Latency Minimization for Content Delivery Networks with Wireless Edge Caching

Edge-caching has received much attention as an efficient technique to reduce delivery latency and network congestion during peak-traffic times by bringing data closer to end users. In this paper, we investigate the latency performance of content delivery networks with the aid of edge-caching, in which a data centre is serving the users via a shared wireless medium. Firstly, we derive a cache placement design which minimizes the average (buffering) latency during the delivery phase. It is found that the derived placement solution differs from the conventional placement method for throughput minimization. Secondly, for a given cache placement scheme, we optimize the signal transmission in the delivery phase taking into consideration the cached content to minimize the average user latency. Particularly, two optimization problems based on zero-forcing (ZF) and minimum mean square error (MMSE) designs are formulated subject to requesting rate and transmit power constraints. To deal with the non-convexity of the MMSE problem, an iterative algorithm is proposed that approximates the non-convex constraint by its first-order approximation. Finally, numerical results are presented to demonstrate the effectiveness of the proposed designs.