A Comparative Study of Swarm Intelligence-Based Optimization Algorithms in WSN

Abstract

In the last decades, WSN gets all the attention in research and applications especially in science and engineering fields due to it is great benefits which been introduced. These networks are used in rough and inaccessible environments such as battlefields, volcanoes, and forests, so basically there is a low chance to recharge or change the low battery or dead nodes. Hence, WSNs are hypersensitive and vulnerable to energy more than other classic wireless networks. Therefore, this led to emerging improvements rapidly in WSN to reach the goal of achieving the network requirements and satisfying the user needs at the same time to get the best results. Artificial Intelligent systems Toke the biggest share of the WSN development process. So, In this paper we will focus on an important section in an intelligent system based on optimization algorithms, is the swarm intelligence that depends on the real behavior of animals and insects colonies, it is a system that based on many individuals that working within a group as a team and coordinate their behavior using decentralized control and self- organization. SI-based optimization algorithms have a great and affirmative influence on WSN represented by minimize delays in data transmission between nodes in the network, network balancing and avoiding network traffic and overhead, save energy, and maximize the network lifetime. The algorithms that will be covered in this paper are ant colony optimization (ACO), particle swarm optimization (PSO), and artificial bee colony (ABC) by going deeply in describing the criteria of their work and analyses their models.