Abstract
As vehicle complexity and road congestion increase, combined with the emergence of electric vehicles, the need for intelligent transportation systems to improve on-road safety and transportation efficiency using vehicular networks has become essential. The evolution of high mobility wireless networks will provide improved support for connected vehicles through highly dynamic heterogeneous networks. Particularly, 5G deployment introduces new features and technologies that enable operators to capitalize on emerging infrastructure capabilities. Machine Learning (ML), a powerful methodology for adaptive and predictive system development, has emerged in both vehicular and conventional wireless networks. Adopting data-centric methods enables ML to address highly dynamic vehicular network issues faced by conventional solutions, such as traditional control loop design and optimization techniques. This article provides a short survey of ML applications in vehicular networks from the networking aspect. Research topics covered in this article include network control containing handover management and routing decision making, resource management, and energy efficiency in vehicular networks. The findings of this paper suggest more attention should be paid to network forming/deforming decision making. ML applications in vehicular networks should focus on researching multi-agent cooperated oriented methods and overall complexity reduction while utilizing enabling technologies, such as mobile edge computing for real-world deployment. Research datasets, simulation environment standardization, and method interpretability also require more research attention.
Highlights
Journal Pre-proof Abstract As vehicle complexity and road congestion increase, combined with the emergence of electric vehicles, the need for intelligent transportation systems to improve on-road safety and transportation efficiency using vehicular networks has become essential
Machine Learning (ML) applications in vehicular networks should focus on researching multi-agent cooperated oriented methods and overall complexity reduction while utilizing enabling technologies, such as mobile edge computing for real-world deployment
To help researchers focus on learning algorithm design and to simplify performance comparison, common problems should be identified with related datasets, while simulation environments should be standardized as in other Artificial Intelligence (AI) areas; these include the MNIST dataset [62] used for image recognition tasks and the Open AI Gym environment [63] employed for Reinforcement Learning (RL) methods
Summary
Journal Pre-proof Abstract As vehicle complexity and road congestion increase, combined with the emergence of electric vehicles, the need for intelligent transportation systems to improve on-road safety and transportation efficiency using vehicular networks has become essential. Simulation environment standardization, and method interpretability require more research attention As vehicles increase their awareness of their surrounding environment, combined with improvements in onboard computing power, the potential to support future intelligent transportation systems (ITSs) applications [1] grows to enable utility-based onboard services, while improving on-road safety and traffic congestion by inter connecting on-road vehicles, infrastructure, and pedestrians. Road vehicles have a much higher velocity compared to pedestrians using cell phones, leading to rapid temporal variation in vehicular wireless channels [6], significant Doppler spread [7], and the aforementioned rapid network topology changes These highly dynamic properties make tasks such as channel estimation and signal detection for vehicular networks challenging for traditional system designs [8].
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have