A GAT-LSTM-DQN routing framework for LEO satellites outperforms baselines on throughput, delay, and queue length in simulations by treating routing as a POMDP.
Carbon emission quantification of machine learning: A review
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.NI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Spatial-Temporal Learning-Based Distributed Routing for Dynamic LEO Satellite Networks
A GAT-LSTM-DQN routing framework for LEO satellites outperforms baselines on throughput, delay, and queue length in simulations by treating routing as a POMDP.