Telecommunications Science ›› 2024, Vol. 40 ›› Issue (2): 11-21.doi: 10.11959/j.issn.1000-0801.2024022

• Research and Development • Previous Articles    

Environment-aware based access point deployment optimization for cell-free massive MIMO system

Jing JIANG1, Yongqiang LIU1, Fengyang YAN1, Sha TAO1, Sutthiphan WORAKRIN2   

  1. 1 Shaanxi Key Laboratory of Information Communication Network and Security, Xi’an University of Posts and Telecommunication, Xi’an 710121, China
    2 National Telecommunication Public Company, Bangkok 10700, Thailand
  • Revised:2024-02-01 Online:2024-02-01 Published:2024-02-01
  • Supported by:
    The National Natural Science Foundation of China(61871321);The National Natural Science Foundation of China(61901370);Key Program for International Science and Technology Cooperation Projects of Shaanxi Province(2023-GHZD-37);Key Industrial Chain Projects of Shaanxi Province(2023-ZDLGY-49)

Abstract:

Cell-free massive multiple-input multiple-output (MIMO) systems deploy a large number of access point (AP) across the coverage area which can provide uniform high-rate services to users.However, the quality of coverage would be affected by path loss, shadow fading scatters, and environmental occlusions around the randomly placed AP in conventional cell-free massive MIMO systems that do not consider their impact.Considering the impact of actual wireless propagation environments, an AP deployment scheme was proposed to acquire uniform and consistent coverage.Firstly, a hybrid probabilistic path loss model was utilized to characterize various wireless propagation environments.Then, the AP deployment optimization problem was solved with the objective of maximizing the average throughput.Finally, the problem was transformed into a Markov game process and solved by the multi-agent deep deterministic policy gradient (MADDPG) algorithm.The simulation results demonstrate that the proposed scheme can provide more uniform coverage in complex environments and serve users with reliable and consistent service compared to random AP deployment and existing AP deployment methods.

Key words: cell-free massive MIMO, AP deployment, hybrid probabilistic path loss model, MADDPG algorithm

CLC Number: 

No Suggested Reading articles found!