No abstract

Due to the inherent property of the processing resource request from mobile active or passive devices as part of internet of things (IoT), processing capacity as well as latency become major optimization criteria. To achieve overall optimized uses of cloud resources -having dynamic tracking, monitoring as well as orchestration framework is one of the key challenges to overcome. In the same context, enhanced uses of computing devices at distributed location is predicted to facilitate the success of IoT; subsequently the success of fifth generation (5G) of Wireless technologies. This opens enormous potential to integrate the unused resources of such distributed computed devices within the conventional cloudlet or cloud federation. However, this requires an efficient micro-level distributed computing resource tracking, monitoring and orchestration; where resources are distributed in geo-location as well as the availability of unused resources are time variant in nature. In this paper, we have proposed a cognitive edge-computing based framework solution for these requirements in order to achieve an efficient use of these distributed resources. This provides the end-user with a dynamic soft extension of computing facilities of cloudlet and cloud federation, as well as a revenue generation avenue to enduser. The simulation results show that such extension can be an exponential function of the number of local processing platforms agreed to participate in the proposed cognitive resource sharing.

Although federated cloud computing has emerged as a promising paradigm, autonomous orchestration of resource utilization within the federation is still required to be balanced on the basis of workload assignment at a given time. Such potential imbalance of workload allocation as well as resource utilization may lead to a negative cloudburst within the federation. The analytical models found in the literature do not provide explicit framework to provide dynamic measure of workload requirement within a cloud federation environment. An additional challenge is the adoption of operational restrictions from regulatory body, the federation, or the federation participants. The analytical models presented in this paper have addressed workload balancing within a federated cloud environment under the access control restrictions agreed between federation members. The proposed analytical models provide a closed form solution for access probability and resource utilization at a given time. The analytical results are evaluated at different degree of security within the cloud federation environment and efficiency of the proposed workload balancing models is demonstrated. The proposed models can be used for cloud services dimensioning to handle high computational demand.

No abstract

No abstract