Reliable task allocation for soil moisture wireless sensor networks using differential evolution adaptive elite butterfly optimization algorithm

Wireless sensor technology advancements have made soil moisture wireless sensor networks (SMWSNs) a vital component of precision agriculture. However, the humidity nodes in SMWSNs have a weak ability in information collection, storage, calculation, etc. Hence, it is essential to reasonably pursue ta...

Full description

Bibliographic Details
Published in:Mathematical Biosciences and Engineering
Main Authors: Haitao Huang, Min Tian, Jie Zhou, Xiang Liu
Format: Article in Journal/Newspaper
Language:English
Published: AIMS Press 2023
Subjects:
task allocation
precision agriculture
soil moisture wireless sensor networks
algorithm
network benefit
Biotechnology
TP248.13-248.65
Mathematics
QA1-939
Boa
Beluga
Beluga whale
Beluga*
Online Access:https://doi.org/10.3934/mbe.2023656
https://doaj.org/article/056d8d3f2ad046f7bbf900ac0f100a4b
Description
Summary:Wireless sensor technology advancements have made soil moisture wireless sensor networks (SMWSNs) a vital component of precision agriculture. However, the humidity nodes in SMWSNs have a weak ability in information collection, storage, calculation, etc. Hence, it is essential to reasonably pursue task allocation for SMWSNs to improve the network benefits of SMWSNs. However, the task allocation of SMWSNs is an NP (Non-deterministic Polynomial)-hard issue, and its complexity becomes even higher when constraints such as limited computing capabilities and power are taken into consideration. In this paper, a novel differential evolution adaptive elite butterfly optimization algorithm (DEAEBOA) is proposed. DEAEBOA has significantly improved the task allocation efficiency of SMWSNs, effectively avoided plan stagnation, and greatly accelerated the convergence speed. In the meantime, a new adaptive operator was designed, which signally ameliorates the accuracy and performance of the algorithm. In addition, a new elite operator and differential evolution strategy are put forward to markedly enhance the global search ability, which can availably avoid local optimization. Simulation experiments were carried out by comparing DEAEBOA with the butterfly optimization algorithm (BOA), particle swarm optimization (PSO), genetic algorithm (GA), and beluga whale optimization (BWO). The simulation results show that DEAEBOA significantly improved the task allocation efficiency, and compared with BOA, PSO, GA, and BWO the network benefit rate increased by 11.86%, 5.46%, 8.98%, and 12.18% respectively.

Similar Items