Open Access

ARTICLE

A Genetic Based Leader Election Algorithm for IoT Cloud Data Processing

by Samira Kanwal¹, Zeshan Iqbal¹, Aun Irtaza¹, Rashid Ali², Kamran Siddique^3,*

1 Department of Computer Science, University of Engineering and Technology, Taxila, 47050, Pakistan
2 School of Intelligent Mechatronics Engineering, Sejong University, Seoul, Korea
3 School of Electrical and Computer Engineering, Department of Information and Communication Technology, Xiamen University Malaysia, Sepang, 43900, Malaysia

* Corresponding Author: Kamran Siddique. Email:

(This article belongs to the Special Issue: Machine Learning-based Intelligent Systems: Theories, Algorithms, and Applications)

Computers, Materials & Continua 2021, 68(2), 2469-2486. https://doi.org/10.32604/cmc.2021.014709

Received 11 October 2020; Accepted 14 November 2020; Issue published 13 April 2021

Abstract

In IoT networks, nodes communicate with each other for computational services, data processing, and resource sharing. Most of the time huge data is generated at the network edge due to extensive communication between IoT devices. So, this tidal data is transferred to the cloud data center (CDC) for efficient processing and effective data storage. In CDC, leader nodes are responsible for higher performance, reliability, deadlock handling, reduced latency, and to provide cost-effective computational services to the users. However, the optimal leader selection is a computationally hard problem as several factors like memory, CPU MIPS, and bandwidth, etc., are needed to be considered while selecting a leader amongst the set of available nodes. The existing approaches for leader selection are monolithic, as they identify the leader nodes without taking the optimal approach for leader resources. Therefore, for optimal leader node selection, a genetic algorithm (GA) based leader election (GLEA) approach is presented in this paper. The proposed GLEA uses the available resources to evaluate the candidate nodes during the leader election process. In the first phase of the algorithm, the cost of individual nodes, and overall cluster cost is computed on the bases of available resources. In the second phase, the best computational nodes are selected as the leader nodes by applying the genetic operations against a cost function by considering the available resources. The GLEA procedure is then compared against the Bees Life Algorithm (BLA). The experimental results show that the proposed scheme outperforms BLA in terms of execution time, SLA Violation, and their utilization with state-of-the-art schemes.

---

Keywords

---

Citations