Cloud storage applications, such as Dropbox and Google Drive, have recently become very popular among mobile users. In these applications, a cloud server is responsible for synchronizing updates to files among mobile users, and thus if files are shared by many mobile users and are frequently updated then the resulting synchronization traffic can be significant. In order to reduce the synchronization traffic with providing acceptable access latency, we propose a fog-assisted aggregated synchronization (FAS) scheme in which the fog computing server and the cloud server conduct localized and aggregated synchronizations, respectively. We develop an analytical model of the FAS scheme based on renewal-reward theory and use it for model-based adjustment of the timer that controls the trade-off between access latency and synchronization traffic. We use analytical and simulation results to give insight into the effects of the timer, the update-to-access ratio, the number of mobile users, and the sensitivity to the arrival process. The analytical and simulation results demonstrate that the FAS scheme can reduce the synchronization traffic significantly with acceptable access latency compared to conventional schemes.
Bibliographical noteFunding Information:
This work was supported in part by the National Research Foundation of Korea through the Korean Government under Grant NRF-2017R1E1A1A01073742, and in part by the Swedish Foundation for Strategic Research (SSF) through the Modane Project under Grant NRF-2014R1A2A1A12066986.
© 2019 IEEE.
- Mobile cloud storage
- fog-assisted aggregated synchronization
- renewal-reward theory
- synchronization traffic
ASJC Scopus subject areas
- Computer Science(all)
- Materials Science(all)