In this chapter, we focus on the link layer between a vehicle and an access point. Due to the high mobility of vehicles, the channel condition is highly dynamic due to the varying path loss, shadowing, multi-path fading, etc., which requires an accurate tracking for the link capacity for the proper rate selection for the data packets sent to the air. Traditional model-based link management schemes cannot well follow the various channel variation patterns, and can lead to significantly performance loss especially in high mobility conditions. We propose to utilize multiple model-free ML enabled intelligent schemes that can learn from the previous network trace, which can provide efficient link prediction and near-optimal link rate choice. We analyze different spectrum access for vehicles, including unlicensed bands, TVWS, etc. And more categories of vehicles, e.g., maritime vehicles, flying vehicles, etc., are considered to evaluate the performance gain via the intelligent link management based on machine learning algorithms.
Intelligent Link Management for Vehicular Internet Access
Internet Access in Vehicular Networks ; Chapter : 4 ; 83-143
2021-09-25
61 pages
Article/Chapter (Book)
Electronic Resource
English
Internet access in vehicular networks
TIBKAT | 2021
|Internet Access Modeling for Vehicular Connection
Springer Verlag | 2021
|V2X Interworking via Vehicular Internet Access
Springer Verlag | 2021
|Introduction of Internet Access of Vehicular Networks
Springer Verlag | 2021
|