Resource allocation strategy for ultra-dense Internet of things based on graph convolutional neural network
To address the significant issue of hidden terminal interference that severely impacted resource management in ultra-dense Internet of things (UD-IoT) environments, a deep deterministic gradient-based conflict-free resource allocation strategy using graph convolution neural network was proposed. The...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Journal on Communications
2024-10-01
|
| Series: | Tongxin xuebao |
| Subjects: | |
| Online Access: | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2024178/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | To address the significant issue of hidden terminal interference that severely impacted resource management in ultra-dense Internet of things (UD-IoT) environments, a deep deterministic gradient-based conflict-free resource allocation strategy using graph convolution neural network was proposed. The conflict graph model was constructed by employing matrix transformations to represent potential hidden terminal interference among devices. Then, using the concepts of maximal cliques and hypergraph theory, the conflict graph model was transformed into a conflict hypergraph model. This transformation allowed the conflict-free resource allocation problem to be formulated as a hypergraph vertex coloring problem. A deep deterministic gradient-based conflict-free resource allocation algorithm, leveraging graph convolutional neural network reinforcement learning, was developed to achieve conflict-free resource allocation and maximize resource reuse. Simulation results demonstrated that the proposed algorithm achieved higher resource reuse rates and throughput compared to existing methods, providing superior performance in ultra-dense IoT. |
|---|---|
| ISSN: | 1000-436X |