No abstract

No abstract

The proliferation of IoT devices has amplified the challenges for cloud computing, causing bottleneck congestion which affects the delivery of the required quality of service. For some services that are delay sensitive, response time is extremely critical to avoid fatalities. Therefore, Cisco presented fog computing in 2012 to overcome such limitations. In fog computing, data processing happens geographically close to the data origin to reduce response time and decrease network and energy consumption. In this paper, a new fog computing model is presented, in which a management layer is placed between the fog nodes and the cloud data centre to manage and control resources and communication. This layer addresses the heterogeneity nature of fog computing and complex connectivity that are considered challenges for fog computing. Sensitivity analysis using simulation is conducted to determine the efficiency of the proposed model. Different cluster configurations are implemented and evaluated in order to reach the optimal clustering method. The results show that the management layer improves QoS, with less bandwidth consumption and execution time.

The distributed nature of fog computing is designed to alleviate bottleneck traffic congestion which happens when a massive number of devices try to connect to more powerful computing resources simultaneously. Fog computing focuses on bringing data processing geographically closer to data source utilizing existing computing resources such as routers and switches. This heterogeneity nature of fog computing is an important feature and a challenge at the same time. To enhance fog computing availability with such nature, several studies have been conducted using different methods such as placement policies and scheduling algorithms. This paper proposes a fog computing model that includes an extra layer of duplex management system. This layer is designated for operating fog managers and warm spares to ensure higher availability for such a geographically disseminated paradigm. A Markov chain is utilized to calculate the probabilities of each possible state in the proposed model along with availability analysis. By utilizing the standby system, we were able to increase the availability to 93%.