The design of mobility-aware framework for edge/fog computing for IoT systems with back-end cloud is gaining research interest. In this paper, a mobility-driven cloud-fog-edge collaborative real-time framework, Mobi-IoST, has been proposed, which has IoT, Edge, Fog and Cloud layers and exploits the mobility dynamics of the moving agent. The IoT and edge devices are considered to be the moving agents in a 2-D space, typically over the road-network. The framework analyses the spatio-temporal mobility data (GPS logs) along with the other contextual information and employs machine learning algorithm to predict the location of the moving agents (IoT and Edge devices) in real-time. The accumulated spatio-temporal traces from the moving agents are modelled using probabilistic graphical model. The major features of the proposed framework are: (i) hierarchical processing of the information using IoT-Edge-Fog-Cloud architecture to provide better QoS in real-time applications, (ii) uses mobility information for predicting next location of the agents to deliver processed information, and (iii) efficiently handles delay and power consumption. The performance evaluations yield that the proposed Mobi-IoST framework has approximately 93% accuracy and reduced the delay and power by approximately 23-26% and 37-41% respectively than the existing mobility-aware task delegation system.

Fast interactive response in mobile cloud computing is an emerging area of interest. Execution of applications inside the remote cloud increases the delay and affects the service quality. To avoid this difficulty cloudlet is introduced. Cloudlet provides the same service to the device as cloud at low latency but at high bandwidth. But selection of a cloudlet for offloading computation at low power is a major challenge if more than one cloudlet is available nearby. In this paper we have proposed a power and latency aware optimum cloudlet selection strategy for multi-cloudlet environment with the introduction of a proxy server. Theoretical analysis show that using the proposed approach the power and the latency consumption are reduced by approximately 29-32 and 33-36 percent respectively than offloading to the remote cloud. An experimental analysis of the proposed cloudlet selection scheme is performed using cloudlets and cloud servers located at our university laboratory. Theoretical and experimental results demonstrate that using the proposed strategy power and latency aware cloudlet selection can be performed. The proposed approach is compared with the existing methods on multi-cloudlet scenario to demonstrate that the proposed approach reduces the power consumption and the system response time.