Professional Documents
Culture Documents
Thesis
Thesis
By
Huthaifa Mohammed Kanoosh AL Jubori
Department of Computer Science
Faculty of Computers and Artificial Intelligence,
Benha University,
Egypt.
Supervised By
Professor of CS, Vice-Dean for Education & Associate Prof. of CS, Vice Dean for
Student Affairs, Faculty of Computers Postgraduate Studies and Research Affairs,
and Artificial Intelligence , Faculty of Computers & Information,
Minia University, Egypt.
Benha University, Egypt.
2019
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
Signature:
Name:
Title:
Data: / / 2019
Signature:
Name:
Title:
Data: / /2019
Signature:
Name: Prof. Mazen Mohamed Selim
Title:
Data: / /2019
Vice-Dean for Education & Student Affairs, Faculty of Computers &
Artificial Intelligence, Benha University.
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
Supervisor Certification
We certify that this thesis was prepared under our supervision at Department of
Computer Sciences, Faculty of Computers and Informatics, Benha University, by
(Huthaifa Mohammed Kanoosh AL Jubori) as a partial fulfillment of the
requirements for the degree of Master in computers and informatics from Faculty
of Computers and Informatics.
Signature:
Name: Prof. Mazen Mohamed Selim
Title:
Data: / /2019
Vice-Dean for Education & Student Affairs, Faculty of Computers &
Artificial Intelligence, Benha University.
Signature:
Title:
Data: / /2019
Vice Dean for Graduate Studies and Research, Faculty of Computers and
Information, Minia University.
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
﴿اجملادةل﴾11 :
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
Degrees:
M.Sc. Registration Date: 1 / 7/ 2017
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
Acknowledgements
All the praises and thanks are to Allah, the most beneficent, and the most merciful.
It is fair to record my special thanks and gratitude to all my family members for
their support throughout my life, this thesis is simply impossible without them.
Dedicate my work
To My sweet heart
My Wife and my sons Yaman, Rawan, Yara, Shaam
Huthaifa
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
ABSTRACT
Nowadays, wireless sensor networks (WSNs) play a vital role in many real-life
environmental monitoring. In many cases, the nodes of WSNs are deployed randomly.
However, many of these applications cannot perform their function properly without
knowing the accurate location of the sensor nodes used to collect the data. Therefore,
estimating the locations of unknown nodes with the help of some nodes with known
metaheuristic algorithm called the Salp Swarm Algorithm (SSA) in which the
has been implemented and validated in different WSN deployments using different
numbers of target nodes and anchor nodes. Moreover, the proposed algorithm has been
algorithm (FA), and grey wolf optimizer (GWO) in terms of localization accuracy,
computing time, and a number of localized nodes. The obtained simulation results
have proved the superiority of the proposed algorithm compared to the other
List of Contents
i
Table of Contents
ii
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
List of Figures
Figure No: Figure Name……………...…...…………....…...…. …. Page No.
Figure.2.1 : The Architecture of a node in WSN ………….....………....……..….11
Figure.2.2 : WSNs and their relationship to infrastructure-based networks………11
Figure.2.3 : Taxonomy of WSNs applications.....….……...………………....…....12
Figure.2.4 : The classification of optimization problems ………….......................13
Figure.2.5 : Single-solution based metaheuristic algorithms …………….............15
Figure.2.6 : Population based metaheuristic Algorithms ……….……..................26
Figure.3.1 : A Taxonomy for the node localization schemes ……………….........32
Figure.3.2 : The pseudocode of the PSO algorithm …………………...…….........42
Figure.3.3 : The flow chart of the PSO algorithm ……………………….….....….43
Figure.3.4 : The pseudocode of the BOA algorithm ………………………..….…45
Figure.3.5 : The flow chart of the BOA algorithm ………………..….………......46
Figure.3.6 : The pseudocode of the FA algorithm………………………………...48
Figure.3.7 : The flow chart of the FA algorithm ………..….………………….….49
Figure.3.8 : The pseudocode of the GWO algorithm …….....................................51
Figure.3.9 : The flow chart of the GWO algorithm ………….…..……………….52
Figure.3.10 : (a) Individual salp. (b) Salps chain …………………………..….…...53
Figure.3.11 : The pseudocode of the SSA algorithm……………………...…….….55
Figure.3.12 : The flow chart of the SSA algorithm …………….……….…....…...56
Figure.4.1 : Node localization using different numbers of target nodes and anchor
nodes……………………………………………………………........64
Figure.4.2 : The localization error of the different localization algorithms in
different WSN deployments …………………………………………67
Figure.4.3 : The computing time of the different localization algorithms in different
WSN deployments……………………………………...…………….68
Figure.4.4 : The number of localized nodes of the different localization algorithms
in different WSN deployments ………………………………………68
iii
Table of Contents
List of Tables
Table No: Table Name……………………………………………….....Page No.
Table.4.1 : Parameters setting of simulation environment ............................................61
Table.4.2 : Performance metrics of different localization algorithms …………...........65
Table.4.3 : Summary of experimental results of the different localization algorithms ….
……………………………………………...……………………………...66
iv
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
Abbreviations
Abbreviation : Description…………………….………….……........................
ABC : Artificial Bee Colony ……………………………..………………..
AoA : Angle of Arrival …………………………….……………………...
BBO : Biogeography-Based Optimization ………………………………..
BOA :
Butterfly Optimization Algorithm ……………………………..…..
BOA : Bat Optimization Algorithm ……………………………..………...
DA :
Dragonfly Algorithm ……………………………..………………..
DE : Differential Evolution……………………………..………………..
EC :
Evolutionary Computation ……………………………..…………..
EFWA :
Enhanced Fireworks Algorithm ……………………………..……..
FA : Firefly Algorithm ……………………………..……………………
GA :
Genetic Algorithm ……………………………..…………………..
GSA : Gravitational Search Algorithm ……………………………..……..
HS :
Harmony Search ……………………………..…………………….
IOT : Internet of Things ……………………………..……………………
ITS :
Intelligent Transport System ……………………………..………...
LM : Linearization Method ……………………………..………………..
v
Table of Contents
MCS :
Modified Cuckoo Search ……………………………..……………
MDS : Multi-Dimensional Scaling ……………………………..………….
PGSA :
Plant Growth Simulation Algorithm ……………………………….
PSO : Particle Swarm Optimization ……………………………..………..
SA :
Simulated Annealing ……………………………..………………...
SDP : Semi-Definite Programming ……………………………..………...
SSA :
Salp Swarm Algorithm ……………………………..………………
TDoA : Time Difference of Arrival ……………………………..………….
WSNs :
Wireless Sensor Networks ……………………………..…………..
vi
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
Chapter 1: Introduction
1.1. Introduction
autonomous sensor nodes that are distributed in a specific area for cooperatively
sensing their environment. In the last decade, WSNs have been employed in
environments where the sensor nodes of a WSN are deployed, people may not
be able to go and fix these nodes. In these environments, the sensor nodes are
usually take random positions. On the other hand, in many applications, the
positions of the sensor nodes that gathered the information are unknown. This
In order to localize the sensor nodes of a WSN, a GPS can be attached to each
sensor during the network deployment. Then, the GPS can be used to find the
coordinates of the sensor nodes. However, using GPS for localizing sensor
2
Chapter 1: Introduction
conditions may disturb the GPS reception ability [2]. An alternative approach is
to attach GPS to some nodes which are called anchor nodes or beacon nodes.
Thus, the positions of these nodes with attached GPS are known after deploying
the nodes of the wireless sensor network. Using the known locations of anchor
unknown nodes [2]. There are two classes of non-GPS based localization
point-to-point distance estimation among the sensor nodes is used with rang-
1.2. Motivation
the locations of the used sensor nodes are known. These applications include
3
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
last two decades, many approaches have been developed to handle this problem.
stochastic approaches.
an optimization problem by trial and error in which the feasible solutions are
particle swarm optimization (PSO), artificial bee colony (ABC), etc. have been
accuracy, number of localized nodes, and computation time. Hence, more efforts
Sensor nodes of WSNs are usually scattered in an ad-hoc fashion in which the
important for many applications that deploy WSNs to perform its mission. A
4
Chapter 1: Introduction
simple solution for this problem is to equip each sensor node with a GPS
• Using a GPS receiver with each sensor node increases the total cost of the
WSN.
WSN in which some nodes are equipped with GPS receivers (anchors or
beacons) and the rest of nodes (unknown or target nodes) are localized with the
5
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
and efficient localization approach that can estimate the locations of target nodes
literature.
6
Chapter 1: Introduction
the Salp Swarm Algorithm (SSA) for the first time ever to localize the nodes of
butterfly optimization algorithm (BOA), firefly algorithm (FA), and grey wolf
optimizer (GWO) algorithms. The results have shown that the SSA based
localization accuracy.
scheme based on a recent swarm optimization algorithm which can optimize the
organized as follows:
7
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
• Chapter 5 contains the conclusion and the future work of the thesis.
8
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
2.1. Introduction
This chapter presents the basic concepts that are relevant to the topic of the
section to describe the basic ideas behind the different metaheuristic algorithms.
autonomous sensor nodes and communicate over short distances [6]. Each node
converter, a memory unit, and a power supply (battery). The typical architecture
of a WSN node is illustrated in Figure 2.1. A WSN node may also be equipped
Typically, sensor nodes are usually grouped into clusters. In each cluster, one
of these nodes is considered as a cluster head. All other nodes collect the
10
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
information and deliver them to the cluster head which in turn forwards the
collected information to a special node call sink node or base station, through a
Sensors
A/D
Memory Processor
Converter
Radio Transceiver
Power Supply
11
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
Tracking applications include habitat tracking [15], traffic tracking [16], military
Enviornment
Agriculture
Industry
Health care
Monitoring
Ecology
Urban
Applications
Smart House
Military
Industry
Public Health
Tracking
Ecology
Military
12
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
within a reasonable time limit. As shown in Figure 2.4, these problems can be
adapt to each problem. The greek prefix “meta” means that these algorithm are
there is no heuristic that can be used to provide a reasonable solution for that
Optimization
Problems
13
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
biology or ethology);
function;
under consideration.
space that contain high quality solutions. It is important to focus the search in
some promising areas of the accumulated search experience. On the other side,
the main objective of the exploration is to discover new areas in the search
space. The main difference between metaheuristic algorithms is the way they
take to achieve the balance between the exploration and the exploitation [28,
including the search path they follow, the memory usage, the type of
14
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
algorithms begins with a single initial solution and move away from it,
Trajectory methods mainly include the simulated annealing method, the tabu
search, the GRASP method, the variable neighborhood search, the guided local
Simulated Annealing
Single-Solution Based Metahuristics
Tabu Search
GRASP Method
Variable
Neighborhood search
etc.
15
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
of solutions rather than with a single solution. As shown in Figure 2.6, the most
programming [23]. On other side, the idea behind SI, the idea is to produce
consisting of a population of simple agents that interact locally with one another
and with their environment. These entities individually have very limited
capabilities. However, through the cooperative work they can perform many
complex tasks that are crucial for their survival. Although there is normally no
local interactions between such agents often lead to the emergence of global and
16
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
Genetic Algorithms
Evolution Strategies
Evolutionary Evolutionary
Computation (EC) Programming
Population Based Metahuristics
Genetic
Programming
etc.
Ant Colony
Optimization
Particle Swarm
Optimization
Grey Wolf
Swarm Intelligence
Optimization
Bee Colony
Optimization
etc.
In the last years, many optimization algorithms have been employed for
17
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
transforms the parameter estimation task into an optimization problem that can
nodes by utilizing the Free Search optimization. The simulation results have
verified that the proposed localization algorithm has significantly improved the
among adjacent nodes. The proposed system does not require good network
optimization (PSO) has been employed to determine the optimum location of the
sensor nodes. Experimental results have proved that the proposed system has a
iterative localization using bio-inspired algorithms. The nodes that have been
localized during an iteration are used as references for the unknown nodes in the
next iterations. In their proposed work, particle swarm optimization (PSO) and
18
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
bacterial foraging algorithm (BFA) have been used for addressing the
on Harmony Search (HS) algorithm with a local search procedure. The main
decrease the area in which each node can be located. The simulation results have
verified that the proposed algorithm is better than another Simulated Annealing
node localization algorithm that considers the whole effects resulting from
topology. Additionally, the obtained simulation results have shown that the
precision stability compared to the DV-Hop algorithm without the need for extra
19
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
Optimization (PSO). The main design objectives of the proposed algorithm are
to enhance the efficiency and accuracy of BFA and to avoid getting stuck in a
local extreme. In the proposed algorithm, PSO is merged into the chemotaxis of
BFA to speed up the convergence rate. Moreover, the global search ability is
based on the energy of bacteria. The obtained simulation results have verified
simulation algorithm (PGSA) that simulates the growth of plants. In their work,
they proposed inserting the plant root of adaptive backlight function into the
original PGSA for improving convergence time and localization precision. The
obtained simulation results have verified that the proposed algorithm is better
O.D. Jegede and K. Ferens have employed the genetic algorithm (GA) for
learning the environmental issues within a WSN for effectively localizing its
sensor nodes. For every coordinate in the grid network area, given random
20
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
environment and to decrease the possible errors associated with the RSSI
measurement taken for each coordinate. The conducted simulation shows that
GA can reasonably localize sensor nodes using the coordinates of three anchors
[30].
S. Goyal and M.S. Patterh have proposed a Cuckoo Search (CS) based
controlling the global search ability. The conducted simulation has shown that
algorithm for efficiently and precisely localizing the sensor nodes in addition to
solving the flip ambiguity problem. In the first phase, the initial search space is
defined using the bounding box method. In the second phase, a refinement
process is performed for correcting the error resulting from the flip ambiguity.
21
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
problem. Also, the proposed algorithm tried to handle the flip ambiguity
problem and to localize the sensor nodes that collinear anchor nodes through the
refinement phase. The obtained simulation results have shown that the proposed
compared to the range-based algorithms. In order to deal with this problem, they
have shown that the proposed localization algorithm has better localization
which depends on the measurements of the received signal strength (RSS) and
Parallel Firefly Algorithm (PFA). Taking into consideration the distance factor,
the proposed algorithm transforms the node localization problem in WSN into a
sensor nodes using the distances between a sensor and a few numbers of its 1-
22
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
hop neighbors. Simulation results have shown that the proposed approach is
better than PSO, GA, PFA, and RSS in terms of localization accuracy [35].
localization algorithm in WSNs. In the first phase, the positions of sensor nodes
approach. In their work, to perform the second phase, they employed Bat
shown that FOA-MAP is better than both BOA-MAP and MCS-MAP in terms
multiobjective functions include the space distance and the geometric topology
constraints. In the proposed algorithm, the size of the archive remains limited
using a dynamic method. Simulation results have shown that the proposed
23
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
in case of no ranging errors and provides good results in case of ranging errors.
achieved better results compared to FWA. Also, the two proposed localization
methods such as Grey Wolf Optimizer (GWO), Firefly Algorithm (FA), and
have been compared to the original ones in terms of the number of localized
based node localization algorithm. In the proposed method, the step size has
been modified to obtain a global optimal solution in a short time. Also, the
avoid local convergence. The performance of the proposed algorithm has been
range in terms of average localization error and localization success ratio. The
24
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
simulation results have proved that the proposed algorithm is better than the
time [40].
P.T. Daely and S.Y. Shin have proposed a node localization algorithm
which are randomly distributed in a specific area. The simulation results proved
that the proposed DA based algorithm is better than PSO in terms of localization
accuracy [41].
estimate the coordinates of sensor nodes in WSNs. The used objective functions
depend on two criteria namely, the nodes’ distance constraint and geometric
topology constraint. The simulation results have shown the superiority of the
localize the sensor nodes in WSNs. The proposed localization algorithm has
been validated using different numbers of nodes with distance measurements are
corrupted through the Gaussian noise. The simulation results have shown that
25
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
grey wolf optimization (GWO) whose main objective is to localize sensor nodes
in WSNs accurately. The proposed algorithm has been validated under different
algorithm (MBA). The simulation results have shown the superiority of the
(DE) algorithms. The authors observed that decreasing the square error of
estimated and measured distance can improve the localization accuracy. The
better than the Linearization Method (LM) in terms of localization accuracy and
26
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
localized nodes. The simulation results have shown the superiority of FPA
Based on the conducted experiments, the obtained results have shown that the
localization accuracy and time complexity get better when the size of the
algorithms and the obtained results have shown the superiority of the proposed
Things (IOT) using social learning based particle swarm optimization (SL-PSO).
The design objectives of the proposed algorithm are reducing the localization
error and time complexity. The obtain results have shown that SL-PSO is better
27
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
Doppler effect for improving the performance. The obtained results have shown
that the proposed algorithm is better than traditional bat algorithm and PSO
precision [50].
Tuba et al. have proposed a two-stage node localization algorithm with semi-
mobile anchors using firefly algorithm. The conducted experiments have shown
that the proposed localization algorithm is better that another PSO based
was never used for the localization problem in WSNs so far. Therefore, the main
objective of this thesis is to employ the SSA algorithm for handling the
28
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
2.5. Summary
In this chapter, the basic concepts that are relevant to the thesis have been
definition of wireless sensor networks and its applications. Then, taxonomy has
researches that are relevant to the topic of thesis have been covered and
metaheuristic algorithms that have been used in the proposed work are
29
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
3.1. Introduction
This chapter provides taxonomy for the node localization scheme with a
[52-56]. Equipping each sensor node with a GPS can be a direct solution for this
problem. However, this is impractical solution because of high cost and high
environments and dense forests. These problems associated with The GPS-
31
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
nodes with the help of some nodes with known positions or using the
classified into “Sparse vs. Dense”, “Anchor based vs. Anchor free”, “Indoor vs.
Outdoor” and “Static vs. Mobile”. “Anchor Based" and “Anchor Free"
localization schemes are further divided into “Range Based" and “Range Free"
schemes [58].
Localiztion
Algorithms
dense) and the type of applications that employ WSNs (indoor vs. outdoor). In
addition, it considers the mobility of sensor nodes (static vs. mobile) and the
32
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
sparse networks.
On the other side, sequential schemes compute the locations of sensor nodes
networks, two types of algorithms are proposed namely, node based localization
The node based localization based algorithm called ‘Sweeps’ [62] is related to
33
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
receivers. They are called known nodes, anchors, or beacons. The unknown
from the anchors. If the unknown nodes cooperate with each other and share
based localization approaches into: “Range based” and “Range free” localization
schemes.
to measure the distances including angle of arrival (AoA), time of arrival (ToA),
34
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
time difference of arrival (TDoA), acoustic energy, and received signal strength
indicator (RSSI). The first three methods provide more accurate distance
nodes, distances are combined using techniques like lateration or particle filter
etc [58].
the sensor nodes to compute the positions of the unknown nodes. It can be an
alternative for range based localization schemes that need complex and
do not localizes the unknown nodes using the known locations of some nodes
are classified into: range based anchor free and range free anchor free. Anchor
free localization algorithms do not need the anchor selection process, which is
35
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
Recently, the indoor positioning system became very popular because of its
task because the indoor environments are usually crowded and cluttered.
These are known as range based and range free, or profiling or fingerprinting.
Also, other hybrid localization schemes that depend on new concepts have been
introduced. Most of these localization schemes address the mobility issue along
which use triangulation, [67] which uses spectrum analysis, [68] which uses
curve fitting, [69] which uses multi-lateration, and [70] which uses a
nodes.
36
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
Node localization schemes can also be categorized into “Static” and “Mobile”
localization schemes. Generally, few research works that addressed the mobility
issue of sensor nodes in WSNs. Most of them use the nodes’ mobility
usually need centralized processing which requires long time to run. In addition,
Mobility can influence the localization process in many aspects. One of the
may lead to latency, where the sensor will have changed its position since the
measurement took place. Another issue is Doppler shift which can occur when
Although WSNs were first presented for military purposes, it now deployed
in many applications to perform a variety of tasks. The fields that employ WSNs
37
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
given below.
1. Military Applications
landmines [73] with sensing information regarding threats from their neighbor
and medical via 911 calling. One such implementation involves the localization
of a mobile station placed within a city for citizens to place immediate 911 calls
[74].
The Internet of Things (IoT) and Cyber Physical Systems are newly
wide variety of electronic devices communicate with each other and control the
systems [58].
38
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
One of the most popular applications of WSNs is the transport control and
agricultural issues, forest and water quality monitoring etc. Being necessary for
estimation [60].
Wireless sensor networks have improved the home and office environment by
environments [60].
Recently, researchers have used to look into natural processes and creatures to
get inspired for solving the difficult real-world problems. Many natural
39
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
social group behavior and foraging strategies. During the last decades, the field
research area and getting an increasing attention. Currently, these algorithms are
widely adopted to solve a wide range of problems that belong to different fields
in this field constitute two main families: the evolutionary computing methods
and the swarm intelligence algorithms. Although both families of algorithms are
generally dedicated towards solving search and optimization problems, they are
certainly not equivalent, and each has its own distinguishing features [76].
which has gained huge popularity in these days. Algorithms belonging to this
domain, draw inspiration from the collective intelligence emerging from the
behavior of a group of social insects (like bees, termites and wasps). When
acting as a community, these insects even with very limited individual capability
can jointly (cooperatively) perform many complex tasks necessary for their
survival. Problems like finding and storing foods, selecting and picking up
materials for future usage require a detailed planning, and are solved by insect
40
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
butterfly optimization algorithm (BOA), firefly algorithm (FA), and grey wolf
optimizer (GWO). The ideas behind the different the swarm optimization
that simulate a swarm population moving around in the search space to find the
best solution. Each particle provides a candidate solution for the problem and is
search space to find optimal solutions and each particle has a velocity
each particle is updated based on the best position that has been achieved by the
particle himself (pbest) and the best position that has been achieved by all the
41
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
particles so far (gbest). The velocity and the position of each particle are updated
𝑡+1 𝑡 𝑡 𝑡
𝑣𝑖𝑑 = 𝑤 ∗ 𝑣𝑖𝑑 + 𝑐1 ∗ 𝑟1 ∗ (𝑝𝑖𝑑 − 𝑥𝑖𝑑 ) + 𝑐2 ∗ 𝑟2 ∗ (𝑝𝑔𝑑 − 𝑥𝑖𝑑 ) (3.2)
normally distributed in [0,1], and 𝑝𝑖𝑑 and 𝑝𝑔𝑑 indicate the elements of pbest and
maximum velocity 𝑣𝑚𝑎𝑥 . The pseudocode and the flowchart of PSO are shown
The new velocity and positions will be updated using Eq. 3.1 and 3.2 respectively.
42
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
Start
Yes
Fitness <pid Renew pid and
position
No
Yes
pid <pgd Renew pgd
No
No Yes
Stop
End
condition?
sense receptors. The role of these sense receptors, also called chemoreceptors, is
to sense fragrance/smell [81]. In BOA, butterflies are the search agents that
perform optimization. Each butterfly emits fragrance with some intensity. This
43
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
means that the fragrance of a butterfly changes according to its current location
[80]. When a butterfly is able to sense fragrance from any other butterfly that is
larger than its fragrance, it will move toward the latter and this phase is called
global search. On the other side, when a butterfly cannot sense fragrance from
other butterflies that is larger than its local fragrance, it will move randomly and
this phase is called local search [82]. In BOA, the fragrance is defined as a
𝑓𝑖 = 𝑐𝐼 𝑎 (3.3)
two phases in BOA algorithm namely, local search phase and global search
phase. In global search phase, the butterfly moves one step toward the best
best solution found in the current stage, 𝑓𝑖 is the fragrance of 𝑖 𝑡ℎ butterfly, and 𝑟
44
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
where 𝑥𝑗𝑡 and 𝑥𝑘𝑡 are 𝑗𝑡ℎ and 𝑘 𝑡ℎ butterflies chosen randomly from the solution
space. Eq. (3.5) is considered a local random walk if and only if 𝑥𝑗𝑡 and 𝑥𝑘𝑡
belongs to the same sub-swarm and 𝑟 is a random number in[0, 1]. Search for
food and mating partner by butterflies can occur at both local and global scale;
common global search and intensive local search. The pseudocode and the flow
chart of the BOA algorithm are shown in Figures 3.4 and 3.5, respectively.
45
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
Start
Yes No
rand1 <p
Yes
Perform intensive exploitation rand2 <p
No
Update the position of all
butterflies Fitness Evaluation
No
Stop
condition?
Yes
End
46
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
mimics the social behaviors and flashing patterns of fireflies. FA depends on the
1) Fireflies are unisex which means that a firefly can get attracted to any
Thus, for any two flashing fireflies, the firefly with less brightness moves
toward the one with higher brightness. If there is no a brighter firefly than
47
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
where 𝑟𝑖𝑗 is the distance between the fireflies 𝑖 and 𝑗 that is calculated using the
Euclidean norm, the second term is due to the attraction, the third term is a
that includes random numbers. The pseudocode and the flow chart of the FA
end if
end for j
end for i
end while
48
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
Start
Yes
f(j) > f(i) Move firefly I toward firefly j
No
No
Stop
condition?
Yes
Start
in 2014. Grey wolf is a very dangerous creature which belongs to the Canidae
family. Grey wolves usually live in packs that consist of 5 to 12 wolves. Each
group has social dominance hierarchy: alpha, beta, and omega, in order. The
alphas are a male and female which represent the leaders of the group. The betas
are the second level of management hierarchy. The omegas are the final level in
49
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
fittest solution is referred to as the alpha (α). Consequently, the second and third
best solutions are Beta (β) and Delta (δ), respectively. The rest of candidate
solutions are Omega (ω) [28]. The mathematical model of the encircling
⃗ = |𝐶 . 𝑋𝑝 (𝑡) − 𝑋(𝑡)|
𝐷 (3.8)
⃗ = 2. r2 , A
where t indicates the current iteration, C ⃗ = 2a⃗. r1 − a⃗, X
⃗ m is the
position vector of the wolf, 𝑟1 and 𝑟2 are random vectors in [0, 1] and a linearly
the prey. During the optimization, the 𝜔 wolves update their positions around
⃗ 𝛼 = |𝐶 1. 𝑋𝛼 − 𝑋|,
𝐷
⃗ 𝛽 = |𝐶 2. 𝑋𝛽 − 𝑋|,
𝐷
⃗ 𝛿 = |𝐶 3. 𝑋𝛿 − 𝑋|
𝐷 (3.10)
⃗ 𝛼),
𝑋1 = 𝑋𝛼 − 𝐴1. (𝐷
⃗ 𝛽),
𝑋2 = 𝑋𝛽 − 𝐴2. (𝐷
⃗ 𝛿)
𝑋3 = 𝑋𝛿 − 𝐴3. (𝐷 (3.11)
50
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
⃗ 1+𝑋
𝑋 ⃗ 2+ 𝑋
⃗3
𝑋(𝑡 + 1) = (3.12)
3
in the search space [85]. The pseudocode and the flowchart of the GWO
51
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
Start
Initialize a, A, and C
Update a, A, and C
No
Stop
condition?
Yes
End
look like jellyfishes in texture and movement. The shape of a salp is shown in
Figure 3.10 (a). The water is pushed Salps bodies to move forward [86].
Generally, the biological researches about salps in its early stages because their
living environments are hardly accessible, and it is very difficult to keep them in
52
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
Salp Swarm Algorithm [87]. Salps compose a swarm in profound oceans which
is called Salp chain. This chain is illustrated in Figure 3.10 (b). This chain can
(a) (b)
Figure 3.10: (a) Individual salp. (b) Salps chain [29]
Originally, the salps population is divided into two groups to formulate the
mathematical model for salp chains: head and followers. The head position is at
the beginning of the chain while the rest of the chain is referred to as the
followers [89].
dimensional search area via considering the number of variables inside the
described as x will contains the position of all Salps. It is supposed too, in search
53
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
space, there is 'F' which is a food source as the target of the swarm. The
where 𝑥𝑗1 shows the position of the first Salp (leader) in the 𝑗th dimension, 𝐹𝑗 is
the position of the food source in the 𝑗th dimension, 𝑢𝑏𝑗 indicates the upper
bound of 𝑗th dimension, 𝑙𝑏𝑗 indicates the lower bound of jth dimension, 𝑐1 , 𝑐 2 ,
Eq. (3.13) shows that the leader only updates its position with respect to the
food source. The coefficient 𝑐1 is the most important parameter in SSA because
4𝑙 2
𝑐1 = 2𝑒 − ( 𝐿 ) (3.14)
where l is the current iteration and L is the maximum number of iterations. The
[0, 1]. In fact, they dictate if the next position in jth dimension should be towards
positive infinity or negative infinity as well as the step size. To update the
motion) [87]:
54
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
1
𝑥𝑗𝑖 = 𝑎 𝑡 2 + 𝑣0 𝑡 (3.15)
2
𝑣𝑓𝑖𝑛𝑎𝑙 𝑥 − 𝑥0
time, 𝑣0 is the initial speed, and 𝑎 = where 𝑣 = . Because the time
𝑣0 𝑡
where 𝑖 ≥ 2 and 𝑥𝑗𝑖 shows the position of 𝑖 th follower Salp in 𝑗th dimension.
Using equations (1) and (4), the Salp chains can be simulated. Figure 3.11 and
3.12 show the pseudocode and the flow chart of the SSA algorithm,
respectively.
Initialize the Salp population 𝑥𝑖 (𝑖 = 1, 2, … , 𝑛)considering 𝑢𝑏 and 𝑙𝑏
While (end condition is not satisfied)
Calculate the fitness of each search agent (salp)
F = the best search agent
Update 𝑐1 by Eq. 2
For each salp (𝑥𝑖 )
If (𝑖 == 1)
Update the position of the leading salp by Eq. 3.13
Else
Update the position of the follower salp by Eq. 3.16
End
Figure 2.13: The pseudocode of the SSA algorithm
End
Amend the salps based on the upper and lower bounds of variables
End
Return F
Figure 3.11: The pseudocode of the SSA algorithm
55
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
Start
Yes No
The current salp
is the leader
Amend the salps based on the upper and lower bounds of variables
No
Stop condition is
satisfied
Yes
End
3.9. Summary
In this chapter, the different types of localization schemes are briefly
metaheuristic algorithms that are used in the proposed work. In the next chapter,
56
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
a node localization scheme based on the salp swam algorithm is presented and
57
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
4.1. Introduction
WSN node localization problem is formulated using the single hop range-
coordinates (X, Y) with the aid of anchor nodes (position of known nodes)
coordinates (x, y). Anchor nodes are provided with a GPS device, so it has the
WSN are not equipped with GPS due to high cost. To measure the coordinates
within the communication range (R). Anchor nodes measure their position
and communicate their coordinates to their neighbors. For all iterations, the
59
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
node which settles at the end is termed as reference node and this node will
Step 3: Let (x, y) be the coordinates of the target node to be determined and
di be the distance between the target node and the ith anchor node.
𝑑𝑖 = √(𝑥 − 𝑥𝑖 )2 + (𝑦 − 𝑦𝑖 )2 (4.1)
formulated as:
2
𝑓(𝑥, 𝑦) = min( ∑𝑀 2 2
𝑖=1(√(𝑥 − 𝑥𝑖 ) + (𝑦 − 𝑦𝑖 ) ) ) (4.2)
where M is the anchor nodes within the transmission range (R) of the target
node.
Step 5: All target localized nodes (NL) is determined, the whole localization
coordinates node (xi, yi) and the actual node coordinates (Xi, Yi), for i = 1, 2,
. . ., NL.
1
𝐸𝐿 = ∑𝐿𝑖=1(√(𝑥𝑖 − 𝑋𝑖 )2 + (𝑦𝑖 − 𝑌𝑖 )2 ) (4.3)
𝑁𝐿
60
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
Step 6: Repeat the steps 2–5 until all unknown/target nodes get localized or
In this section, the proposed WSN localization approach that is employs the
salp swarm algorithm is evaluated under different scenarios, and its performance
is compared to four other swarm based algorithms (PSO, BOA, FA, and GWO)
Intel Core i7 CPU, 4GB RAM, and Windows7 operating system. The
Parameters Values
Sensor Nodes Varies on ∑6𝑖=1 𝑖 ∗ 2 5
Anchor nodes Varies on increment 𝑖 = 𝑖 + 5
Node transmission range (R) 30 m
Deployment area 100 m*100 m
Maximum number of iterations 100
For BOA, the sensory modality c is set 0.01, whereas the initial value of
power exponent a is set to 0.1 [43]. For PSO, initial values of ω = 0.7 and c1 =
[43]. For FA, the randomization parameter α is set to 0.25, the absorption
For GWO, the parameter a linearly decreases in the interval of [2 to 0] and the C
61
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
using Eq. 3.14, whereas c2 = 0.7 and c3 = 0.3 and c2 , c3 are random numbers
destination nodes (M) are randomly configured during the construction of the
deployment area. The deployment area includes three types of nodes: anchor
nodes whose known position, target nodes whose unknown position, and
localized nodes whose positions are already estimated. In this section, the
62
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
63
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
Figure 4.1: Node localization using different numbers of target nodes and anchor nodes
number of localized nodes. The obtained results of the different algorithms are
64
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
noticed that, for all the localization algorithms, increasing the number of
iterations increases both of the number of localized nodes and the computing
time while reduces the localization error. This notice is rational because
which requires longer computation time. On the other side, increasing the
number of iterations means that the chance to find a better solution get bigger;
hence, the number of localized nodes get larger and the value of localization
65
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
error get smaller. For better results analysis, the experimental results are
Based on Table 4.3, regarding the Mean Localization Error (EL), there is no
clear pattern that can be detected to represent the relationship between this
performance metric and the number of target nodes and anchor nodes. However,
it is noticed that SSA has the best results regarding this performance metric
compared to PSO, BOA, FA, and GWO, particularly, when the numbers of
target nodes and anchor nodes are increased. Regarding the computing time, it is
noticed that increasing the number of target nodes and anchor nodes increase the
computing time for all localization algorithms. However, once again, SSA has
the best computing time compared to PSO, BOA, FA, and GWO. Finally,
regarding the number of localized nodes (NL), it is noticed that SSA has the best
SSA has inferior EL when the percentage of (number of anchor nodes/ number
of target nodes) becomes larger such as (10/25) in the first case in Table 4.3.
66
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
That is because the localization accuracy increases when the anchor density
0.9
Mean Localization Error (m)
0.8
0.7
0.6
PSO
0.5 BOA
FA
0.4 GWO
SSA
0.3
0.2
0.1
0
25 -10 50 -15 75 - 20 100 -25 125 - 30 150 - 35
(Number of Target Nodes - Number of Anchors)
Figure 4.2: The localization error of the different localization algorithms in different WSN deployments
67
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
10
9
8
COMPUTING TIME (S)
7
6
5
4
3
2
1
0
25 -10 50 -15 75 - 20 100 -25 125 - 30 150 - 35
Figure 4.3: The computing time of the different localization algorithms in different WSN deployments
150 - 35
(NUMBER OF TARGET NODES - NUMBER OF ANCHORS)
125 - 30
100 -25
75 - 20
50 -15
25 -10
Figure 4.4: The number of localized nodes of the different localization algorithms in different WSN deployments
68
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
4.4. Summary
to the conducted experiments. The proposed work has employed the salp swarm
algorithm to localize the unknown nodes in wireless sensor networks for the first
other well-known metaheuristic algorithms including PSO, BOA, FA, and GWO
contains the conclusion of the thesis and presents a set of recommendations for
69
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
5.1. Conclusion
Many applications that deploy WNS cannot perform its functions properly
unless the locations of the sensor node used to collect the data are known. These
WSNs. In this thesis, a node localization scheme has been proposed based on a
novel bio-inspired algorithm call Salp Swarm Algorithm (SSA) which handled
using different numbers of target nodes and anchor nodes. Moreover, the
butterfly optimization algorithm (BOA), firefly algorithm (FA), and grey wolf
number of localized nodes. The obtained simulation results have proved the
71
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
The proposed work can be extended in the future through following one or
the network is sparse and the set of reference nodes are almost
collinear. In this case, there is a possibility that the target node can be
node localization.
72
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
process in WSNs.
73
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
Bibliography
Publications:
1. Kanoosh, H. M., Houssein, E. H., & Selim, M. M. (2019). Salp Swarm Algorithm for
Node Localization in Wireless Sensor Networks. Journal of Computer Networks and
Communications, 2019.
75
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
Bibliography
76
Bibliography
15. Sharma, S. (2015, May). Target tracking technique in wireless sensor network.
In International Conference on Computing, Communication & Automation (pp. 486-
491). IEEE.
16. Rashid, B., & Rehmani, M. H. (2016). Applications of wireless sensor networks for urban
areas: A survey. Journal of network and computer applications, 60, 192-219.
17. Butun, I., Morgera, S. D., & Sankar, R. (2013). A survey of intrusion detection systems
in wireless sensor networks. IEEE communications surveys & tutorials, 16(1), 266-282.
18. BoussaïD, I., Lepagnot, J., & Siarry, P. (2013). A survey on optimization
metaheuristics. Information sciences, 237, 82-117.
19. Baum, E. B. (1986, August). Towards practical ‘neural’computation for combinatorial
optimization problems. In AIP Conference Proceedings (Vol. 151, No. 1, pp. 53-58).
AIP.
20. Holland, J. H. (1992). Adaptation in natural and artificial systems: an introductory
analysis with applications to biology, control, and artificial intelligence. MIT press.
21. Rechenberg, I. (1994). Evolutionsstrategie: Optimierung technischer Systeme nach
Prinzipien der biologischen Evolution. frommann-holzbog, Stuttgart, 1973. Step-Size
Adaptation Based on Non-Local Use of Selection Information. In Parallel Problem
Solving from Nature (PPSN3).
22. Fogel, L. J., Owens, A. J., & Walsh, M. J. (1966). Artificial intelligence through
simulated evolution.
23. Koza, J. R. (1992). Genetic Programming: On the Programming of Computers by Means
of Natural Selection (Complex Adaptive Systems). A Bradford Book, 1, 18.
24. Zhou, H., Li, D. M., Shao, S. H., & Xu, C. (2007, September). A novel intelligent
estimation algorithm in WSN location based on free search. In 2007 International
Conference on Wireless Communications, Networking and Mobile Computing (pp. 2629-
2632). IEEE.
25. Low, K. S., Nguyen, H. A., & Guo, H. (2008, June). A particle swarm optimization
approach for the localization of a wireless sensor network. In 2008 IEEE international
symposium on industrial electronics (pp. 1820-1825). IEEE.
26. Manjarres, D., Del Ser, J., Gil-Lopez, S., Vecchio, M., Landa-Torres, I., & Lopez-
Valcarce, R. (2011, November). On the application of a hybrid harmony search algorithm
to node localization in anchor-based wireless sensor networks. In 2011 11th International
Conference on Intelligent Systems Design and Applications (pp. 1014-1019). IEEE.
27. Li, M., Xiong, W., & Liang, Q. (2012, September). An improved abc-based node
localization algorithm for wireless sensor network. In 2012 8th International Conference
on Wireless Communications, Networking and Mobile Computing (pp. 1-4). IEEE.
28. Tamizharasi, A., Arthi, R., & Murugan, K. (2013, July). Bio-inspired algorithm for
optimizing the localization of wireless sensor networks. In 2013 Fourth International
Conference on Computing, Communications and Networking Technologies
(ICCCNT) (pp. 1-5). IEEE.
77
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
29. Tang, C., Liu, R., & Ni, J. (2013). A novel wireless sensor network localization approach:
localization based on plant growth simulation algorithm. Elektronika ir
Elektrotechnika, 19(8), 97-100.
30. Jegede, O. D., & Ferens, K. (2013). A genetic algorithm for node localization in wireless
sensor networks. In Proceedings of the International Conference on Genetic and
Evolutionary Methods (GEM) (p. 1). The Steering Committee of The World Congress in
Computer Science, Computer Engineering and Applied Computing (WorldComp).
31. Goyal, S., & Patterh, M. S. (2014). Wireless sensor network localization based on cuckoo
search algorithm. Wireless personal communications, 79(1), 223-234.
32. Dan, L., & Xian-Bin, W. (2014). An improved PSO algorithm for distributed localization
in wireless sensor networks. International Journal of Distributed Sensor Networks (2015).
https://doi.org/ 10.1155/2015/970272.
33. Krishnaprabha, R., & Gopakumar, A. (2014, October). Performance of gravitational
search algorithm in wireless sensor network localization. In 2014 IEEE National
Conference on Communication, Signal Processing and Networking (NCCSN) (pp. 1-6).
IEEE.
34. Peng, B., & Li, L. (2015). An improved localization algorithm based on genetic algorithm
in wireless sensor networks. Cognitive Neurodynamics, 9(2), 249-256.
35. Sai, V. O., Shieh, C. S., Nguyen, T. T., Lin, Y. C., Horng, M. F., & Le, Q. D. (2015,
November). Parallel firefly algorithm for localization algorithm in wireless sensor
network. In 2015 Third International Conference on Robot, Vision and Signal Processing
(RVSP) (pp. 300-305). IEEE.
36. Sivakumar, S., & Venkatesan, R. (2015). Meta-heuristic approaches for minimizing error
in localization of wireless sensor networks. Applied Soft Computing, 36, 506-518.
37. Sun, Z., Tao, L., Wang, X., & Zhou, Z. (2015). Localization algorithm in wireless sensor
networks based on multiobjective particle swarm optimization. International Journal of
Distributed Sensor Networks, 11(8), 716291.
38. Arsic, A., Tuba, M., & Jordanski, M. (2016, July). Fireworks algorithm applied to
wireless sensor networks localization problem. In 2016 IEEE Congress on Evolutionary
Computation (CEC) (pp. 4038-4044). IEEE.
39. Shieh, C. S., Sai, V. O., Lin, Y. C., Lee, T. F., Nguyen, T. T., & Le, Q. D. (2016, July).
Improved node localization for WSN using heuristic optimization approaches. In 2016
International Conference on Networking and Network Applications (NaNA)(pp. 95-98).
IEEE.
40. Cheng, J., & Xia, L. (2016). An effective Cuckoo search algorithm for node localization
in wireless sensor network. Sensors, 16(9), 1390.
41. Daely, P. T., & Shin, S. Y. (2016, July). Range based wireless node localization using
dragonfly algorithm. In 2016 eighth international conference on ubiquitous and future
networks (ICUFN) (pp. 1012-1015). IEEE.
42. Nguyen, T. T., Pan, J. S., Chu, S. C., Roddick, J. F., & Dao, T. K. (2016). Optimization
localization in wireless sensor network based on multi-objective firefly algorithm. Journal
of Network Intelligence, 1(4), 130-138.
78
Bibliography
43. Arora, S., & Singh, S. (2017). Node localization in wireless sensor networks using
butterfly optimization algorithm. Arabian Journal for Science and Engineering, 42(8),
3325-3335.
44. Rajakumar, R., Amudhavel, J., Dhavachelvan, P., & Vengattaraman, T. (2017). GWO-
LPWSN: Grey wolf optimization algorithm for node localization problem in wireless
sensor networks. Journal of Computer Networks and Communications, 2017.
45. Sujatha, S. R., & Siddappa, M. (2017). Node localization method for wireless sensor
networks based on hybrid optimization of particle swarm optimization and differential
evolution. IOSR of Computer Engineering, 19(2), 07-12.
46. Kaur, R., & Arora, S. (2017). Nature Inspired Range Based Wireless Sensor Node
Localization Algorithms. International Journal of Interactive Multimedia & Artificial
Intelligence, 4(6).
47. Srideviponmalar, P., Kumar, V. J. S., & Harikrishnan, R. (2018). Hybrid Genetic
Algorithm–Differential Evolution Approach for Localization in WSN. In Intelligent
Engineering Informatics (pp. 263-271). Springer, Singapore.
48. Liu, W., Huang, Y., Zong, X., Shi, H., Ye, Z., & Wei, S. (2018, September). Application
of lightning search algorithm in localization of Wireless Sensor Networks. In 2018 IEEE
4th International Symposium on Wireless Systems within the International Conferences
on Intelligent Data Acquisition and Advanced Computing Systems (IDAACS-SWS) (pp.
57-61). IEEE.
49. Rauniyar, A., Engelstad, P., & Moen, J. (2018, June). A New Distributed Localization
Algorithm Using Social Learning Based Particle Swarm Optimization for Internet of
Things. In 2018 IEEE 87th Vehicular Technology Conference (VTC Spring) (pp. 1-7).
IEEE.
50. Mihoubi, M., Rahmoun, A., Lorenz, P., & Lasla, N. (2018). An effective Bat algorithm
for node localization in distributed wireless sensor network. Security and Privacy, 1(1),
e7.
51. Tuba, E., Tuba, M., & Beko, M. (2018). Two stage wireless sensor node localization
using firefly algorithm. In Smart trends in systems, security and sustainability (pp. 113-
120). Springer, Singapore.
52. Hussain, M. A., & kyung Sup, K. (2009, February). WSN research activities for military
application. In 2009 11th International Conference on Advanced Communication
Technology (Vol. 1, pp. 271-274). IEEE.
53. Đurišić, M. P., Tafa, Z., Dimić, G., & Milutinović, V. (2012, June). A survey of military
applications of wireless sensor networks. In 2012 Mediterranean conference on
embedded computing (MECO) (pp. 196-199). IEEE.
54. Maurer, U., Rowe, A., Smailagic, A., & Siewiorek, D. P. (2006, April). eWatch: A
Wearable Sensor and Notification Platform. In BSN (Vol. 6, pp. 142-145).
55. Lee, H., Wu, C., & Aghajan, H. (2011). Vision-based user-centric light control for smart
environments. Pervasive and Mobile Computing, 7(2), 223-240.
79
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
56. Bangali, J., & Shaligram, A. (2013). Energy efficient smart home based on wireless
sensor network using labview. American Journal of Engineering Research (AJER), 2(12),
409-413.
57. Wang, X., Liu, Y., Yang, Z., Lu, K., & Luo, J. (2013). Robust component-based
localizationin sparse networks. IEEE Transactions on Parallel and Distributed
Systems, 25(5), 1317-1327.
58. Chowdhury, T. J., Elkin, C., Devabhaktuni, V., Rawat, D. B., & Oluoch, J. (2016).
Advances on localization techniques for wireless sensor networks: A survey. Computer
Networks, 110, 284-305.
59. Savvides, A., Park, H., & Srivastava, M. B. (2002, September). The bits and flops of the
n-hop multilateration primitive for node localization problems. In Proceedings of the 1st
ACM international workshop on Wireless sensor networks and applications (pp. 112-
121). ACM.
60. Shang, Y., & Ruml, W. (2004, March). Improved MDS-based localization. In IEEE
INFOCOM 2004 (Vol. 4, pp. 2640-2651). IEEE.
61. Fang, J., Cao, M., Morse, A. S., & Anderson, B. D. O. (2006, December). Localization of
sensor networks using sweeps. In Proceedings of the 45th IEEE Conference on Decision
and Control (pp. 4645-4650). IEEE.
62. Goldenberg, D. K., Bihler, P., Cao, M., Fang, J., Anderson, B., Morse, A. S., & Yang, Y.
R. (2006, September). Localization in sparse networks using sweeps. In Proceedings of
the 12th annual international conference on Mobile computing and networking (pp. 110-
121). ACM.
63. Savarese, C., Rabaey, J. M., & Beutel, J. (2001). Location in distributed ad-hoc wireless
sensor networks. In 2001 IEEE international conference on acoustics, speech, and signal
processing. proceedings (Cat. No. 01CH37221) (Vol. 4, pp. 2037-2040). IEEE.
64. Liu, J., Zhang, Y., & Zhao, F. (2006, May). Robust distributed node localization with
error management. In Proceedings of the 7th ACM international symposium on Mobile
ad hoc networking and computing (pp. 250-261). ACM.
65. Tian, Y., Tang, Z., & Yu, Y. (2013). Third-order channel propagation model-based
indoor adaptive localization algorithm for wireless sensor networks. IEEE Antennas and
Wireless Propagation Letters, 12, 1578-1581.
66. Bahl, P., Padmanabhan, V. N., Bahl, V., & Padmanabhan, V. (2000). RADAR: An in-
building RF-based user location and tracking system.
67. Wen, F., & Liang, C. (2014). Fine-grained indoor localization using single access point
with multiple antennas. IEEE Sensors Journal, 15(3), 1538-1544.
68. Wang, B., Zhou, S., Liu, W., & Mo, Y. (2014). Indoor localization based on curve fitting
and location search using received signal strength. IEEE transactions on industrial
electronics, 62(1), 572-582.
69. Arias-de-Reyna, E., & Djurić, P. M. (2013). Indoor localization with range-based
measurements and little prior information. IEEE Sensors Journal, 13(5), 1979-1987.
70. Haque, I. T., & Assi, C. (2013). Profiling-based indoor localization schemes. IEEE
Systems Journal, 9(1), 76-85.
80
Bibliography
71. Wu, B. F., & Jen, C. L. (2014). Particle-filter-based radio localization for mobile robots
in the environments with low-density WLAN APs. IEEE Transactions on Industrial
Electronics, 61(12), 6860-6870.
72. Mao, G., Fidan, B., & Anderson, B. D. (2007). Wireless sensor network localization
techniques. Computer networks, 51(10), 2529-2553.
73. Merrill, W., Girod, L., Schiffer, B., McIntire, D., Rava, G., Sohrabi, K., & Kaiser, W.
(2005). Defense systems: self healing land mines. Wireless Sensor Networks: A Systems
Perspective.
74. Chaczko, Z., & Ahmad, F. (2005, July). Wireless sensor network based system for fire
endangered areas. In Third International Conference on Information Technology and
Applications (ICITA'05) (Vol. 2, pp. 203-207). IEEE.
75. Kafi, M. A., Challal, Y., Djenouri, D., Doudou, M., Bouabdallah, A., & Badache, N.
(2013). A study of wireless sensor networks for urban traffic monitoring: applications and
architectures. Procedia computer science, 19, 617-626.
76. Derrac, J., García, S., Molina, D., & Herrera, F. (2011). A practical tutorial on the use of
nonparametric statistical tests as a methodology for comparing evolutionary and swarm
intelligence algorithms. Swarm and Evolutionary Computation, 1(1), 3-18.
77. Abraham, A., Das, S., & Roy, S. (2008). Swarm intelligence algorithms for data
clustering. In Soft computing for knowledge discovery and data mining (pp. 279-313).
Springer, Boston, MA.
78. Xue, B., Zhang, M., & Browne, W. N. (2012). Particle swarm optimization for feature
selection in classification: A multi-objective approach. IEEE transactions on
cybernetics, 43(6), 1656-1671.
79. Ho, S. L., Yang, S., Ni, G., Lo, E. W., & Wong, H. C. C. (2005). A particle swarm
optimization-based method for multiobjective design optimizations. IEEE transactions on
magnetics, 41(5), 1756-1759.
80. Arora, S., & Singh, S. (2015, September). Butterfly algorithm with levy flights for global
optimization. In 2015 International conference on signal processing, computing and
control (ISPCC) (pp. 220-224). IEEE.
81. Arora, S., & Singh, S. (2017). An improved butterfly optimization algorithm with
chaos. Journal of Intelligent & Fuzzy Systems, 32(1), 1079-1088.
82. Blair, R. B., & Launer, A. E. (1997). Butterfly diversity and human land use: Species
assemblages along an urban grandient. Biological conservation, 80(1), 113-125.
83. Yang, X. S., & He, X. (2013). Firefly algorithm: recent advances and applications. arXiv
preprint arXiv:1308.3898.
84. Yang, X. S. (2009, October). Firefly algorithms for multimodal optimization.
In International symposium on stochastic algorithms (pp. 169-178). Springer, Berlin,
Heidelberg.
85. Mirjalili, S., Mirjalili, S. M., & Lewis, A. (2014). Grey wolf optimizer. Advances in
engineering software, 69, 46-61.
86. Madin, L. P. (1990). Aspects of jet propulsion in salps. Canadian Journal of
Zoology, 68(4), 765-777.
81
Wireless Sensor Networks Localization Based on Meta-heuristic Algorithms
87. Mirjalili, S., Gandomi, A. H., Mirjalili, S. Z., Saremi, S., Faris, H., & Mirjalili, S. M.
(2017). Salp Swarm Algorithm: A bio-inspired optimizer for engineering design
problems. Advances in Engineering Software, 114, 163-191.
88. Anderson, P. A. V., & Bone, Q. (1980). Communication between individuals in salp
chains. II. Physiology. Proceedings of the Royal Society of London. Series B. Biological
Sciences, 210(1181), 559-574.
89. Ibrahim, H. T., Mazher, W. J., Ucan, O. N., & Bayat, O. (2017). Feature selection using
salp swarm algorithm for real biomedical datasets. International journal of computer
science and network security, 12, 13.
82
تحديد مواقع شبكات االستشعار الالسلكية باستخدام خوارزميات التحسين االرشادية
هيكلية الرسالة
تتكونالرسالةمنخمسةفصول :
الفصل الثانى :في هذا الفصل نعرض خلفية المفاهيم لهذه الرسالة ,والتي تشمل مبادئ
شبكات اإلستشعار الالسلكية وتطبيقاتها ,ويعرض أيضا شرح ألنواع الخوارزميات
) (Metaheuristic Algorithmsالتى يمكناستخدامهالحلمشكالتالتحسين,وينتهى
بعرضمجموعةمنالجهودالبحثيةالتىبذلتفىهذاالمجال .
الفصل الثالث :فى هذا الفصل يتم عرض المفاهيم الخاصة بتوطين العقد فى شبكات
اإلستشعار الالسلكية بما فيها األنواع المختلفة للتوطين .أيضا يتم شرح خمس من
الخوارزمياتالمستخدمةفىالتجاربلتوطينالعقدفىشبكاتاإلستشعارالالسلكية .
الفصل الخامس :وفيه قمت بعرض ما تم إنجازه في البحث ,كما قدمت توصيات لعمل
أبحاثمستقبليةفيمجاالتمتعلقةبموضوعالرسالة .
أ
تحديد مواقع شبكات االستشعار الالسلكية باستخدام خوارزميات التحسين االرشادية
ملخص الرسالة
دورا حيويًا في العديد من تطبيقات
في الوقت الحاضر ،تلعب شبكات االستشعار الالسلكية (ً )WSNs
الحياة الواقعية مثل الرعاية الصحية والتطبيقات العسكرية ومراقبة حركة المرور والمراقبة البيئية .في
العديد من الحاالت ،يتم نشر نقاط اإلستشعار بشكل عشوائي فى شبكات االستشعار الالسلكية.
ومع ذلك ،ال يمكن للعديد من هذه التطبيقات أداء وظيفتها بشكل صحيح دون معرفة الموقع الدقيق لعقد
االستشعار المستخدمة في جمع البيانات .لذلك ،توطين العقدة ) (Node localizationالدقيق مهم للغاية
في شبكات اإلستشعار الالسلكية .توطين العقدة يعني تقدير مواقع العقد غير المعروفة بمساعدة بعض
في هذه األطروحة ،يُقترح مخطط تعريب العقدة استنادًا إلى خوارزمية حديثة تسمى (Salp Swarm
)Algorithmوالتي تتم فيها معالجة مشكلة توطين كمشكلة تحسين .تم تنفيذ الخوارزمية المقترحة
والتحقق من صحتها فى حاالت مختلفة لنشر عقد شبكات االستشعار الالسلكية باستخدام أعداد مختلفة
من العقد المستهدفة وعقد المراس .عالوة على ذلك ،تم تقييم الخوارزمية المقترحة ومقارنتها بأربع
خوارزميات تحسين معروفة ،وهي خوارزمية تحسين سرب الجسيمات ( ، )PSOخوارزمية تحسين
الفراشة ( ، )BOAخوارزمية اليراع ( ، )FAوخوارزمية الذئب الرمادي ( )GWOمن حيث دقة تحديد
أماكن العقد ووقت الحوسبة وعدد العقد التى تم تحديد أماكنهم .أثبتت نتائج المحاكاة التي تم الحصول
عليها تفوق الخوارزمية المقترحة مقارنة بخوارزميات التوطين األخرى فيما يتعلق بمقاييس األداء
المختلفة.
ب
تحديد مواقع شبكات االستشعار الالسلكية باستخدام خوارزميات التحسين االرشادية
جهة منح الدرجة العلمية :قسم علوم الحاسوب -كلية الرافدين الجامعة
جهة منح الدرجة العلمية :قسم علوم الحاسوب -كلية علوم الحاسوب والرياضيات
جامعة الموصل
ج
كلية الحاسبات والذكاء األصطناعي جامعة بنها
قسم علوم الحاسب
رسالة مقدمة إلى كلية الحاسبات والذكاء األصطناعي -جامعة بنها الستكمال متطلبات
الحصول على درجة الماجستير فى الحاسبات والمعلومات في "علوم الحاسب "
مقدمة من الباحث
حذيفة محمد كنوش الجبوري
قسم علوم الحاسب
كلية الحاسبات والذكاء األصطناعي
جامعة بنها
مصر
إشراف
2019م