AutoEdge
NSF: CAREER: AutoEdge: Deep Reinforcement Learning Methods and Systems for Network Automation at Wireless Edge
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:
- Xueyu Hou
- Yang Deng
Undergrduate Students:
- Erika Hurst (2022 Provost URI Summer Research Fellow)
Industrial Collaborator:
- Dr. Nakjung Choi, Nokia Bell Labs
Project Outcomes:
Publications:
- 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 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.