.png){kind=icon}
.png){kind=icon}
Return
The counterfactual baseline multi-agent reinforcement learning Time-Sensitive Network planning algorithm based on graph convolution
.png){kind=icon}
OA
AI
DOI：10.1016/j.array.2026.101032.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Traditional TSN scheduling methods suffer from gradually decreasing solving speed under complex topologies. • This paper proposes the GCN-COMA algorithm combining GCN and multi-agent reinforcement learning. • The GCN-COMA algorithm optimizes network structure using graph neural networks to improve scheduling speed. • The GCN-COMA algorithm generates better scheduling results across various network topologies. • The designed TSN planning software validates the feasibility and effectiveness of the proposed algorithm.
Keywords:
Time-Sensitive Networking
Message scheduling
Multi-agent reinforcement learning
Graph convolutional networks
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
4.5
Papers:
748
Citations:
1.2K