Abstract | ||
---|---|---|
The Internet of Vehicles is a product of the mobile Internet background and an innovative driving force for the industrial upgrading of the automotive industry. The rapid and reliable completion of the vehicle to roadside unit (V2R) communication is an important research direction. In order to improve the communication efficiency between the vehicles and the roadside units (RSUs), we propose a deep reinforcement learning approach for joint proactive caching and automatic vehicle control in the vehicle network. First, we model the autonomous vehicle system and the proactive caching system as separate Markov decision processes, respectively. Then, we propose a model-free algorithm based on deep Q-learning to find effective automatic vehicle control policy and proactive caching policy. Finally, the simulation results are given to demonstrate that the proposed solution can effectively maintain high-quality user experience in the V2R communication. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/WCSP.2019.8928131 | 2019 11th International Conference on Wireless Communications and Signal Processing (WCSP) |
Keywords | Field | DocType |
Internet of vehicles,V2R,proactive caching,automatic vehicle control,deep reinforcement learning | Data modeling,Base station,User experience design,Computer science,Markov decision process,Real-time computing,Vehicle control,Reinforcement learning,Automotive industry,The Internet | Conference |
ISSN | ISBN | Citations |
2325-3746 | 978-1-7281-3556-4 | 0 |
PageRank | References | Authors |
0.34 | 6 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zihui Zhu | 1 | 0 | 0.68 |
Zhengming Zhang | 2 | 20 | 2.65 |
Wen Yan | 3 | 0 | 1.69 |
Yongming Huang | 4 | 1472 | 146.50 |
Luxi Yang | 5 | 1180 | 118.08 |