Content-Aware Caching at the Mobile Edge Network Using Federated Learning

The explosive growth of mobile data traffic generated primarily from resource-hungry video streaming sessions challenges the service providers to deliver a better Quality of Service to the heterogeneous end-users. Content caching in Edge Computing is a promising solution to cope with this exponential rise in video traffic. The most popular videos are typically stored in the local caches of edge servers to provide fast and continuous access to videos. However, various edge caching strategies fail to cope with the dynamic request patterns of the users. Most learning-based caching models are generally trained in a centralized way, which overconsumes the network resources during training and transmission of video requests. Therefore, we propose a Federated Learning-based Reinforcement Learning caching framework called FedCache in this work. In FedCache, the training is decentralised on the end-user devices with its local data. The trained parameters from the end users are aggregated at the central server. A comprehensive set of experiments were performed, and FedCache outperformed existing state-of-the-art caching strategies concerning cache hit rate, access delay and backhaul traffic significantly.