DRL-Based Low-Latency Content Delivery for 6G Massive Vehicular IoT
- 9 March 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 9 (16), 14551-14562
- https://doi.org/10.1109/jiot.2021.3064874
Abstract
Vehicle-to-everything communication is an indispensable component of 6G networks that could help to facilitate future transportation systems. However, massive vehicles and unstable vehicle-to-vehicle (V2V) links may become bottlenecks for the low-latency delivery of contents, such as safety-critical emergency messages and multimedia. Instead of resolving the problem in a centralized way, we propose a massive vehicular Internet of Things (IoT) system and investigate the approach that would enable each vehicle to decide the transmission mode from three modes, i.e., vehicle-to-network (V2N), vehicle-to-infrastructure (V2I) and V2V sidelinks, and wireless resources. Specifically, a multi-agent deep reinforcement learning framework is formulated by combining the multi-agent reinforcement learning approach, WoLF-PHC, with the techniques from deep Q-learning (DQN) to gain the formulated framework the capability of capturing the effects of interaction between learning agents and states of complex environment. The framework is set to maximize the throughput of vehicles while maintaining the latency and reliability constraints of the vehicle communication links. However, it could be easily extended to other objectives. The simulation results demonstrate that the proposed approach outperforms the compared ones in total traffic capacity and satisfaction rate of the vehicles in communication.Funding Information
- National Key Research and Development Program of China (2018YFE0205502)
This publication has 40 references indexed in Scilit:
- Graph-Based Resource Sharing in Vehicular CommunicationIEEE Transactions on Wireless Communications, 2018
- A Distributed Position-Based Protocol for Emergency Messages Broadcasting in Vehicular Ad Hoc NetworksIEEE Internet of Things Journal, 2018
- Cluster-Based Content Distribution Integrating LTE and IEEE 802.11p with Fuzzy Logic and Q-LearningIEEE Computational Intelligence Magazine, 2018
- Game Theoretic Mechanisms for Resource Management in Massive Wireless IoT SystemsIEEE Communications Magazine, 2017
- Interworking of DSRC and Cellular Network Technologies for V2X Communications: A SurveyIEEE Transactions on Vehicular Technology, 2016
- Cluster-Based Radio Resource Management for D2D-Supported Safety-Critical V2X CommunicationsIEEE Transactions on Wireless Communications, 2015
- Human-level control through deep reinforcement learningNature, 2015
- Joint Mode Selection and Resource Allocation for Device-to-Device CommunicationsIEEE Transactions on Communications, 2014
- VWCA: An efficient clustering algorithm in vehicular ad hoc networksJournal of Network and Computer Applications, 2011
- A tutorial on spectral clusteringStatistics and Computing, 2007