Adaptive Task Offloading in Vehicular Edge Computing Networks: a Reinforcement Learning Based Scheme
- PDF / 1,360,159 Bytes
- 10 Pages / 595.224 x 790.955 pts Page_size
- 90 Downloads / 185 Views
Adaptive Task Offloading in Vehicular Edge Computing Networks: a Reinforcement Learning Based Scheme Jie Zhang1 · Hongzhi Guo2
· Jiajia Liu2
© Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract In recent years, with the rapid development of Internet of Things (IoTs) and artificial intelligence, vehicular networks have transformed from simple interactive systems to smart integrated networks. The accompanying intelligent connected vehicles (ICVs) can communicate with each other and connect to the urban traffic information network, to support intelligent applications, i.e., autonomous driving, intelligent navigation, and in-vehicle entertainment services. These applications are usually delay-sensitive and compute-intensive, with the result that the computation resources of vehicles cannot meet the quality requirements of service for vehicles. To solve this problem, vehicular edge computing networks (VECNs) that utilize mobile edge computing offloading technology are seen as a promising paradigm. However, existing task offloading schemes lack consideration of the highly dynamic feature of vehicular networks, which makes them unable to give time-varying offloading decisions for dynamic changes in vehicular networks. Meanwhile, the current mobility model cannot truly reflect the actual road traffic situation. Toward this end, we study the task offloading problem in VECNs with the synchronized random walk model. Then, we propose a reinforcement learning-based scheme as our solution, and verify its superior performance in processing delay reduction and dynamic scene adaptability. Keywords Vehicular networks · Mobile edge computing · Reinforcement learning
1 Introduction In the past, vehicular networks were only defined as some massive interactive networks of information such as vehicles’ location, speed, and route. However, with the rapid development of 5th generation mobile networks, Internet of Things (IoTs) and artificial intelligence, the explosion of data and computing needs has made vehicular networks begin to enter the intelligent era. Vehicular networks are transforming into integrated networks that enable traffic Jiajia Liu
[email protected] Jie Zhang zhangjie [email protected] Hongzhi Guo [email protected] 1
School of Cyber Engineering, Xidian University, Xi’an, Shaanxi, 710071, China
2
School of Cybersecurity, Northwestern Polytechnical University, Xi’an, Shaanxi, 710072, China
management, dynamic information services, and vehicle control with intelligence [1–3]. This trend of vehicular networks has attracted the attention of automakers such as Toyota, Volvo, and Mercedes-Benz. The accompanying intelligent connected vehicles (ICVs) with high-intelligent in-vehicle information systems can be connected to the urban traffic information network and smart grid. All the real-time information about road conditions, weather, and emergencies can be obtained at any time, and then the corresponding data can be provided. These features will lead to a new lifestyle shift, such as smar
Data Loading...
