Home > Archive>Volume 38, Issue 2, 2024 >160-170
PDF HTML XML Export Cite reminder
Power allocation in flexible duplex networks: GNN computation accelerated by edge pruning
Author:
Affiliation:

1.College of Electronics and Information Engineering, Nanjing University of Information Science and Technology, Nanjing 210044, China;2.Jiangsu Integrated Circuit Reliability Technology and Testing System Engineering Research Center, Wuxi University, Wuxi 214105, China; 3.Graduate School of Chinese Aeronautical Establishment, Yangzhou 225006, China

Clc Number:

TN915.81

  • Article
    • | |
  • Metrics
    • |
  • Reference
    • |
  • Related
    • |
  • Cited by
    • | |
  • Comments
    Abstract:

    Due to the presence of interference between users, power allocation problems in wireless communication networks are often non convex and require a huge amount of computation. The current graph neural network (GNN) has become an effective computational method used to solve this problem. In order to maximize network transmission speed while reducing computational complexity, a flexible duplex network graph representation method that incorporates device and communication connection attributes into GNN is proposed, and a corresponding flexible duplex graph neural network (FD-GNN) model is constructed. For the first time, the distance between node pairs, channel gain, and neighbors are introduced as dynamic thresholds into FD-GNN to adapt to dynamic environments. Excluding channel state information of neighbors in GNN, pruning edges in FD-GNN reduces computation time and network complexity. Simulation results show that the proposed threshold setting method based on channel gain neighbors has the best performance and reaches 97% of the weighted minimum mean square error (WMMSE), reducing the training time required by 24% compared to Full GANN. The proposed threshold based effectively reduces the time complexity of GNN operations and improves the effectiveness of the algorithm.

    Reference
    Related
    Cited by
Get Citation

Copy
Share
Article Metrics
  • Abstract:
  • PDF:
  • HTML:
  • Cited by:
History
  • Online: April 29,2024
Article QR Code
You are the first     visitors
Superintended by：China Association for Science and Technology
Sponsored by：Chinese Institute of Electronics
Address：No. 79, Beiheyan Street, Dongcheng District, Beijing, China
Tel：010-64004400
Journal of Electronic Measurement and Instrumentation ® 2025 All Rights Reserved