Asia-Pacific Network Operations and Management Symposium
Artificial Intelligence Based Edge Caching in Vehicular Mobile Networks: Architecture, Opportunities, and Research Issues
Kai-Min Liao, Guan-Yi Chen, Yu-Jia Chen,
PDF download (575.3KB)
This paper investigates the potentials of utilizing artificial intelligence (AI) based edge caching in the next generation of vehicular mobile networks. In recentyears, vehicle-to-everything (V2X) has been a researchfocus, which enables the exchange of informationbetween the vehicles and the outside world. To integratevehicular networks and cellular radio technology,cellular-V2X (C-V2X) was proposed in 3GPP release14. Further, mobile edge caching is regarded as aneffective technique to allow local data access, whichcan support the low latency requirement of the V2X usecases. With the advance of AI technologies such asdeep learning, there has been increasing demand ininference and learning from big vehicular data. In thispaper, we present the detail architecture of AI basededge caching in vehicular networks with misbehavingvehicle detection as an illustrative case. Performanceresults are provided to investigate the benefit of theproposed architecture. Finally, we highlight thepotential research directions.