Multi-Agent Driven Resource Allocation and Interference Management for Deep Edge Networks
- 13 December 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 71 (2) , 2018-2030
Abstract
Sixth generation mobile networks (6G) may experience a huge evolution on vertical industry scenarios, where deep edge networks ( $\mathbf{D}\mathrm{E}\mathrm{N}\mathrm{s}$ ) become an important network structure for the intelligent resource management of computing, caching and communications (3 C). In this paper, we propose two pervasive scenarios including single edge scene and multiple edge scenes for deep integration of wireless communications and computation depending on real-time adaptive collaboration. Specifically, in the single edge scenario, a novel deep reinforcement learning (DRL)-based framework is invoked for collaboratively optimizing the task scheduling, transmission power and CPU cycle frequency under metabolic channel conditions. Meanwhile, in order to alleviate interference in multiple edge scenarios, we propose a multi-agent aided deep deterministic policy gradient (MADDPG) algorithm to minimize total energy consumption and latency. Numerical experiments demonstrate these methods have substantial performance improvement in terms of saving system’s total overhead (i.e., energy consumption and delay) upon considering the task scheduling, transmission power, channel mutual interference and CPU cycle frequency against other conventional benchmarks.Keywords
Funding Information
- Artificial Intelligence and Smart City Joint Laboratory (B2020001)
- Future Intelligent Networking and Intelligent Transportation Joint Laboratory (B2019007)
- Intelligent Network Joint Laboratory (B2021006)
- Young Elite Scientist Sponsorship Program by CAST (2020QNRC001)
This publication has 41 references indexed in Scilit:
- Joint Computation Offloading and Interference Management in Wireless Cellular Networks with Mobile Edge ComputingIEEE Transactions on Vehicular Technology, 2017
- Energy-Efficient Resource Allocation for Mobile-Edge Computation OffloadingIEEE Transactions on Wireless Communications, 2016
- Dynamic Computation Offloading for Mobile-Edge Computing With Energy Harvesting DevicesIEEE Journal on Selected Areas in Communications, 2016
- Delay-optimal computation task scheduling for mobile-edge computing systems2016
- Mobile-Edge Computing: Partial Computation Offloading Using Dynamic Voltage ScalingIEEE Transactions on Communications, 2016
- DaVe: Offloading Delay-Tolerant Data Traffic to Connected Vehicle NetworksIEEE Transactions on Vehicular Technology, 2016
- Toward Vehicle-Assisted Cloud Computing for SmartphonesIEEE Transactions on Vehicular Technology, 2015
- Joint Cloud and Wireless Networks Operations in Mobile Cloud Computing Environments With Telecom Operator CloudIEEE Transactions on Wireless Communications, 2015
- Computation Offloading for Service Workflow in Mobile Cloud ComputingIEEE Transactions on Parallel and Distributed Systems, 2014
- Energy-Efficient Fault-Tolerant Data Storage and Processing in Mobile CloudIEEE Transactions on Cloud Computing, 2014