CACROS: A Context-Aware Cloud Content Roaming Service
Mahmud Hossain, Shahid Noor, Dibya Mukhapadhay, Ragib Hasan, Lei Li · 2016
Cloud computing has emerged as the primary and popular computing paradigm recently. Since cloud users move continuously, sustaining the required quality of service (QoS) in a cost effective manner is very challenging. For maintaining the required QoS for a moving user, the current cloud systems use some of the existing service replication or/and migration strategies. However, those policies become inefficient when a user frequently moves among multiple places. The primary reason for the failure of the existing migration strategies is they overlook several critical parameters associated with users' context during the service migration or replication. In this paper, we analyze the users' context thoroughly to determine their mobility and content usage patterns. We identify the key factors that affect the time and cost associated with the content storage and migration and design a model considering those factors. Based on our model CACROS (Context-Aware Cloud content Roaming Service), a cloud provider can perform the cost-benefit analysis between service migration and replication, and determine an efficient point for service hosting. We test our model with different potential scenarios using a real and simulated testbed and show that the model can provide a cost efficient solution for mobile cloud users while maintaining the desired level of quality of service.