Deep Reinforcement Learning Based Resource Allocation for V2V Communications

By Hao Ye, Geoffrey Y. Li, Biing-Hwang Fred Juang. IEEE Transactions on Vehicular Technology, 2018

722 citations recorded by the source corpus.

In this paper, we develop a novel decentralized resource allocation mechanism for vehicle-to-vehicle (V2V) communications based on deep reinforcement learning, which can be applied to both unicast and broadcast scenarios. According to the decentralized resource allocation mechanism, an autonomous “agent,” a V2V link or a vehicle, makes its decisions to find the optimal sub-band and power level for transmission without requiring or having to wait for global information. Since the proposed method is decentralized, it incurs only limited transmission overhead. From the simulation results, each agent can effectively learn to satisfy the stringent latency constraints on V2V links while minimizing the interference to vehicle-to-infrastructure communications.

Subfields: Computer Networks and Communications, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/2b429774b5d867ef60f8b464cfa0b4886ffd77f0

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

In Electrical and Electronic Engineering

Citations in the corpus

Multi-Agent Reinforcement Learning Based Resource Management in MEC- and UAV-Assisted Vehicular Networks (2021, background): “BENEFITING from advances in the automobile industry and wireless communication technologies, the vehicular network has been emerged as a key enabler of intelligent transportation services [1]–[4].”
Single and Multi-Agent Deep Reinforcement Learning for AI-Enabled Wireless Networks: A Tutorial (2020, methodology): “The work in [118] proposes a fully decentralized algorithm based on DQN to maximize the Vehicle-to-Infrastructure capacity under V2V latency constraints.”
Edge Learning for B5G Networks With Distributed Signal Processing: Semantic Communication, Edge Computing, and Wireless Sensing (2022, positive): “Combining RL with DNN, deep reinforcement learning (DRL), e.g., deep Q-learning (DQL) [87], has emerged as a powerful tool to solve resource allocation problems in many wireless applications, e.g., [88], [89], [90], [91].”
Spectrum Sharing in Vehicular Networks Based on Multi-Agent Reinforcement Learning (2019, methodology): “1) The single-agent RL based algorithm in [12], termed SARL, where at each moment only one V2V agent updates its action, i.”
Future Intelligent and Secure Vehicular Network Toward 6G: Machine-Learning Approaches (2020, methodology): “Also considering the vehicular network, for optimal channel and power selection without requiring/waiting for global information, a DRL-based algorithm for V2V was proposed in [87].”
6G for Vehicle-to-Everything (V2X) Communications: Enabling Technologies, Challenges, and Opportunities (2020, background): “It is worth mentioning that a single-agent learning framework is considered in prior art (e.g., see [154]), where each agent in the same network may take its action without collaborating with any of the others [156].”