Multimedia Microservice Placement in Hierarchical Multi-tier Cloud-to-Fog Networks

The demand for multimedia services in mobile networks has increased in the last years. The high quantity of users mobile, both consuming and producing multimedia content to and from the Cloud can outpace the available bandwidth capacity. Notwithstanding the many benefits of Cloud Computing (CC), it has been noticed that it does not provide adequate latency in areas with high demands for multimedia content. Furthermore, using Fog Computing (FG) it is possible to improve on the above-mentioned issues, being especially useful in latency-sensitive applications such nodes are physically much closer to devices if compared to centralized data centers. The main goal of this work is twofold, first, it proposed a method to design/create a hierarchical multi-tier Cloud-to-Fog network. Second, it introduced a novel multimedia microservices placement algorithm for multi-tier Fog nodes. The performance assessment was composed of two months of real-world mobile network traffic data from Milan, Italy. The obtained results showed that our algorithm selects the nodes closer to the user to meet their demands. This decision improves the services delivered to end-users, for example, a local Fog node can instead be responsible for the video stream and is far quicker than offloading the processing to a centralized cloud platform.