An autonomous IoT service placement methodology in fog computing. (10th December 2020)

• Record Type: Journal Article
• Authors: Ayoubi, Masoumeh; Ramezanpour, Mohammadreza; Khorsand, Reihaneh
• Is Part Of: Software, practice & experience. Volume 51:Number 5(2021)
• Page Start: 1097
• Page End: 1120
• Publication Date: 2020-12-10
• Subjects: evolutionary algorithm -- fog computing -- Internet of Things -- service placement; Computer software -- Periodicals; Computer programming -- Periodicals; Computer programs -- Periodicals; 005.3
• DOI: 10.1002/spe.2939
• Languages: English
• ISSNs: 0038-0644

Abstract

Abstract: With the increase in the number of Internet of Things (IoT) devices having limited resources, an extension of the cloud‐computing paradigm has emerged so‐called fog computing, where all the fog cells are located at the edge of the network and the latency can be reduced. Meanwhile, an important challenge has attracted much attention with the definition of fog computing is service placement problem that is still at its very beginning research. It allows to deployment IoT applications on computational fog resources, with the objective of optimizing quality of service (QoS) requirements of applications while taking into account maximizing the utilization of fog resources. In this paper, an autonomous IoT service placement methodology including four phases of monitoring, analysis, decision‐making, and execution is proposed called as (MADE). First, the available resources and application services' status are monitored at run time. Next, the requested services are prioritized with respect to application services' deadline. Then, the Strength Pareto Evolutionary Algorithm II is applied to take decisions about the application services placement as a multi‐objective optimization problem. Finally, the decisions made in the previous phases are executed in a fog environment. The experiment results indicate that the proposed methodology outperforms its counterparts in terms of different performance metrics.