A Review on AI-Enabled Content Caching in Vehicular Edge Caching and Networks

With the emergence of many vehicular networking applications, the amount of data traffic in vehicular networks (VNs) is increasing at an exponential rate. Vehicular edge caching (VEC), which utilizes the on board storage resources and roadside edge servers has been considered as a promising technology to satisfy the demands of vehicular networking applications in VNs. However, the classical optimization schemes for content caching perform poorly in VEC primarily owing to the characteristics of the VNs. For instance, the high mobility of vehicles makes the content popularity highly time-varying and location-dependent. Artificial intelligence (AI) and machine learning (ML) is considered as a powerful technique to improve the caching efficiency in VEC. In this paper, we discuss the distinct challenges in VEC and provide a review on AI-enabled content caching schemes in VEC networks. In addition, we highlight the existing challenges and open research issues in order to spur further investigation in this area.