Smart pareto-optimized genetic algorithm for energy-efficient clustering and routing in wireless sensor networks

一种用于无线传感器网络节能聚类和路由的智能帕累托优化遗传算法

阅读:1

Abstract

Healthcare, business, and the military employ wireless sensor networks (WSNs). Unfortunately, these networks have power supply, storage, and computing restrictions for sensor nodes. To overcome these difficulties, enhance energy efficiency, and extend network lifetime, we present a novel Pareto-based Genetic Algorithm for Energy-Efficient Clustering and Routing (PGAECR). It incorporates the best results from earlier networking sessions into the starting population for the present rounds, improving convergence speed and solution quality in the search process. The technique combines decisions about clustering and routing into one chromosome. A multi-objective fitness function that takes into account total energy consumption, residual energy balance, load distribution, and network longevity evaluates it. The first group comprises the best-performing solutions from the past, designed to aid convergence and enhance solution quality. An experimental examination examines factors such as transmission energy (ET, ER), data packet length, amplifier energy models (Efs, Emp), communication range, and node density across different network conditions. Experimental results indicate that PGAECR outperforms five other methods, demonstrating superior load balancing with minimal variance in cluster head loads across various scenarios. The proposed algorithm reduced energy usage by 12.4% and increased network longevity by 15.7% compared to conventional clustering and routing methods.

特别声明

1、本页面内容包含部分的内容是基于公开信息的合理引用;引用内容仅为补充信息,不代表本站立场。

2、若认为本页面引用内容涉及侵权,请及时与本站联系,我们将第一时间处理。

3、其他媒体/个人如需使用本页面原创内容,需注明“来源:[生知库]”并获得授权;使用引用内容的,需自行联系原作者获得许可。

4、投稿及合作请联系:info@biocloudy.com。