The increased usage of IoT devices, grouped in fogs, has highlighted the existent breach between traditional cloud computing services offering and current IoT needs. Cloud computing traditionally serves IoT customers supporting them on the storage and virtualization of their generated data and generating value for their businesses. However, the growth of IoT is affecting the way traditional cloud architectures work. The increased amount of data to be transferred can create potential bottlenecks driving non-negligible latency concerns. Furthermore, sending such a big amount of data to a cloud environment in very short periods of time can be inefficient and ineffective, apart from cumbersome and expensive. Both, fog and cloud, are concerned with compute, networking and storage; they share many of the mechanisms and attributes, such as virtualization and multitenancy. However, fog computing aims to address the latency issues detected in large IoT scenarios. This way, fog computing is not devised as a competitor to cloud; quite on the contrary, it is envisioned as the perfect ally for a broad spectrum of use cases and applications for which traditional cloud computing is not sufficient.
mF2C aims to close this gap providing a framework capable of managing resources and services in an optimal way. When put together, cloud and fog computing create a new stack of resources, referred to as Fog-to-Cloud (F2C), creating the need for a new, open, coordinated management ecosystem. To tackle those issues mF2C proposes an open, secure, decentralized, multi-stakeholder management framework, expected to set the foundations for a novel distributed system architecture.
Thus, the main goal is to design and develop a platform facilitating the efficient usage of resources, taking into consideration service requirements and user demands, in a paradigm shifting scenario combining cloud and fog computing. More in detail, mF2C can be decomposed in the following objectives:
- Manage a large, decentralized, heterogeneous, open, volatile, dynamic and non-trustable set of resources (from cloud to the edge of the network).
- Create new fog instances dynamically, facilitating their collaboration (resource sharing) with other fog instances, and associations with cloud computing systems through open interfaces and software compatibility.
- Offload computations, transparently and optimally to applications, between fog and cloud computing systems, reallocating both resources and services, as well as executing services in parallel.
- Enable efficient and cost-effective solutions, while expanding the scalability of businesses. Thus, developing new business models based on F2C solutions.
- Ensure interoperability by adopting standards and de-facto market standards.