Evaluating the benefits of combined and continuous Fog-to-Cloud architectures

Abstract

The need to extend the features of Cloud computing to the edge of the network has fueled the development of new computing architectures, such as Fog computing. When put together, the combined and continuous use of fog and cloud computing, lays the foundation for a new and highly heterogeneous computing ecosystem, making the most out of both, cloud and fog. Incipient research efforts are devoted to propose a management architecture to properly manage such combination of resources, such as the reference architecture proposed by the OpenFog Consortium or the recent Fog-to-Cloud (F2C). In this paper, we pay attention to such a combined ecosystem and particularly evaluate the potential benefits of F2C in dynamic scenarios, considering computing resources mobility and different traffic patterns. By means of extensive simulations we specifically study the aspects of service response time, network bandwidth occupancy, power consumption and service disruption probability. The results indicate that a combined fog-to-cloud architecture brings significant performance benefits in comparison with the traditional standalone Cloud, e.g., over 50% reduction in terms of power consumption.

Towards a proper service placement in combined Fog-to-Cloud (F2C) architectures

“…From what has been stated so far, it is clear that fog computing and cloud computing, when jointly deployed can bring remarkable benefits. In line with this, the F2C approach, as a theoretical concept, can become the right framework to optimize the execution of highly demanding IoT services, paving the way to a perfect matching between resources capacities and services demands, leveraging both the distributed and centralized resource allocation and service placement (see also [9]). As a matter of wording, we define that if a service to be executed is placed in several resources, a distributed resource allocation strategy is deployed.…”

“…The first, leverages the work done by the, industrially led, OpenFog Consortium, turning into the definition of a high-level architecture, referred to as the OpenFog RA (Reference Architecture) for cloud and fog management [7], intended to have a remarkable impact on the standards bodies. The second, so-called Fog-to-Cloud (F2C), was proposed in [8], evaluated in [9] and its design is the main purpose of the EU H2020 mF2C project [10]. The proposed management architecture is envisioned as a set of hierarchically distributed layers, putting together the complete set of resources from the edge up to the cloud.…”

Towards Distributed Data Management in Fog Computing

“…In Fog Computing, both control and data storage are performed centrally. However, storing everything in the Cloud is not realistic because of (a) the high latency [57], (b) the high traffic demand between edge and Cloud, and (c) the high storage cost. In addition, the mobility of the Fog or edge devices is an important parameter under consideration.…”

Benefits of a Fog-to-Cloud Approach in Proximity Marketing

“…The EC Horizon 2020 program in 2016 has funded a new research initiative (mF2C) 3 bringing together relevant industry and academic players in the cloud arena, aimed at designing an open, secure, decentralized, multi-stakeholder management framework for F2C (Fog-to-Cloud) computing, including novel programming models, privacy and security, data storage techniques, service creation, brokerage solutions, SLA policies, and resource orchestration methods [7] [8]. There is an increasing demand on evaluating and identifying new market sectors and opportunities, and interest at the IoT evolution as a potential arena where current commercial cloud services offering could be enriched and differentiated.…”