4.8 6.

Article

A UAV-Swarm-Communication
Model Using a Machine-Learning
Approach for Search-and-Rescue
Applications

Hisham Khalil, Saeed Ur Rahman , Inam Ullah, Inayat Khan, Abdulaziz Jarallah Alghadhban,
Mosleh Hmoud Al-Adhaileh , Gauhar Ali and Mohammed ElAffendi

Special Issue
Recent Advances in Unmanned Aerial Vehicles for Next Generation Wireless Communications
Networks
Edited by
Dr. Wali Ullah Khan, Dr. Khaled Rabie, Dr. Xingwang Li and Dr. Dinh-Thuan Do

https://doi.org/10.3390/drones6120372
 drones

Article
A UAV-Swarm-Communication Model Using a
Machine-Learning Approach for Search-and-Rescue
Applications
Hisham Khalil 1, *, Saeed Ur Rahman 2 , Inam Ullah 3 , Inayat Khan 4 , Abdulaziz Jarallah Alghadhban 5 ,
Mosleh Hmoud Al-Adhaileh 6 , Gauhar Ali 7, * and Mohammed ElAffendi 7

1 Department of Technology, University of Lahore, Lahore 54000, Pakistan

2 School of Electronic Engineering, Xidian University, Xi’an 710071, China
3 BK21 Chungbuk Information Technology Education and Research Center, Chungbuk National University,
Cheongju 28644, Republic of Korea
4 Department of Computer Science, University of Engineering & Technology Mardan, Mardan 61000, Pakistan
5 Department of Software Engineering, College of Computer Science and Information, King Suad University,
Riyadh 11451, Saudi Arabia
6 Deanship of E-Learning and Distance Education, King Faisal University, P.O. Box 400,
Al-Ahsa 31982, Saudi Arabia
7 EIAS Data Science and Block Chain Lab., College of Computer and Information Sciences, Prince Sultan
University, Riyadh 11586, Saudi Arabia
* Correspondence: [email protected] (H.K.); [email protected] (G.A.)

Abstract: This paper presents a UAV-swarm-communication model using a machine-learning ap-



proach for search-and-rescue applications. Firstly, regarding the communication of UAVs, the receive


signal strength (RSS) and power loss have been modeled using random forest regression, and the
Citation: Khalil, H.; Rahman, S.U.;
mathematical representation of the channel matrix has also been discussed. The second part consisted
Ullah, I.; Khan, I.; Alghadhban, A.j.;
of swarm control modeling of UAVs; however, a dataset for five types of triangular swarm formations
Al-Adhaileh, M.H.; Ali, G.; ElAffendi,
was generated, and K-means clustering was applied to predict the cluster. In order to obtain the
M. A UAV-Swarm-Communication
Model Using a Machine-Learning
correct swarm formation, the dendrogram of all types was investigated. Finally, the heat map and
Approach for Search-and-Rescue contour were plotted for all kinds of swarm clusters. Furthermore, it was observed that the RSS of
Applications. Drones 2022, 6, 372. proposed swarms had good agreement with swarm distances.
https://doi.org/10.3390/
drones6120372 Keywords: path-loss; artificial intelligence/machine learning for UAV communications; clustering;
UAV swarm control; integration of UAV communications with space and terrestrial networks;
Academic Editor: Kamesh
emergency services
Namuduri

Received: 30 October 2022

Accepted: 18 November 2022
Published: 23 November 2022 1. Introduction
Publisher’s Note: MDPI stays neutral The applications of unmanned aerial vehicles (UAVs) are increasing in different fields.
with regard to jurisdictional claims in They can be utilized for emergency services, life-saving missions and information-gathering
published maps and institutional affil- systems. In order to ensure the reliability of a specific mission, a robust wireless commu-
iations. nication channel is required. A number of technical committees have defined the basic
standards for UAV radio communication links. Similarly, a regulatory body named the
Radio Technical Commission for Aeronautics (RTCA) has standardized the minimum set
of parameters for stable UAV operation [1]. Moreover, for the safe induction of UAVs in the
Copyright: © 2022 by the authors.
airspace, another technical committee has developed the standards [2].
Licensee MDPI, Basel, Switzerland.
Generally, the UAVs are divided into three categories, such as rotary-wing, fixed-wing
This article is an open access article
and vertical-takeoff ones. However, each type has its advantages and disadvantages in
distributed under the terms and
conditions of the Creative Commons
terms of hovering capabilities, take-off and landing, endurance length, loading capacity
Attribution (CC BY) license (https://
and operating radius. Specifically, in emergency response scenarios, the UAV relaying
creativecommons.org/licenses/by/
communications, emergency lighting and other rescue support can be used to collect on-site
4.0/). data and enable communication relay, night illumination and other support [3]. In the case

Drones 2022, 6, 372. https://doi.org/10.3390/drones6120372 https://www.mdpi.com/journal/drones

Drones 2022, 6, 372 2 of 18

of UAV swarms, a collection or group of UAVs carry out activities in a self-organized and
self-adaptive manner to accomplish a task, which is the current trend in the developments of
UAV technology. The self-organized part indicates that through local interactions, the UAV
swarm spontaneously creates a totally decentralized or hybrid mode [4].
In the literature, numerous networking techniques and routing protocols have been
developed and examined to improve networking performance. In order to guarantee
the stability and dependability of UAVs, many researchers have already made significant
progress in task allocation and cooperative execution. The idea of an avionics cloud based
on a UAV swarm was proposed by [5], wherein the cloud model for avionics system
integration was discussed. Regarding the communication mechanism of an intelligent UAV
swarm, UAVs are highly mobile communication nodes that may function as transmitters
or relays simultaneously. However, in the presence of interference, UAV swarms require
multi-channel access and networking, and the omnidirectional antenna often employed for
inter-UAV coordination may degrade spectrum efficiency [6]. Additionally, the cognitive-
radio, broad-spectrum sensing capacity set up the learning process for reinforcement
learning and produced better policy sets than conventional Q-Learning [7]. A real-time
reinforcement learning system based on Q-Learning that utilized broadband spectrum
sensing and greedy policy to improve real-time policy was presented by [8]. Additionally,
multiple machine-learning types, their utilization and specific algorithms are provided in
the alluvial map in Figure 1.

Algorithm
CNN
Hopfield
Machine Learning Type Utilization AQL
K-means
GA
Clustering
Superised PSO
DP
NDP
Swarm DQL
Reinforcement Kalman
swarm laws
RNN
Deep ANN
Unsuperised Resource Management
Federated learning
APC clustering
Finite difference
Deep RL
Power cognition
Multi-Agent RL

Figure 1. Alluvial map for machine-learning model types, utilization and algorithms.
Loading [a11y]/accessibility-menu.js
A detailed review paper related to swarm intelligence algorithms was published,
where a number of optimization techniques are discussed [9]. The reallocation in emergent
scenarios has been reported by [10]. In order to solve the problem of reallocation, Jun
Tang et al. utilized the clustering of UAVs based on fuzzy C-means (FCM), along with
ant colony optimization (ACO). The clustering head of a UAV swarm has been discussed
by [11], wherein effective communication management has been addressed. Addition-
ally, a multistage cluster of remotely located UAV swarm has also been addressed by
Rang Ruan et al. [12]. The UAV swarm coordination protocol for supporting the assigned
mission was reported by [13]. The problem of edge intelligence for UAV swarms has been
discussed in [14]. Similarly, an adaptive weighted clustering algorithm is presented by [15].
Yongkun summarized the trends and application areas of UAV swarms; he also discussed
the layer-based control of swarms [16]. Another paper was found related to UAVs’ collision
avoidance, wherein, the author has discussed new approaches [17]. In addition, the uses of
UAV swarms for modern applications are reported in [18]. Moreover, the survey paper re-
Drones 2022, 6, 372 3 of 18

lated to remotely piloted aircraft systems (RPAS) is presented by [19]. Thereby, the research
gap of communication models using machine learning was identified.
In this paper, a swarm of UAVs for rescue applications is discussed, as shown in
Figure 2. The main objective of this work is to maximize the effectiveness of search and
rescue activities during emergency. Furthermore, the UAV swarm can also be considered
as a potential candidate for an emergency communication network. The Section 2, we
present the machine-learning model for UAV communication based on the path-loss profile.
The wireless channel matrix for unit swarm UAV is presented along with UAV cluster power.
Furthermore, Section 3 describes the 2D swarm-control model with relative velocities υix (t)
y
and υi (t) of UAVs. In Section 4, the generation of the cluster’s dataset is presented, based
on multiple triangular swarm formation techniques. However, in Section 5, we present
the application of K-means clustering to predict the swarm cluster’s formation, along with
deprograms of UAVs. Finally, the prediction of received signal strength (RSS) based on
UAVs’ reallocation in the cluster (swarm) is presented in a heat map and contour plot.

House fire

Master
Slave
Fire area identified

Road accident

Flood
Wild fire

Figure 2. UAV master-and-slave configuration to operate in emergency scenarios such as wild fires,
floods and road accidents.

2. Path Loss Profile Additionally, Modeling for UAV Swarm

The section describes the UAV’s air-to-air link for swarm UAVs, whereas the commu-
nication channel is considered a line of sight (LOS), as shown in Figure 2. The Doppler
frequency drift is taken as a dominant effect in the aerial link between the swarm of UAVs,
and the effects increase with the moving speed of the swarm. Additionally, the Doppler
effect can also be observed through a large-scale fading model, as shown below [20].
  α0
λ0
RSS(dB) = Pt + GU AV1 + GU AV2 + 10 log10 (1)
4πd0
In Equation (1), the received signal strength is RSS, Pt is taken as transmitted power
and λ0 is the wavelength. The distance between the UAVs is d0 , and the antenna gains of
UAVs are GU AV1 and GU AV2 . Referring to Equation (1), the Pt and distance d0 are constant
for all swarm elements. The RSS vs. d0 is plotted and shown in the Figure 3 [21]. However,
there is a need to improve the gain of the antenna array in order to receive the Pr from
other UAVs. On the other hand, the relative velocities of swarm elements are assumed to
be zero for the simplicity of the model. According to the reference [22], the Doppler effect
of moving UAVs can be shown as below.

fc + δ f
   
d δh
PL (dB) = PL (d0 ) + 10αo log10 − log10 + C p + 10x log10 +ς (2)
d0 hopt fc

where frequency-dependent path-loss is represented by x and δ f is considered as frequency

drift [23]. One can understand that the aforementioned formula does not take antenna
Drones 2022, 6, 372 4 of 18

gain into account. During the flight of the swarm, the path-loss is calculated through [24].
Similarly, the power loss (PL) and RSS vs. d0 are shown in Figure 3.

25 80
RSS (dB)
Dynamic PL (dB)
30 85

35 90
RSS (dB)

PL (dB)
40 95
45 100
50 105

0 200 400 600 800 1000

Distance d0(m)
Figure 3. Channel characteristics of UAV at h = 500 m.

The wireless channels (small-scale fading-model) are also taken into consideration
to reflect the influences of the multi-path components while assessing the effectiveness of
the deployed antenna design which was previously stated. Since the 3GPP/ITU model is
the foundation for the 3D channel model created in [24,25], it is taken into consideration.
The model provides information on the received multipath components such as ampli-
tude, phase, time delay, angle of arrival (AoA) and angle of departure (AoD) in elevation
and azimuth domains. As a result, the wireless channel matrix may be modeled using
Equation (3). Table 1 provides a detailed list of the variables used in the equation below.

√ M T " vv √ vh
#
Etx0,s,Vi ((θi , φi )n,m,AOA ) e jΦn,m κn,m e jΦn,m

Gu,s,n (t0 ) = Pn ∑ Etx0,s,Hi ((θi , φi )n,m,AOA ) √ hv
κn,m e jΦn,m
hh
e jΦn,m
m =1
T (3)
Erx0,u,Vi ((θi , φi )n,m,AOD )

e j̟tx e j̟rx e2jπυn,m t
Erx0,u,Hi ((θi , φi )n,m,AOD )

Table 1. Variables used in the channel matrix equation.

Parameters Description
Pn Cluster power
H , EH
ERx,i Horizontal polarization of antenna
Tx,j
V , EV
ERx,i Vertical polarization of antenna
Tx,j
VV,HH Received co-polarized signal
VH,HV Received cross-polarized signal
ΦVV VH
n,m , Φn,m Initial phases of a ray m in cluster n
HV , Φ HH
Φn,m Initial phases of a ray m in cluster n
n,m
ψn,m , ψn,m Tx and Rx antenna elements unit vectors
rs , ru Spatial Coordinate of Tx and Rx MIMO
λ0 wavelength of the carrier frequency
κ Cross-polarization power ratio

The dataset of path loss and RSS was extracted from Figure 3 [21]. For this purpose,
the plot digitization technique (plot to CSV) was used and preprocessed in Python (Jupyter
notebook). Thereafter, the supervised machine-learning algorithm known as random forest
(RF) was applied to train the model based on available data points with (n_estimators =
10, random_state = 0). Accordingly, the prediction plots of path loss and RSS has been
Drones 2022, 6, 372 5 of 18

presented in Figures 4 and 5. As a result, the regression score of RF algorithm is observed

around 99%.

25
Model prediction
RSS (dB)
30

35
RSS (dB)

40

45

50

0 200 400 600 800 1000

Distance d0(m)
Figure 4. Random forest model training on channel characteristics (RSS) of UAV at h = 500 m.

80
Model prediction
Dynamic PL (dB)
85

90
PL (dB)

95

100

105

0 200 400 600 800 1000

Distance d0(m)
Figure 5. Random forest model training on channel characteristics (power loss) of UAV at h = 500 m.

3. Mathematical Model for Swarm Control

In this section, a mathematical model is formulated for a unit swarm (three UAVs).
In order to make the model simple, it is assumed that all the UAVs are flying at the same
altitude (2D flying pattern). The mathematical model for a 3D flying pattern is reserved for
future work. In the presented unit swarm configuration, the leading UAV is regarded as the
master and the two following UAVs are considered as slaves (see Figure 6). Accordingly,
the moving parameters of slaves such as speed and direction are dependent on those of the
master UAV. In order to avoid a collision, every element of a unit swarm must be at the
safe distance. In a master–slave network configuration, there is need of a radar sensor on
each element of the unit swarm. In fact, every master UAV of the unit swarm has the ability
to communicate with two of its subsequent UAVs, as shown in Figure 7. Consequently, a
sub-cluster is formed by joining multiple unit swarms. The expansion of the sub-cluster is
the cluster swarm.
Drones 2022, 6, 372 6 of 18

Figure 6. Rectangular coordinate system-based representation of a unit swarm.

Figure 7. Mater–slave hierarchy for UAV swarm flying formation.

A unit swarm is represented in the rectangular coordinate system in Figure 6. The

UAVs’ positions are ( xi (t0 ), yi (t0 ), zi (t0 )) while i ∈ {0, 1, 2}. For simplicity, it has been
assumed that the UAVs are at the same height (z = 0) and the inter UAV distance or guard
distance is (x (t0 ), y(t0 )). According to [26], the equation of the swarm movement can be
written as below.
∗
ρ0,1 = x0 (t0 ) − x1 (t0 ) − x0,1 (t0 )
∗
ρ0,2 = x0 (t0 ) − x2 (t0 ) − x0,2 (t0 ) (4)
∗
ρ1,2 = x1 (t0 ) − x2 (t0 ) − x1,2 (t0 )

where the necessary x-axes spacing for swarm elements are x0,1 (t0 ), x0,2 (t0 ) and x1,2 (t0 ),
and the spacing error function is ρ∗ (t0 ). The velocity of UAVs may be expressed as:

∆er v1 = ∇v1 (t0 ) − v x (t0 )

(5)
∆er v2 = ∇v2 (t0 ) − v x (t0 )

The velocity equations (Equations (5)) belong to UAVs1 and UAVs2 , whereas ∇v(t0 )
and v x (t0 ) are the gradients of velocity and required velocities of UAVs. According to
Figure 7 and Equation (5), the error function for velocities belonging to the nth swarm
element may be expressed as follows:
Drones 2022, 6, 372 7 of 18

∆er vn = ∇vn (t0 ) − v x n (t0 ) (6)

Referring to [27], the acceleration of UAVs in any swarm configuration must be depend
on the error function (∆e vn ) along the x-axes. In addition, the dynamic control rule along
the x and y axis are defined as mentioned in reference [26].

υax (t0 ) = α ax ρ0,a

x x
+ β ax [v0 (t0 − τ0,a (t0 )) − v a (t0 )] + γax ρ a,b + ζ ax [v0 (t0 − τa,b (t0 )) − v a (t0 )] (7)

On other hand, the velocity component is given as

y y y
υa (t0 ) = α ay ρ0,a + β ay [v0 (t0 − τ0,a (t0 )) − v a (t0 )] + γay ρ a,b + ζ ay [v0 (t0 − τa,b (t0 )) − v a (t0 )] (8)

In the above two expressions ((7) and (8)) a 6= b ∈= {1, 2}, the parameters α ax , β ax ,
γax and ζ ax are considered as the gains in the x component. Furthermore, α ay , β ay , γay and
ζ ay are y components in two dimensional space. Moreover, the variable τa,b is considered a
time delaying function in the wireless communication.

4. Swarm Formation
In order to accelerate search and rescue operations, swarm formation is unavoidable.
Many emergency applications require more than one UAV, such as those for highway road
accidents, earthquakes, wild fires and floods. Consider a flood emergency scenario, since
these are increasing due to environmental changes [28]. The search for humans during
high water flow can be, more effectively carried out with the help of a swarm as compared
to a single UAV. In addition, if one UAV carries one life jacket for a flood-flown person,
there will be high significance of the UAV swarm for searching and rescuing. On the
other hand, the swarm UAVs can share the search data (location and photos) with other
UAVs for effective utilization of resource. Furthermore, a leading UAV be considered
as a data acquisition terminal, and other UAVs can be assigned to drop the payloads.
Consequently, the utilization of swarm of UAV during a hazard would be very effective for
search-and-rescue applications.
The formation of UAVs with five different techniques based on triangles is discussed.
However, the triangular formation is considered the most efficient for aerodynamic ap-
plications [29]. For this purpose, N UAVs were selected (N = 10), which were ultimately
divided into further sub-clusters and unit swarms. From Figures 8–12, the mentioned
types of triangular formation have been generated through Python code. According to
Figure 8, the green dots represent the allocated space for the UAVs, whereas the random
appointment of UAVs was taken for the worst case. The length of the UAV swarm is shown
along the x-axis in Figure 8, and width along the y-axis.
According to Figure 8, the equilateral-swarm mode was presented with N = 10 UAVs,
wherein it can be observed that none of them crossed the boundary. It was considered that
the UAVs were propagating along the direction of length. In order to avoid intra-swarm
collision, very type of swarm formation was iterated multiple times to get a reasonable
spatial distribution. Secondly, in isosceles-swarm formation proceeded with the starched
top of the triangle. Thirdly, the obtuse-swarm data were generated from critically packed
UAVs; most of them are seen in a linear arrangement and random uniform distribution.
Furthermore, the acute- and right swarms are shown to have similar distributions.
Drones 2022, 6, 372 8 of 18

Figure 8. UAV equilateral swarm formation.

Figure 9. UAV isosceles swarm formation.

Figure 10. UAV obtuse swarm formation.

Drones 2022, 6, 372 9 of 18

Figure 11. UAV acute swarm formation.

Figure 12. UAV right swarm formation.

5. Swarm Cluster Prediction

This section consists of two parts: firstly, the cluster prediction of previously generated
swarms; secondly, the dendrogram plot, heat map and contour plot of the clustered swarm.

5.1. Machine-Learning Model

The dataset generated in the previous section is unlabeled, and UAVs are considered
to be placed nearby. The optimum choice is to apply K-means clustering. The reason for
the selection of K-means clustering is that the transmitted radiowave (Ei = Eo e−2πz/λ )
directly intersects with the receptor UAV. However, the diversity signal (multi-path) at
the receiving UAV was ignored due to the near field. The K-means algorithm works with
Euclidean distance between the UAVs, whereas the cosine and Manhattan algorithms do
not use the direct distance approach. In order to satisfy Equation (1), d is considered as
peer-to-peer distance between UAVs; therefore, only Euclidean distance could meet the
requirement. According to Figure 6, the proposed mathematical model for swarm control
has a two-dimensional (2D) assumption, and K-means with Euclidean distance can also
fulfill this condition. However, the cosine, Manhattan, Minkowski and Chebyshev models
can be used for higher dimensions. In fact, the distance and reallocation parameters are
required for such applications.
The cluster process of UAVs is divided into three steps. Firstly, the optimum numbers
of clusters are found through within-cluster sum of squares (WCSS), as shown in Figure 13.
According to the elbow plot, i = 4 for the given swarm datasets. Secondly, the Euclidean
Drones 2022, 6, 372 10 of 18

distance of each UAV is depicted with reference to k i centroids. In Figure 6, the coordinates
of U AV1 and U AV2 are ( x1 (t), y1 (t)) and ( x2 (t), y2 (t)), respectively. The equation for
euclidean distance can be expressed as below:
q
d(U AVs1 , U AVs2 ) = ( x2 (t) − x1 (t))2 + (y2 (t) − y1 (t))2 (9)
Thereafter, the centroids of UAV swarm can be found by

arg min dist(k i , U AVx )2 (10)

k i is the number of centroids (k i ∈ 1 . . . 4) which have been found through WCSS.
Thirdly, we assign each UAV to the closest centroid, once the UAVs gather around the
centroid; then, we again find the centroid by taking the average of each cluster. Finally, we
repeat the steps of averaging cluster centroids till the centroid does not change. Likewise,
the given below expressed as:

1
ki = ∑ U AVi
|Si | U AV
(11)
i ∈S
i

According to the Equation (11), the Si is set of all UAVs assigned to k i cluster. Finally,
Figures 14–18 present the K-means cluster for all proposed types of UAV swarms formation.
It has been observed from Figure 15 that one UAV has been marked as a cluster which can
be justified the inherent property of outlier in K-means clustering.

Figure 13. Proposed UAV swarm formation with mater–slave hierarchy.

Figure 14. K-means right-cluster swarm of UAVs.

Drones 2022, 6, 372 11 of 18

Figure 15. K-means acute-cluster swarm of UAVs.

Figure 16. K-means isosceles-cluster swarm of UAVs.

Figure 17. K-means equilateral-cluster swarm of UAVs.

Drones 2022, 6, 372 12 of 18

Figure 18. K-means obtuse-cluster swarm of UAVs.

5.2. Deprogram for UAV formation

The dendrogram plots are presented for the above-mentioned clusters. In hierarchical
clustering, the agglomerative algorithm is used, which has a bottom-to-top approach (unit
swarm to cluster). The swarm-ability factor f sw is introduced with the minimum criteria
of f sw = 0.5 for each unit cluster, and f sw = 1 for sub-clusters. Additionally, Figures 19–23
present the dendrogram, and Figure 20 is considered the most suitable configuration for
swarm formation. On the other hand, f sw < 0.5 generates the interference or highlights the
y
other issues related to the physical movement (υix (t) and υi (t)) of swarm elements.

Figure 19. Hierarchical clustering for acute swarm.

Drones 2022, 6, 372 13 of 18

Figure 20. Hierarchical clustering for equilateral swarm.

Figure 21. Hierarchical clustering for obtuse swarm.

Figure 22. Hierarchical clustering for right swarm.

Drones 2022, 6, 372 14 of 18

Figure 23. Hierarchical clustering for isosceles-swarm.

5.3. Prediction Data Visualization

In the path loss profiling and modeling, the predicted RSS and K-means clustering
data were visualized. However, the complete procedure is described in Figure 24. Whereas
Figure 25 shows the head map with two predictions: UAV clusters and their corresponding
RSS. In other words, the heat map can be considered to show the cluster power Pn of
parameters (mentioned in Table 1). The odd column shows the predicted RSS, and even
columns are UAVs’ clustering distances. The rows in the heat map are the numbers of
UAVs; N = 10. Moreover, it has been observed that the UAVs, on there reallocation, receive
power (Pn ) in the range of −30 to −40 dB. In Figure 26, the contour plot shows the predicted
power for the visualization of RSS. Finally, it is shown the whole swarm has a similar range
of RSS with normalized clustered distances.
In Table 2, a comparison is presented wherein a number of research works are listed.
According to that table, [30–35] used the conventional approaches towards communication,
control, networking and collaboration for UAVs. As listed in Table 2, most reported works did
not incorporate a UAV swarm, whereas the proposed UAV swarm technique has the potential
to enhance the effectiveness of such applications. Few researchers have adopted swarm UAVs
for other applications while using a machine-learning approach. However, the presented
work is intelligent enough to utilize a machine-learning algorithm for UAV swarm formation.
Additionally, a machine-learning-based communication model is also presented here for
intra-swarm communication. As a result, the proper UAV swarm formations, along with
received signal strength (−30 dB to −40 dB), have been achieved. Therefore, the presented
work can be considered a good candidate for search-and-rescue applications.
Drones 2022, 6, 372 15 of 18

Figure 24. Hierarchical clustering for isosceles swarm.

20 -36 11 -34 20 -36 35 -39 28 -38

9 8 7 6 5 4 3 2 1 0

30
26 -37 21 -37 37 -39 27 -38 33 -38
30 -38 17 -36 27 -38 32 -38 33 -38 20
34 -39 15 -35 18 -36 14 -35 26 -37 10
Number of UAVs

17 -36 18 -36 34 -39 22 -37 28 -38

0
13 -34 19 -36 27 -38 33 -38 26 -37
30 -38 17 -36 36 -39 25 -37 30 -38 10
29 -38 16 -35 27 -38 24 -37 30 -38 20
22 -37 25 -37 26 -37 36 -39 23 -37
30
18 -36 19 -36 20 -36 26 -37 30 -38
0 1 2 3 4 5 6 7 8 9
Swarm distance (even colum) and RSS (odd colum)
Figure 25. Heat map for hierarchical clustering to RSS (Pn cluster power) prediction with random forest.
4

−34
3.5

3 −35
Distance and RSS

2.5

−36
2

1.5 −37

−38
0.5

0
0 2 4 6 8

Number of UAVs

Figure 26. Contour plot for predicted RSS of UAVs cluster with N =10.
Drones 2022, 6, 372 16 of 18

Table 2. Comparison of UAVs and swarm parameters.

Ref. UAVs ML & AI Algorithm Model Swarm Application

[36] 4 Yes OpenCV Communication No S&R
[30] 10 No – Flux No Robotics
[37] 7 Yes CNN Network No S&R
[31] 2 No PSO Control No S&R
[38] 2 Yes OpenCV Collaboration No Robotics
[32] 1 No Fusion Collaboration No S&R
Mission Reliabil-
[33] 8 No Maintenance Communication Yes
ity
distributed
[34] 8 No Communication Yes Wildfires
algorithms
[35] 5 No Leader-follower Control Yes Robotics
Gaussian
[39] 1 Yes Communication No Mobile com.
mixture
R. Forest and
Proposed work 10 Yes Swarm control Yes S&R
K-means

6. Conclusions
This work presents a path-loss-profiling method for UAV swarms with machine learn-
ing, and it provides receive-signal-strength prediction. The UAV-swarm-communication
problem for search-and-rescue applications has been solved by the proposed procedure
machine-learning approach. Initially, the path-loss profile is generated though the training
of a random forest model-based received-signal-strength dataset. In order to find the
reallocation of UAVs, the dataset was generated for UAV clustering with the concept of
triangular-based swarm formation. After that, K-means clustering was applied for the
prediction of cluster parameters for a UAV swarm. Furthermore, the inter-swarm euclidean
distance was found through the dendrogram plots. Finally, the results of communication
model for the complete UAV swarm were presented in heap maps and contour plots. Future
work could be related to radio-frequency-interference mitigation through machine learning.

Author Contributions: Conceptualization, H.K.; Methodology, I.K. and M.H.A.-A.; Software, H.K.;
Investigation, A.J.A.; Resources, S.U.R. and M.E.; Visualization, I.U.; Supervision, H.K.; Project
administration, G.A. All authors have read and agreed to the published version of the manuscript.
Funding: This work do not have any funding.
Data Availability Statement: The code is available on request.
Acknowledgments: This work was supported by the EIAS Data Science and Block chain Lab., College
of Computer and Information Sciences, Prince Sultan University, Riyadh Saudi Arabia.
Conflicts of Interest: The authors declare no conflict of interest.

References
1. Radio Technical Commission for Aeronautics (RTCA). Minimum Operational Performance Standards for Unmanned Aircraft Systems;
Technical Report; RTCA: Washington, DC, USA, 2013.
2. Radio Technical Commission for Aeronautics (RTCA); Technical Report; Drone Advisory Committee (DAC): Washington, DC, USA,
2016.
3. Jin, W.; Yang, J.; Fang, Y.; Feng, W. Research on Application and Deployment of UAV in Emergency Response. In Proceedings of
the 2020 IEEE 10th International Conference on Electronics Information and Emergency Communication (ICEIEC), Beijing, China,
17–19 July 2020; pp. 277–280. [CrossRef]
4. Bai, G.; Li, Y.; Fang, Y.; Zhang, Y.A.; Tao, J. Network approach for resilience evaluation of a UAV swarm by considering
communication limits. Reliab. Eng. Syst. Saf. 2020, 193, 106602. [CrossRef]
5. Gu, X.; He, F.; Wang, R.; Chen, L. Group Mobility Model for Complex Multimission Cooperation of UAV Swarm. Int. J. Aerosp.
Eng. 2022, 2022, 22. [CrossRef]
6. Peng, J.; Zhang, Z.; Wu, Q.; Zhang, B. Anti-Jamming Communications in UAV Swarms: A Reinforcement Learning Approach.
IEEE Access 2019, 7, 180532–180543. [CrossRef]
Drones 2022, 6, 372 17 of 18

7. Slimeni, F.; Scheers, B.; Chtourou, Z.; Le Nir, V. Jamming mitigation in cognitive radio networks using a modified Q-learning
algorithm. In Proceedings of the 2015 International Conference on Military Communications and Information Systems (ICMCIS),
Cracow, Poland, 18–19 May 2015; pp. 1–7. [CrossRef]
8. Slimeni, F.; Chtourou, Z.; Scheers, B.; Le Nir, V.; Attia, R. Cooperative Q-learning based channel selection for cognitive radio
networks. Wirel. Netw. 2019, 25, 4161–4171. [CrossRef]
9. Tang, J.; Liu, G.; Pan, Q. A Review on Representative Swarm Intelligence Algorithms for Solving Optimization Problems:
Applications and Trends. IEEE/CAA J. Autom. Sin. 2021, 8, 1627–1643. [CrossRef]
10. Tang, J.; Chen, X.; Zhu, X.; Zhu, F. Dynamic Reallocation Model of Multiple Unmanned Aerial Vehicle Tasks in Emergent
Adjustment Scenarios. IEEE Trans. Aerosp. Electron. Syst. 2022, 1–43 . [CrossRef]
11. Li, H.; Zhang, B.; Qin, S.; Peng, J. UAV-Clustering: Cluster head selection and update for UAV swarms searching with unknown
target location. In Proceedings of the 2022 IEEE 23rd International Symposium on a World of Wireless, Mobile and Multimedia
Networks (WoWMoM), Belfast, UK, 14–17 June 2022; pp. 483–488. [CrossRef]
12. Ruan, L.; Li, G.; Cheng, J.; Lv, J.; Dai, W.; Tian, S.; Hu, J. Multistage Clustering-Based Localization for Remote UAV Swarm: A
Coalitional Game Framework. IEEE Commun. Lett. 2022, 26, 2047–2051. [CrossRef]
13. Fabra, F.; Zamora, W.; Reyes, P.; Calafate, C.T.; Cano, J.C.; Manzoni, P.; Hernandez-Orallo, E. An UAV Swarm Coordination
Protocol Supporting Planned Missions. In Proceedings of the 2019 28th International Conference on Computer Communication
and Networks (ICCCN), Valencia, Spain, 29 July–1 August 2019; pp. 1–9. [CrossRef]
14. Qu, Y.; Dong, C.; Wu, T.; Zhuang, Y.; Dai, H.; Wu, F. Efficient Edge Intelligence under Clustering for UAV Swarm Networks. In
Proceedings of the 2021 International Conference on Space-Air-Ground Computing (SAGC), Huizhou, China, 23–25 October
2021; pp. 112–117. [CrossRef]
15. Sun, Y.; Mi, Z.; Wang, H.; Lu, F.; Zhao, N. Adaptive Enhanced Weighted Clustering Algorithm for UAV Swarm. In Proceedings
of the 2020 IEEE 20th International Conference on Communication Technology (ICCT), Nanning, China, 28–31 October 2020;
pp. 709–714. [CrossRef]
16. Zhou, Y.; Rao, B.; Wang, W. UAV Swarm Intelligence: Recent Advances and Future Trends. IEEE Access 2020, 8, 183856–183878.
[CrossRef]
17. Tang, J.; Lao, S.; Wan, Y. Systematic Review of Collision-Avoidance Approaches for Unmanned Aerial Vehicles. IEEE Syst. J. 2022,
16, 4356–4367. [CrossRef]
18. Manel Khelifi, a.I.B. Swarm Unmanned Aerial Vehicles (SUAVs): A Comprehensive Analysis of Localization, Recent Aspects,
and Future Trends. J. Sens. 2022, 2022. [CrossRef]
19. Aibin, M.; Aldiab, M.; Bhavsar, R.; Lodhra, J.; Reyes, M.; Rezaeian, F.; Saczuk, E.; Taer, M.; Taer, M. Survey of RPAS Autonomous
Control Systems Using Artificial Intelligence. IEEE Access 2021, 9, 167580–167591. [CrossRef]
20. Goddemeier, N.; Wietfeld, C. Investigation of Air-to-Air Channel Characteristics and a UAV Specific Extension to the Rice
Model. In Proceedings of the 2015 IEEE Globecom Workshops (GC Wkshps), San Diego, CA, USA, 6–10 December 2015; pp. 1–5.
[CrossRef]
21. Khalil, H.; Ahmed, M.M.; Rafique, U.; Almesaeed, R.; Nazar, W. Optimum Placement of Conformal Antenna Array Based on
Path Loss Profile. In Proceedings of the 2019 International Conference on Advances in the Emerging Computing Technologies
(AECT), Al Madinah Al Munawwarah, Saudi Arabia, 10 February 2020; pp. 1–5.
22. Khawaja, W.; Guvenc, I.; Matolak, D. UWB Channel Sounding and Modeling for UAV Air-to-Ground Propagation Channels. In
Proceedings of the 2016 IEEE Global Communications Conference (GLOBECOM), Washington, DC, USA, 4–8 December 2016;
pp. 1–7. [CrossRef]
23. Feng, Q.; McGeehan, J.; Tameh, E.K.; Nix, A.R. Path Loss Models for Air-to-Ground Radio Channels in Urban Environments.
In Proceedings of the 2006 IEEE 63rd Vehicular Technology Conference, Melbourne, VIC, Australia, 7–10 May 2006; Volume 6,
pp. 2901–2905. [CrossRef]
24. Almesaeed, R.; Ameen, A.S.; Mellios, E.; Doufexi, A.; Nix, A.R. A proposed 3D extension to the 3GPP/ITU channel model for 800
MHz and 2.6 GHz bands. In Proceedings of the 8th European Conference on Antennas and Propagation (EuCAP 2014), The
Hague, The Netherlands, 6–11 April 2014; pp. 3039–3043.
25. Almesaeed, R.N.; Ameen, A.S.; Mellios, E.; Doufexi, A.; Nix, A. 3D Channel Models: Principles, Characteristics, and System
Implications. IEEE Commun. Mag. 2017, 55, 152–159. [CrossRef]
26. Zeng, T.; Mozaffari, M.; Semiari, O.; Saad, W.; Bennis, M.; Debbah, M. Wireless Communications and Control for Swarms of
Cellular-Connected UAVs. In Proceedings of the 2018 52nd Asilomar Conference on Signals, Systems, and Computers, Pacific
Grove, CA, USA, 28–31 October 2018; pp. 719–723.
27. Bando, M.; Hasebe, K.; Nakayama, A.; Shibata, A.; Sugiyama, Y. Dynamical model of traffic congestion and numerical simulation.
Phys. Rev. E 1995, 51, 1035–1042. [CrossRef] [PubMed]
28. Swain, D.L.; Wing, O.E.; Bates, P.D.; Done, J.M.; Johnson, K.A.; Cameron, D.R. Increased Flood Exposure Due to Climate Change
and Population Growth in the United States. Earth’s Future 2020, 8. [CrossRef]
29. Bangash, Z.; Ahmed, A.; Khan, J.; Sanchez, R. Aerodynamics of Formation Flight. J. Aircr. 2006, 43, 907–912. [CrossRef]
30. Hartley, J.; Shum, H.P.; Ho, E.S.; Wang, H.; Ramamoorthy, S. Formation control for UAVs using a Flux Guided approach. Expert
Syst. Appl. 2022, 205, 117665. [CrossRef]
Drones 2022, 6, 372 18 of 18

31. de Alcantara Andrade, F.A.; Reinier Hovenburg, A.; Netto de Lima, L.; Dahlin Rodin, C.; Johansen, T.A.; Storvold, R.; Moraes Cor-
reia, C.A.; Barreto Haddad, D. Autonomous Unmanned Aerial Vehicles in Search and Rescue Missions Using Real-Time
Cooperative Model Predictive Control. Sensors 2019, 19, 4067. [CrossRef]
32. Waharte, S.; Trigoni, N. Supporting Search and Rescue Operations with UAVs. In Proceedings of the 2010 International
Conference on Emerging Security Technologies, Canterbury, UK, 6–7 September 2010; pp. 142–147. [CrossRef]
33. Guo, J.; Wang, L.; Wang, X. A Group Maintenance Method of Drone Swarm Considering System Mission Reliability. Drones 2022,
6, 269. [CrossRef]
34. Saffre, F.; Hildmann, H.; Karvonen, H.; Lind, T. Monitoring and Cordoning Wildfires with an Autonomous Swarm of Unmanned
Aerial Vehicles. Drones 2022, 6, 301. [CrossRef]
35. Gao, H.; Li, W.; Cai, H. Fully Distributed Robust Formation Flying Control of Drones Swarm Based on Minimal Virtual Leader
Information. Drones 2022, 6, 266. [CrossRef]
36. Scherer, J.; Yahyanejad, S.; Hayat, S.; Yanmaz, E.; Andre, T.; Khan, A.; Vukadinovic, V.; Bettstetter, C.; Hellwagner, H.; Rinner, B.
An Autonomous Multi-UAV System for Search and Rescue. In Proceedings of the First Workshop on Micro Aerial Vehicle Networks,
Systems, and Applications for Civilian Use; Association for Computing Machinery: New York, NY, USA, 2015; pp. 33–38. [CrossRef]
37. Alsamhi, S.H.; Shvetsov, A.V.; Kumar, S.; Shvetsova, S.V.; Alhartomi, M.A.; Hawbani, A.; Rajput, N.S.; Srivastava, S.; Saif,
A.; Nyangaresi, V.O. UAV Computing-Assisted Search and Rescue Mission Framework for Disaster and Harsh Environment
Mitigation. Drones 2022, 6, 154. [CrossRef]
38. Evangeliou, N.; Chaikalis, D. Visual Collaboration Leader-Follower UAV-Formation for Indoor Exploration. Front. Robot. AI
2021, 8. [CrossRef] [PubMed]
39. Zhang, Q.; Mozaffari, M.; Saad, W.; Bennis, M.; Debbah, M. Machine Learning for Predictive On-Demand Deployment of Uavs
for Wireless Communications. In Proceedings of the 2018 IEEE Global Communications Conference (GLOBECOM), Abu Dhabi,
United Arab Emirates, 9–13 December 2018; pp. 1–6. [CrossRef]