Toward Intelligent Vehicular Networks: A Machine Learning Framework

Abstract

As wireless networks evolve towards high mobility and providing better support for connected vehicles, a number of new challenges arise due to the resulting high dynamics in vehicular environments and thus motive rethinking of traditional wireless design methodologies. Future intelligent vehicles, which are at the heart of high mobility networks, are increasingly equipped with multiple advanced onboard sensors and keep generating large volumes of data. Machine learning, as an effective approach to artificial intelligence, can provide a rich set of tools to exploit such data for the benefit of the networks. In this article, we first identify the distinctive characteristics of high mobility vehicular networks and motivate the use of machine learning to address the resulting challenges. After a brief introduction of the major concepts of machine learning, we discuss its applications to learn the dynamics of vehicular networks and make informed decisions to optimize network performance. In particular, we discuss in greater detail the application of reinforcement learning in managing network resources as an alternative to the prevalent optimization approach. Finally, some open issues worth further investigation are highlighted.

Reliable Federated Learning for Mobile Networks

“…However, the distributed vehicles are not willing to share local traffic sensing data because of the concern of privacy leakage. To address this problem, the federated learning technique can be used to train prediction models without a direct access to the personal data on the vehicles, which not only enhances traffic prediction accuracy but also protects data privacy of vehicles [8]. • Mobile healthcare: Health data from patients can be shared among hospitals or medical researchers to improve clinical services and healthcare analytics.…”

Cache-Aided Non-Orthogonal Multiple Access for 5G-Enabled Vehicular Networks

“…Future intelligent vehicles are envisioned to be equipped with hundreds of on-board advanced sensors such as cameras, RADAR, and light detection and ranging, which are expected to generate a massive amount of data. In this regard, machine learning (ML), which is a branch of artificial intelligence (AI), can be used as an effective tool to learn from data, identify unique patterns and finally make proper decisions with minimal human intervention while ensuring reliability and efficiency [11], [12]. ML has recently received significant attention as an emerging field in vehicle automation [13].…”

An Efficient Requirement-Aware Attachment Policy for Future Millimeter Wave Vehicular Networks

“…The aforementioned association policies were proposed for cellular networks, which might not be fully representative of a vehicular system due to the more challenging propagation and traffic characteristics of highly mobile vehicular nodes. Although some recent works in the literature have tried to provide preliminary insights into user association also in the context of vehicular networks [24], e.g., leveraging reinforcement learning [25], there remain many open problems which call for innovative modeling and design solutions. Our work tries to fill this gap by extending traditional cellular-based attachment algorithms and integrating physical-layer metrics with application requirements at the higher layers.…”