Vol.:(0123456789) 1 3
Journal of Ambient Intelligence and Humanized Computing
https://doi.org/10.1007/s12652-020-01698-5
ORIGINAL RESEARCH
An improved dynamic deployment technique based‑on genetic
algorithm (IDDT‑GA) for maximizing coverage in wireless sensor
networks
Hanaa ZainEldin
1
· Mahmoud Badawy
1
· Mostafa Elhosseini
1,2
· Hesham Arafat
1
· Ajith Abraham
3
Received: 29 July 2019 / Accepted: 5 January 2020
© Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract
Recently, many researchers have paid attention to wireless sensor networks (WSNs) due to their ability to encourage the
innovation of the IT industry. Although WSN provides dynamically scalable solutions with various smart applications, the
growing need to maximize the area coverage with decreasing the percentage of deployed sensor nodes is still required. Ran-
dom deployment is preferable for large areas that require a maximal number of nodes but result in coverage holes. As a result,
mobile nodes are used to reduce coverage holes and maximize area coverage. The main objective of this study is to present
an Improved Dynamic Deployment Technique based-on Genetic Algorithm (IDDT-GA) to maximize the area coverage with
the lowest number of nodes as well as minimizing overlapping area between neighboring nodes. A two-point crossover novel
is introduced to demonstrate the notation of variable-length encoding. Simulation results reveal that the superiority of the
proposed IDDT-GA compared with other state-of-the-art techniques. IDDT-GA has better coverage rates with 9.69% and
a minimum overlapping ratio with 35.43% compared to deployment based on Harmony Search (HS). Also, IDDT-GA has
minimized the network cost by 13% and 7.44% than Immune Algorithm (IA) and Whale Optimization Algorithm (WOA)
respectively. Besides, it confrms its stability with 83.04% compared to maximizing coverage with WOA.
Keywords Coverage · Deployment techniques · Genetic algorithm (GA) · Whale optimization algorithm (WOA) · Wireless
sensor network (WSN) · Quality of service (QoS)
1 Introduction
Wireless sensor networks (WSNs) (Ezhilarasi and Krish-
naveni 2018) are a group of sensor nodes with limited pro-
cessing and low power capacity (Su and Zhao 2017). These
nodes are spatially scattered in an ad-hoc manner for collect-
ing physical information from the surrounding environment
and relaying collected data to the sink node as well. Diferent
environmental conditions can be recorded by WSNs such
as sound, wind, pressure, room temperature, humidity, and
pollution level. On other hands, WSNs heavily afect real-
time applications (Sengupta et al. 2013), which comprises
intelligent transportation systems (ITS), security monitor-
ing, military surveillance, battlefelds , health care, trans-
portation, environmental monitoring, industrial monitoring
(Aponte-Luis et al. 2018), and agriculture.
As a part of the WSNs scenario, the environmental appli-
cations which aim to track and record the environmental
changes, whether indoor or outdoor. The indoor applications
may fall into the category of urban applications (including
* Hanaa ZainEldin
eng.hanaa2011@gmail.com
Mahmoud Badawy
engbadawy@mans.edu.eg
Mostafa Elhosseini
melhosseini@mans.edu.eg
Hesham Arafat
h_arafat_ali@mans.edu.eg
Ajith Abraham
ajith.abraham@ieee.org
1
Computers Engineering and Control Systems Department,
Faculty of Engineering, Mansoura University,
Mansoura 35516, Egypt
2
College of Computer Science and Engineering, Taibah
University, Yanbu 30 012, Saudi Arabia
3
Machine Intelligence Research Labs (MIR Labs) Scientifc
Network for Innovation and Research Excellence, Auburn,
USA