Reinforcement Learning for Resource Provisioning in Vehicular Cloud

TL;DR

This paper explores how reinforcement learning can improve resource provisioning in vehicular clouds by addressing dynamic demands and QoS challenges, leveraging long-term benefits and reducing overhead.

Contribution

It demonstrates the advantages of using reinforcement learning techniques for efficient resource provisioning in vehicular cloud environments.

Findings

Reinforcement learning effectively manages dynamic resource demands.

RL reduces overhead in resource provisioning.

Improves QoS compliance in vehicular clouds.

Abstract

This article presents a concise view of vehicular clouds that incorporates various vehicular cloud models, which have been proposed, to date. Essentially, they all extend the traditional cloud and its utility computing functionalities across the entities in the vehicular ad hoc network (VANET). These entities include fixed road-side units (RSUs), on-board units (OBUs) embedded in the vehicle and personal smart devices of the driver and passengers. Cumulatively, these entities yield abundant processing, storage, sensing and communication resources. However, vehicular clouds require novel resource provisioning techniques, which can address the intrinsic challenges of (i) dynamic demands for the resources and (ii) stringent QoS requirements. In this article, we show the benefits of reinforcement learning based techniques for resource provisioning in the vehicular cloud. The learning techniques can perceive long term benefits and are ideal for minimizing the overhead of resource provisioning for vehicular clouds.