Machine Learning-Based Models for Real-time Traffic Flow Prediction in Vehicular Networks
In recent years, ML-based models are gaining enormous attention from both the automotive industry and academia to support IoVs. Through the accurate prediction of traffic/road conditions, various safety and infotainment applications can efficiently utilize the network entities and enhance the quality of service. Topology control and mobility management protocols in IoVs, among others, would achieve higher efficiency through the support of real-time traffic flow forecasting. However, the current research trend on improving prediction accuracy refrains from answering the essential question of whether ML-based prediction schemes are suitable for real-time traffic prediction. To answer this question, a thorough extensive study to evaluate the efficiency of prediction- based traffic flow schemes is required. In this article, we investigate the effectiveness of various ML-based prediction models by considering both the prediction accuracy and computational time cost. Accordingly, we present rigorous quantitative analysis to identify the important factors that may restrict the use of ML-based prediction models to support real-time services in the IoV environment.
Duke Scholars
Published In
DOI
EISSN
ISSN
Publication Date
Volume
Issue
Start / End Page
Related Subject Headings
- Networking & Telecommunications
- 4606 Distributed computing and systems software
- 4006 Communications engineering
- 0906 Electrical and Electronic Engineering
- 0805 Distributed Computing
Citation
Published In
DOI
EISSN
ISSN
Publication Date
Volume
Issue
Start / End Page
Related Subject Headings
- Networking & Telecommunications
- 4606 Distributed computing and systems software
- 4006 Communications engineering
- 0906 Electrical and Electronic Engineering
- 0805 Distributed Computing