# Learn to Allocate Resources in Vehicular Networks

## TL;DR

This paper introduces a hybrid deep learning-based resource allocation framework for vehicular networks that combines centralized decision-making with distributed feedback to optimize long-term network performance.

## Contribution

It proposes a novel hybrid architecture utilizing deep neural networks and deep Q-networks for efficient, low-overhead resource allocation in dynamic vehicular environments.

## Key findings

- Achieves near-optimal resource allocation performance.
- Identifies optimal feedback quantization levels.
- Demonstrates robustness to noise and feedback interval variations.

## Abstract

Resource allocation has a direct and profound impact on the performance of vehicle-to-everything (V2X) networks. Considering the dynamic nature of vehicular environments, it is appealing to devise a decentralized strategy to perform effective resource sharing. In this paper, we exploit deep learning to promote coordination among multiple vehicles and propose a hybrid architecture consisting of centralized decision making and distributed resource sharing to maximize the long-term sum rate of all vehicles. To reduce the network signaling overhead, each vehicle uses a deep neural network to compress its own observed information that is thereafter fed back to the centralized decision-making unit, which employs a deep Q-network to allocate resources and then sends the decision results to all vehicles. We further adopt a quantization layer for each vehicle that learns to quantize the continuous feedback. Extensive simulation results demonstrate that the proposed hybrid architecture can achieve near-optimal performance. Meanwhile, there exists an optimal number of continuous feedback and binary feedback, respectively. Besides, this architecture is robust to different feedback intervals, input noise, and feedback noise.