EMCloud: A hierarchical volunteer cloud with explicit mobile devices

Abstract

Summary Today, the world is witnessing an exponential growth in the computational capabilities and storage capabilities of mobile devices. This has inspired application developers to create new and interesting applications for mobile devices. The applications have varied resource requirements and mobile devices are heterogeneous in their configurations. The idea of this research is to design a model for resource sharing among mobile devices so that any type of application can be run on a mobile device with the help of other such devices in close geographical proximity. A novel architecture for managing a group of volunteer nodes with unused or underused resources is designed and algorithms that are required for its operation are developed. The purpose of this research is to shift the focus towards futuristic computing paradigm where seamless resource sharing in the network would be feasible with explicitly all mobile nodes and without any dependency on fixed infrastructures. An extensive evaluation of the proposed Explicit Mobile Cloud (EMCloud) has been undertaken for mobile nodes in the network. It includes experience with a prototype that demonstrates EMCloud's performance. Simulation results demonstrate that the proposed scheme outperforms the state‐of‐the‐art Serendipity, OpenNebula, and Eucalyptus prototypes in terms of success rate and average delay for different network density, mobility, network load, and extent of hierarchy.

Adaptive Context-Aware Energy Optimization for Services on Mobile Devices with Use of Machine Learning

“…For conducting tests, artificial training data were generated, containing 1,000 random examples, which corresponds to executing 1,000 tasks using the system developed. Every classifier was tested with different percentages (25%, 50%, 75% and 100%) 3 of the training data set used. Tests for specific percentage values were repeated 100 times and the final result was averaged.…”

“…The adaptation process in the context of optimizing power consumption can be implemented with respect to the mobile device itself and also to the mobile services and applications running on the device. Methods allowing for adaptations of this type often use remote resources such as cloud computing (the Mobile Cloud Computing concept [2]) or another mobile device with appropriate resources (the cloudlets concept), to which applications/services or their components are offloaded in order to optimize the operation of the mobile device [3]. The choice of when and what to offload from the mobile device can be made offline during the software development process or dynamically when the device is working.…”

“…Weka's C4.5 implementation (J48) was used in the tests 3. For example, a 25% test meant that to build the classifier, 250 examples were used from the input data.…”

Adaptive context‐aware service optimization in mobile cloud computing accounting for security aspects

“…The use of context information may allow the adaptation of mobile services to prevailing conditions in order to improve their quality parameters (such as execution time) and to optimize power consumption. Methods enabling such adaptations often use remote resources such as in the case of MCC 1 or another mobile device with appropriate resources (the cloudlet concept) to which services or their components can be offloaded in order to optimize the operation of the mobile device 2 . The choice of when and what to offload from the mobile device can be made offline during the software development process or dynamically when the device is operating and a computational task to be allocated arrives.…”