Edge Content Caching with Deep Spatiotemporal Residual Network for IoV in Smart City

• DOI: 10.1145/3447032
• Publication Date: 2021-06-21T20:19:31Z
• Authors: Xiaolong Xu; Zijie Fang; Jie Zhang; Qiang He; Dongxiao Yu; Lianyong Qi; Wanchun Dou
• Keywords: Smart City; Edge device

Internet of Vehicles (IoV) enables numerous in-vehicle applications for smart cities, driving increasing service demands processing various contents (e.g., videos). Generally, efficient delivery, the from providers are processed on edge servers (ESs), as computing offers vehicular low-latency services. However, due to reusability same required by different distributed users, copies repeatedly in an server leads a waste resources storage, computation, and bandwidth) ESs. Therefore, it is challenge provide high-quality services while guaranteeing resource efficiency with content caching. To address challenge, caching method cities requirement prediction, named E-Cache, proposed. First, future requirements vehicles predicted based deep spatiotemporal residual network (ST-ResNet). Then, preliminary schemes elaborated requirements, which further adjusted many-objective optimization aiming at minimizing execution time energy consumption Eventually, experimental evaluations prove effectiveness E-Cache traffic trajectory big data.