Document Type : Computer Article
Authors
1
Department of Computer Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran.
2
Department of Electronic Engineering, Faculty of Engineering,, Shahr-e-Qods branch, Islamic Azad University, Tehran, Iran
3
Department of Computer engineering, science and research branch, Islamic Azad University, Tehran, Iran
Abstract
In the optimization of the Internet of Things (IoT) environment, devising solutions for network challenges, including scalability, routing, reliability, security, energy efficiency, network lifetime, density, heterogeneity, and quality of service, is essential. In this context, the utilization of cutting-edge approaches for monitoring and managing energy consumption and end-to-end delay (E2ED) holds paramount significance. This research addresses these concerns by clustering wireless sensor network nodes as a subset of the Internet of Things, employing a combination of the Self-Organizing Map (SOM) neural network pattern and the Grey Wolf Optimizer (GWO) algorithm for evaluation. In wireless sensor networks, the network layer manages routing challenges, and optimizing the efficiency of power consumption is crucial due to the substantial energy requirements of radio transmission. Consequently, conserving energy becomes a critical consideration in wireless sensor networks. Recent studies have concentrated on developing energy-efficient routing algorithms that reduce energy consumption during communications, thereby extending the network's lifespan. This research introduces and analyzes the SOM-GWO method and an energy-efficient routing algorithm. Simulation is conducted using Python, and a comparative assessment is made against protocols like LEACH, HEED, SOM-LEACH, and EESOM. Results indicate respective increases of 20%, 14.8%, 12.5%, and 3.8% in network lifetime. Furthermore, the proposed method exhibits a reduction of 37.5%, 33.3%, 16.6%, and 6.25% in average energy consumption compared to conventional algorithms. Based on empirical data from simulations, the proposed algorithm excels in terms of network lifetime, packet delivery ratio, operational power, and buffer occupancy.
Keywords
Main Subjects
)