computations. We are exploring how to support modern workloads like machine learning with INC and also provide fundamental abstractions for INC.

EdgeOS aims to provide operating systems support (including programming abstractions and resource scheduling frameworks) for distributed, dynamic, heterogeneous edge infrastructure. In addition, we have studied the edge resource scheduling problem from a theoretical perspective, with new algorithms that make informed decisions on resource allocation and service placement in edge computing with performance guarantees.

Griffin is an edge-native distributed storage service tailored for (collaborative) edge applications to share state/data. Griffin features designs that address challenges like distribution, heterogeneity, and mobility, which are specific to the edge environment. Our new designs in Griffin include expressive abstractions and consistency semantics and network-global monitoring and optimization for heterogeneity and mobility support.

Current Projects

Efficient Distributed Runtime Support with Quality-based Application Adaptation
Principal Investigator
Funded by the German Research Foundation (DFG) within SFB MAKI
Duration: 2021-2024

SmartEdge: Concepts and Methods for Edge Computing
Principal Investigator
Funded by the German Research Foundation (DFG)
Duration: 2018-2021

Past Projects

Microservice Autoscaling and Caching for Edge Computing
Principal Investigator
Funded by the German Research Foundation (DFG) within SFB MAKI
Duration: 2018-2020

Edge Computing for the Internet of Things
Principal Investigator
Funded by TU Darmstadt (Athene Young Investigator Award)
Duration: 2018


@ 2021 Lin Wang. All rights reserved.