中国邮电高校学报(英文) ›› 2021, Vol. 28 ›› Issue (3): 1-10.doi: 10.19682/j.cnki.1005-8885.2021.0016

• Wireless •    下一篇

User association and resource allocation in green mobile edge networks using deep reinforcement learning

郑颖1,孙司远1,魏翼飞1,宋梅2   

  1. 1. 北京邮电大学
    2. 北京邮电大学电子工程学院
  • 收稿日期:2020-09-21 修回日期:2020-11-24 出版日期:2021-06-30 发布日期:2021-06-22
  • 通讯作者: 郑颖 E-mail:yingzhengsdu@163.com
  • 基金资助:
    可编程绿色边缘网络架构及智能资源优化研究

User association and resource allocation in green mobile edge networks using deep reinforcement learning

  • Received:2020-09-21 Revised:2020-11-24 Online:2021-06-30 Published:2021-06-22
  • Contact: Ying Zheng E-mail:yingzhengsdu@163.com

摘要:

In order to meet the emerging requirements for high computational complexity, low delay and energy consumption of the 5th generation wireless systems (5G) network, ultra-dense networks (UDNs) combined with multi-access edge computing ( MEC) can further improve network capacity and computing capability. In addition, the integration of green energy can effectively reduce the on-grid energy consumption of system and realize green computation. This paper studies the joint optimization of user association (UA) and resource allocation (RA) in MEC enabled UDNs under the green energy supply pattern, users need to perceive the green energy status of base stations (BSs) and choose the one with abundant resources to associate. To minimize the computation cost for all users, the optimization problem is formulated as a mixed integer nonlinear programming (MINLP) which is NP-hard. In order to solve the problem, a deep reinforcement learning ( DRL)-based association and optimized allocation (DAOA) scheme is designed to solve it in two stages. The simulation results show that the proposed scheme has good performance in terms of  computationcost and time out ratio, as well achieve load balancing potentially.

关键词:

multi-access edge computing (MEC), ultra-dense networks ( UDNs), deep reinforcement learning ( DRL), user association ( UA),

resource allocation (RA), green energy

Abstract:

In order to meet the emerging requirements for high computational complexity, low delay and energy consumption of the 5th generation wireless systems (5G) network, ultra-dense networks (UDNs) combined with multi-access edge computing ( MEC) can further improve network capacity and computing capability. In addition, the integration of green energy can effectively reduce the on-grid energy consumption of system and realize green computation. This paper studies the joint optimization of user association (UA) and resource allocation (RA) in MEC enabled UDNs under the green energy supply pattern, users need to perceive the green energy status of base stations (BSs) and choose the one with abundant resources to associate. To minimize the computation cost for all users, the optimization problem is formulated as a mixed integer nonlinear programming (MINLP) which is NP-hard. In order to solve the problem, a deep reinforcement learning ( DRL)-based association and optimized allocation (DAOA) scheme is designed to solve it in two stages. The simulation results show that the proposed scheme has good performance in terms of  computationcost and time out ratio, as well achieve load balancing potentially.

Key words:

multi-access edge computing (MEC), ultra-dense networks ( UDNs), deep reinforcement learning ( DRL), user association ( UA),


resource allocation (RA), green energy