mca 23(4): e1

Research Article

Intelligent Reflecting Surface Aided Cloud Access Networks with Federated Learning

Download204 downloads
  • @ARTICLE{10.4108/eetmca.v7i4.2903,
        author={Dahua Fan and Jianghong Ou and Bowen Lu and Shiwei Lai and Yajuan Tang and Tao Cui and Chengyuan Fan},
        title={Intelligent Reflecting Surface Aided Cloud Access Networks with Federated Learning},
        journal={EAI Endorsed Transactions on Mobile Communications and Applications},
        volume={7},
        number={4},
        publisher={EAI},
        journal_a={MCA},
        year={2023},
        month={1},
        keywords={Intelligent reflecting surface, could access network, federated learning},
        doi={10.4108/eetmca.v7i4.2903}
    }
    
  • Dahua Fan
    Jianghong Ou
    Bowen Lu
    Shiwei Lai
    Yajuan Tang
    Tao Cui
    Chengyuan Fan
    Year: 2023
    Intelligent Reflecting Surface Aided Cloud Access Networks with Federated Learning
    MCA
    EAI
    DOI: 10.4108/eetmca.v7i4.2903
Dahua Fan1,*, Jianghong Ou1, Bowen Lu2, Shiwei Lai3, Yajuan Tang3, Tao Cui3, Chengyuan Fan4
  • 1: AI Sensing Technology, Foshan, China
  • 2: Shantou University
  • 3: Guangzhou University
  • 4: Software Engineering Institute of Guangzhou, Guangzhou, China
*Contact email: dahuafan2022@126.com

Abstract

Compared with traditional cellular network architecture, cloud access network has some significant advantages in spectrum utilization, energy consumption and network construction cost. However, a high-quality forward link is required between the baseband processing unit pool and remote radio head (RRH) in the cloud access network, which results in limited RRH deployment and affects user access link transmission and coverage. To solve this issue, this paper introduces the intelligent reflector technology into the cloud access network as a solution with low energy consumption, low cost and easy deployment to deal with the existing bottlenecks. Firstly, an efficient channel information acquisition strategy based on federated learning is designed for the smart reflector to enhance the user access link, so as to achieve a compromise between the channel estimation accuracy and cost. On this basis, a robust beamforming design and optimization method of the compression mechanism of the forward link are proposed for the smart reflector to enhance the user access link and the wireless forward link, so as to improve the system transmission performance. Finally, we explore the joint resource allocation method of intelligent reflector assisted cloud access network, and improve the system energy efficiency through the collaborative configuration of intelligent reflector and cloud access network communication resources. The research of this paper will provide an important theoretical basis for the application of intelligent reflectors in cloud access networks, especially for the federated learning.