Attention-based Open RAN Slice Management using Deep Reinforcement Learning

被引:1
|
作者
Lotfi, Fatemeh [1 ]
Afghah, Fatemeh [1 ]
Ashdown, Jonathan [2 ]
机构
[1] Clemson Univ, Holcombe Dept Elect & Comp Engn, Clemson, SC 29634 USA
[2] Air Force Res Lab, Rome, NY 13441 USA
基金
美国国家科学基金会;
关键词
D O I
10.1109/GLOBECOM54140.2023.10436850
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
As emerging networks such as Open Radio Access Networks (O-RAN) and 5G continue to grow, the demand for various services with different requirements is increasing. Network slicing has emerged as a potential solution to address the different service requirements. However, managing network slices while maintaining quality of services (QoS) in dynamic environments is a challenging task. Utilizing machine learning (ML) approaches for optimal control of dynamic networks can enhance network performance by preventing Service Level Agreement (SLA) violations. This is critical for dependable decision-making and satisfying the needs of emerging networks. Although RL-based control methods are effective for real-time monitoring and controlling network QoS, generalization is necessary to improve decision-making reliability. This paper introduces an innovative attention-based deep RL (ADRL) technique that leverages the O-RAN disaggregated modules and distributed agent cooperation to achieve better performance through effective information extraction and implementing generalization. The proposed method introduces a value-attention network between distributed agents to enable reliable and optimal decision-making. Simulation results demonstrate significant improvements in network performance compared to other DRL baseline methods.
引用
收藏
页码:6328 / 6333
页数:6
相关论文
共 50 条
  • [1] Learning to Drive at Unsignalized Intersections using Attention-based Deep Reinforcement Learning
    Seong, Hyunki
    Jung, Chanyoung
    Lee, Seungwook
    Shim, David Hyunchul
    [J]. 2021 IEEE INTELLIGENT TRANSPORTATION SYSTEMS CONFERENCE (ITSC), 2021, : 559 - 566
  • [2] RAN Slice Strategy Based on Deep Reinforcement Learning for Smart Grid
    Meng, Sachula
    Wang, Zhihui
    Ding, Huixia
    Wu, Sai
    Li, Xuan
    Zhao, Peng
    Zhu, Chunying
    Wang, Xue
    [J]. 2019 COMPUTING, COMMUNICATIONS AND IOT APPLICATIONS (COMCOMAP), 2019, : 6 - 11
  • [3] ARiADNE: A Reinforcement learning approach using Attention-based Deep Networks for Exploration
    Cao, Yuhong
    Hou, Tianxiang
    Wang, Yizhuo
    Yi, Xian
    Sartoretti, Guillaume
    [J]. 2023 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2023), 2023, : 10219 - 10225
  • [4] Attention-Based Deep Reinforcement Learning for Edge User Allocation
    Chang, Jiaxin
    Wang, Jian
    Li, Bing
    Zhao, Yuqi
    Li, Duantengchuan
    [J]. IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT, 2024, 21 (01): : 590 - 604
  • [5] Attention-Based Deep Reinforcement Learning for Virtual Cinematography of 360° Videos
    Wang, Jianyi
    Xu, Mai
    Jiang, Lai
    Song, Yuhang
    [J]. IEEE TRANSACTIONS ON MULTIMEDIA, 2021, 23 : 3227 - 3238
  • [6] Attention-based Deep Reinforcement Learning for Multi-view Environments
    Barati, Elaheh
    Chen, Xuewen
    Zhong, Zichun
    [J]. AAMAS '19: PROCEEDINGS OF THE 18TH INTERNATIONAL CONFERENCE ON AUTONOMOUS AGENTS AND MULTIAGENT SYSTEMS, 2019, : 1805 - 1807
  • [7] ATTENTION-BASED CURIOSITY-DRIVEN EXPLORATION IN DEEP REINFORCEMENT LEARNING
    Reizinger, Patrik
    Szemenyei, Marton
    [J]. 2020 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2020, : 3542 - 3546
  • [8] Open RAN Slicing for MVNOs With Deep Reinforcement Learning
    Filali, Abderrahime
    Mlika, Zoubeir
    Cherkaoui, Soumaya
    [J]. IEEE INTERNET OF THINGS JOURNAL, 2024, 11 (10): : 18711 - 18725
  • [9] Subgoal-Driven Navigation in Dynamic Environments Using Attention-Based Deep Reinforcement Learning
    de Heuvel, Jorge
    Shi, Weixian
    Zeng, Xiangyu
    Bennewitz, Maren
    [J]. 2023 21ST INTERNATIONAL CONFERENCE ON ADVANCED ROBOTICS, ICAR, 2023, : 79 - 85
  • [10] Attention-based model and deep reinforcement learning for distribution of event processing tasks
    Mazayev, Andriy
    Al-Tam, Faroq
    Correia, Noelia
    [J]. INTERNET OF THINGS, 2022, 19