Data caching and selection in 5G networks using F2F communication

Abstract

As an emergent technology the IoT promises to harness the computational and data resources distributed across different remote clouds. Fog computing extends cloud computing by bringing the network and cloud resources closer to the network edge. As the number of resources contributing to the cloud/fog system grows, so the problems associated with efficient and effective resource selection and allocation. In this paper, we introduce a fog-to-fog (F2F) data caching and selection method, which allows IoT devices to retrieve data in a faster and more efficient way. The proposed solution is based on a data caching and selection strategy using a multi-agent cooperation framework. Caching is achieved by decomposing cloud data into a set of files and then placed into fog storage sites. The selection process is based on a run-time file location prediction technique, which collects and maintains a repository of fog data in the form of log files. When data needs to be retrieved, prediction is made with the aid of these logs and previous successful search queries resulting in realistic run-time location estimates as well as best fog selection. Simulation results showcase the reduced data retrieval latency that enable tactile Internet in 5G. Additionally, results show increased successful file hit ratio leading to a reduced number of repeated downloads.