Mobility-Aware Caching Scheduling for Fog Computing in mmWave Band

As an extension of cloud computing, fog computing at the edge of networks provides low latency, location awareness, and real-time interactions. At the same time, millimeter-wave communications are able to provide directional multi-gigabit transmission rates with large available bandwidth. Based on the user mobile trajectories in a region, several activity hotspots that users pass by frequently can be obtained. By caching popular content at the edge nodes near the hotspots, users can download the cached content directly at a short distance, and the user experience can be significantly improved. Considering multiple hotspots in a region, how to efficiently schedule the transmission for the caching at edge nodes becomes a key problem. In this paper, we focus on the problem of mobility-aware transmission scheduling for caching at edge nodes near hotspots and utilize the multi-hop relaying and concurrent transmissions to achieve better performance. After formulating the optimal scheduling problem as a stochastic nonlinear mixed integer program, we propose a mobility-aware caching scheduling scheme, called Multi-Hop Relaying-based Caching, where multi-hop D2D paths are established for edge nodes, and concurrent transmissions are exploited in the scheduling of caching at edge nodes. Extensive performance evaluation demonstrates that MHRC achieves more than $1\times $ higher expected cached data amount compared with the state-of-the-art schemes.