Rainbow framework: Running virtual machines on demand as a grid jobs

Boretskyi, Oleksandr; Salnikov, Andrii; Sliusar, Ievgen; Sudakov, Oleksandr; Boyko, Y.V.

doi:10.1109/idaacs.2015.7341449

Cited by 3 publications

(1 citation statement)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We call this a MAPE cycle. However, the scope of self-adaptation in these studies [11,15,16,17,18,19,20,21,22] is limited to a single system. Although it is possible to expand the application scope of existing frameworks to develop collaboration services between IoT-based multiple systems, it takes much time and effort to build a self-adaptive IoT collaboration service.…”

Section: Introductionmentioning

confidence: 99%

A Cloud-based Middleware for Self-Adaptive IoT-Collaboration Services

Park

2019

Sensors

View full text Add to dashboard Cite

The middleware framework for IoT collaboration services should provide efficient solutions to context awareness and uncertainty issues among multiple collaboration domains. However, existing middleware frameworks are mostly limited to a single system, and developing self-adaptive IoT collaboration services using existing frameworks requires developers to take considerable time and effort. Furthermore, the developed IoT collaboration services are often dependent on a particular domain, which cannot easily be referenced in other domains. This paper proposes a cloud-based middleware framework that provides a set of cloud services for self-adaptive IoT collaboration services. The proposed middleware framework is generic in the sense that it clearly separates domain-dependent components from the layers that leverage existing middleware frameworks. In addition, the proposed framework allows developers to upload domain-dependent components onto the cloud, search for registered components, and launch Virtual Machine (VM) running a new MAPE cycle via a convenient web-based interface. The feasibility of the proposed framework has been shown with a simulation of an IoT collaboration service that traces a criminal suspect. The performance evaluation shows that the proposed middleware framework runs with an overhead of only 6% compared to pure Java-based middleware and is scalable as the number of VMs increases up to 16.

show abstract