Deep learning resource allocation in vehicular communications

Paper Title:

Model-based Deep Learning for Rate Split Multiple Access in Vehicular Communications

Published on:

2 May 2024

Primary Category:

Information Theory

Paper Authors:

Hanwen Zhang,

Mingzhe Chen,

Alireza Vahid,

Haijian Sun

Bullets

Key Details

•

Proposes deep unfolding neural network for vehicular RSMA resource allocation

•

Combines fractional programming and projected gradient descent in model

•

Achieves 97% of optimal weighted sum-rate in simulations

•

156x faster than traditional optimization algorithms

•

Maintains performance in out-of-distribution scenarios

Explore the topics in this paper

deep learning

optimization

rate splitting

resource allocation

vehicular communications

AI generated summary

Deep learning resource allocation in vehicular communications

This paper proposes a deep learning approach to optimize resource allocation in vehicular communications using rate split multiple access. A fractional programming and projected gradient descent based deep unfolding neural network is designed, achieving near optimal performance but with much lower complexity and better resilience to varying conditions.