Video data have been showed to dominate a significant portion of mobile data traffic and have a strong influence on a backhaul congestion issue in cellular networks. To tackle the problem, proactive caching is considered as a prominent candidate in terms of cost efficiency. In this chapter, we study a novel popularity-predicting-based caching procedure that takes raw video data as input to determine an optimal cache placement policy, which deals with both published and unpublished videos. For dealing with unpublished videos whose statistical information is unknown, features from the video content are extracted and condensed into a high-dimensional vector. This type of vector is then mapped to a lower-dimensional space. This process not only alleviates the computational burden but also creates a new vector that is more meaningful and comprehensive. At this stage, different types of prediction models can be trained to anticipate the popularity, for which information from published videos is used as training data.

Driven by the inherent spatiotemporal correlation in wireless data demand, cellular network design is becoming increasingly content-centric. An integral component of this new paradigm is the network's ability to cache popular content at its edge, which includes base stations, access points, and handheld devices. This additionally reduces latency, which is one of the key challenges facing the next generation of cellular networks. As discussed in the earlier chapters, the huge size of a typical library of popular files and the relatively smaller storage capacities of edge devices, especially small cell base stations (SCBSs) and handheld devices, make it necessary to carefully determine the set of files (cache) that should be placed on each device. Compared to a wireless network for which caching mechanisms are fairly well understood, a distinctive feature of content-centric wireless networks is the mobility of the end users, which needs to be included in the system design. Inspired by this, we investigate the impact of mobility on edge caching in this chapter.