AutoEdge

Tao Han
Last updated on May 7, 2025

NSF: CAREER: AutoEdge: Deep Reinforcement Learning Methods and Systems for Network Automation at Wireless Edge

Overview of Network Slicing System
Overview of Network Slicing System

Abstract

This CAREER project aims to develop deep reinforcement learning (DRL) methods and systems that automate end-to-end resource orchestration in wireless edge computing networks. Toward this end, two fundamental research problems are investigated: 1) how to design domain-specific DRL that can effectively solve end-to-end orchestration problems in large-scale wireless edge computing networks and 2) how to efficiently deploy DRL-based orchestration solutions in large-scale networking systems.

Principal Investigator:

  • Tao Han, Ph.D.

Grduate Students:

  • Mingrui Yin
  • Wenrui Zhang
  • Xueyu Hou (Graudated in May 2024, joined the ECE department of the University of Maine as a tenure-track assistant professor)
  • Yang Deng (Graduated in Dec. 2023, joined Nokia Bell Labs as a research scientist)

Undergrduate Students:

  • Erika Hurst (2022 Provost URI Summer Research Fellow)

Industrial Collaborator:

  • Dr. Nakjung Choi, Nokia Bell Labs

Project Outcomes:

  • Publications:

    • Mingrui Yin, Yang Deng, Ahan Kak, Nakjung Choi and Tao Han, “PSASlicing: Perpetual SLA-Aware Reinforcement Learning for O-RAN Slice Management,” GLOBECOM 2024 - 2024 IEEE Global Communications Conference, Cape Town, South Africa, 2024, pp. 4534-4539, doi: 10.1109/GLOBECOM52923.2024.10901152.
    • N. Heydarishahreza, T. Han and N. Ansari, “Spectrum Sharing and Interference Management for 6G LEO Satellite-Terrestrial Network Integration,” in IEEE Communications Surveys & Tutorials, doi: 10.1109/COMST.2024.3507019.
    • Changshi Zhou, Weiqi Liu, Tao Han and Nirwan Ansari, “Deploying On-Device AIGC Inference Services in 6G via Optimal MEC-Device Offloading,” in IEEE Networking Letters, vol. 6, no. 4, pp. 232-236, Dec. 2024, doi: 10.1109/LNET.2024.3490954.
    • Xueyu Hou, Yongjie Guan, Tao Han, Cong Wang, “Towards real-time embodied AI agent: a bionic visual encoding framework for mobile robotics,” International Journal of Intelligent Robotics and Applications, Appl 8, 1038–1056 (2024). https://doi.org/10.1007/s41315-024-00363-w
    • Yuru Zhang, Yongjie Xue, Qiang Liu, Nakjung Choi, Tao Han, “RoNet: Toward Robust Neural Assisted Mobile Network Configuration”, IEEE International Conference on Communications (ICC), 2023.
    • Xueyu Hou, Yongjie Guan, Tao Han, “Dystri: A Dynamic Inference based Distributed DNN Service Framework on Edge”, International Conference on Parallel Processing (ICPP 23), 2023.
    • Yongjie Guan, Xueyu Hou, Nan Wu, Bo Han, Tao Han, “MetaStream: Live Volumetric Content Capture, Creation, Delivery, and Rendering in Real Time”, The 29th Annual International Conference On Mobile Computing And Networking (MobiCom 23), 2023.
    • Qiang Liu, Nakjung Choi, Tao Han, “Atlas: Automate Online Service Configuration in Network Slicing”, in the 18th International Conference on emerging Networking EXperiments and Technologies (ACM CoNEXT), 2022.
    • Qiang Liu, Nakjung Choi, Tao Han, “Deep Reinforcement Learning for End-to-End Network Slicing: Challenges and Solutions”, IEEE Network, 2022.
    • Fatima Salahdine, Qiang Liu, Tao Han, “Towards Secure and Intelligent Network Slicing for 5G Networks”, IEEE Open Journal of the Computer Society, 2022.
    • Xueyu Hou, Yongjie Guan, Tao Han, Ning Zhang, “DistrEdge: Speeding up Convolutional Neural Network Inference on Distributed Edge Devices”, in IEEE International Parallel and Distributed Processing Symposium (IPDPS), 2022.
    • Yongjie Guan, Xueyu Hou, Nan Wu, Bo Han, Tao Han, “DeepMix: Mobility-aware, Lightweight, and Hybrid 3D Object Detection for Headsets”, in the 20th Annual International Conference on Mobile Systems, Applications and Services (ACM MobiSys 22), 2022.
    • Xueyu Hou, Yongjie Guan, Tao Han, “NeuLens: Spatial-based Dynamic Acceleration of Convolutional Neural Networks on Edge”, in the 28th Annual International Conference On Mobile Computing And Networking (ACM MobiCom), 2022.
    • Qiang Liu, Nakjung Choi, Tao Han, “OnSlicing: Online end-to-end network slicing with reinforcement learning”, in the 17th International Conference on emerging Networking EXperiments and Technologies (ACM CoNEXT), 2021.
    • Qiang Liu, Nakjung Choi, Tao Han, “Constraint-Aware Deep Reinforcement Learning for End-to-End Resource Orchestration in Mobile Networks”. in IEEE International Conference on Network Protocols (ICNP), 2021.
    • Qiang Liu, Tao Han, Ephraim Moges, “EdgeSlice: Slicing Wireless Edge Computing Network with Decentralized Deep Reinforcement Learning”, in IEEE International Conference on Distributed Computing Systems (ICDCS), 2020.

  • Opensource Software:

Project Outreach

  • The PI has delivered a research talk on machien leanring and edge computing in 6G networks in IEEE 6G Summit at Singapore.
  • The PI has delivered a research talk on machine learning for network slicing at the computer science department of the Fairleigh Dickinson University.
  • The PI has delivered a research talk on machine learning for network slicing at the electrical and computer engineering department of the Stevens Institute of Technology.
  • The PI has presented the research outcome to high school students at High-Tech High Shool of New Jersey.
  • The PI has created a new undergraduate course on “Introduction to Applied Machine Learning.” which integrates some research outcomes of the project into course materials.
  • The PI has delivered a research talk on machine learning for network slicing at the computer science department of the New Jersey Institute of Technology.
  • The PI has delivered a research talk on machine learning for network slicing at the Annual IEEE North Jersey Advanced Communications Symposium.
Tao Han
Tao Han
Associate Professor