A Systematic Approach of a Flying Ad-hoc Network for Smart Cities

Abstract

Recently, a flying ad-hoc network (FANET) has been employed in modern warfare for monitoring and reconnaissance to produce a healthy living environment in smart cities through multiple unmanned aerial vehicles (UAVs). FANETs allow multiple UAVs to communicate in 3D space to establish an ad-hoc network. FANET applications, among others, can deliver cost-effective services to help future smart cities achieve their goals. However, adopting FANET technology in smart cities is difficult due to its challenges from UAV mobility, energy, and security considerations. Therefore, this study analyzed the new trends and technologies of smart city research and proposes research directions through FANET. This chapter aims to look at FANET's possible applications in smart cities and the implications and issues that come with them. Furthermore, it also goes over the current state of recent enabling technologies for FANET in order.

Full text

55
Copyright © 2023, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited.
Chapter 4
DOI: 10.4018/978-1-6684-6408-3.ch004
ABSTRACT
Recently, a flying ad-hoc network (FANET) has been employed in modern warfare for monitoring and
reconnaissance to produce a healthy living environment in smart cities through multiple unmanned
aerial vehicles (UAVs). FANETs allow multiple UAVs to communicate in 3D space to establish an ad-
hoc network. FANET applications, among others, can deliver cost-effective services to help future smart
cities achieve their goals. However, adopting FANET technology in smart cities is difficult due to its
challenges from UAV mobility, energy, and security considerations. Therefore, this study analyzed the
new trends and technologies of smart city research and proposes research directions through FANET.
This chapter aims to look at FANET’s possible applications in smart cities and the implications and
issues that come with them. Furthermore, it also goes over the current state of recent enabling technolo-
gies for FANET in order.
A Systematic Approach of
a Flying Ad-hoc Network
for Smart Cities
Sudesh Kumar
https://orcid.org/0000-0002-9405-1890
Indira Gandhi National Tribal University, Amarkantak, India
Mamtha Prajapati
GITAM School of Technology, GITAM University, Visakhapatnam, India
Neeraj Kumar Rathore
Indira Gandhi National Tribal University, Amarkantak, India
Sanjay Kumar Anand
Netaji Subhas University of Technology, East Campus, New Delhi, India

56
A Systematic Approach of a Flying Ad-hoc Network for Smart Cities
INTRODUCTION
Smart cities can maximise their resource use and offer efficient and effective services to their citizen’s
thanks to recent developments and breakthroughs in Information and Communication Technologies
(ICTs). One of these technologies is the Flying Ad-hoc Network (FANET), which has the potential to
cover large geographic regions utilizing several Unmanned Aerial Vehicles (UAVs) and enable numerous
applications for future smart cities that will positively affect society. Intelligent transportation, product
distribution, demographic and environmental monitoring, on-board health planning, civic security, ob-
ject identification, smart agriculture, and more uses are possible with FANET. (Bekmezci et al., 2013).
FANET applications, among others, can deliver cost-effective services to help future smart cities achieve
their goals. However, implementing FANET technology in smart cities is a very difficult task due to
several issues. Furthermore, FANET-enabled smart cities will likely become a significant component
of human existence, and UAVs will significantly increase real-time information distribution. They are
the best option because UAVs have the most operational capacity in any worst-case damage scenario
(Siddiqi et al., 2021).
In this sub-section, the paper starts with a theoretical background of smart city and FANET technol-
ogy in Section 2. Further, Section 3 discusses some potential applications of FANET for smart cities.
Sequentially, Section 4 presents the issues and challenges of FANET for smart cities. Section 5 discusses
some key technologies with the fusion of FANET in future smart cities. Finally, Section 6 separately
covers the conclusion.
THEORITICAL BACKGROUND
Smart Cities
By 2050, the population of the world is expected to have doubled. People are also shifting from rural to
urban areas such as cities, which is a growing trend. City officials will have various obstacles in main-
taining or improving city services and inhabitants’ quality of life due to the rapid increase in population.
As a result, there is an increasing interest in integrating robots, intelligent solutions, and current ICTs
into developing smart cities. These technologies will aid in developing intelligent, automated services
that will improve infrastructure performance and resident comfort (Figure 1). A smart city is a concept
that connects technology to long-term economic growth and outstanding quality of life (Trindade et
al., 2017). Europe has recently taken the lead in the construction of smart cities worldwide. Europe has
taken the initiative to encourage its member countries to construct smart cities. Additionally, smart city
technologies seek to improve accessibility and efficiency for daily tasks while addressing issues with
public safety, traffic, and the environment (Joshi et al., 2016; Mohanty et al., 2022). Some of the most
often used smart city components are as follows:
Smart Infrastructure
Buildings and urban infrastructure need to be built more sustainably and effectively for cities to remain
viable, and digital technologies are becoming increasingly important. Cities should invest in electric and
self-propelled vehicles to lower CO2 emissions. Modern technology is needed to provide an infrastructure

57
A Systematic Approach of a Flying Ad-hoc Network for Smart Cities
that is both energy and environmentally friendly. Smart lighting, for instance, only illuminates when
someone walks by it, saving energy; crucial elements of smart lighting include determining brightness
levels and tracking daily use (Joshi et al., 2016).
Smart Public Safety
IoT-based smart city solutions increase public safety by providing real-time monitoring, analytics, and
decision-making capabilities (Grizhnevich, 2021). Public safety systems can pinpoint potential crime
locations by combining data from social media feeds with CCTV cameras and sound sensors throughout
the city. As a result, the police can find and apprehend suspected criminals.
Smart Waste Management System
Waste management is both expensive and inefficient, leading to traffic congestion. Intelligent waste
management solutions can help ease some of these issues by tracking how full trash cans are at any one
time and communicating that information to waste management companies, which can then determine
the optimum waste collection routes (Grizhnevich, 2021).
Smart Air-Quality Monitoring
Today, cities worldwide cope with challenges such as air pollution, extreme air temperatures, and heavy
precipitation. These problems will occur more often due to climate change in the future (Jo et al., 2021).
Figure 1. Main Components of smart city

58
A Systematic Approach of a Flying Ad-hoc Network for Smart Cities
This trend will result in an unknown amount of economic damage and endanger the life and health of
the cities’ populations. As a result, an intelligent air quality monitoring system is required to detect these
particles and inform users of pollutants.
Smart Transportation Management
Utilizing a variety of technologies, smart transportation management keeps track of, assesses, and man-
ages transportation networks to increase effectiveness and safety. In other words, intelligent transportation
makes moving around a city easier, safer, and more affordable for the city and the person (Grizhnevich,
2021).
Smart Health
Most medical emergencies, including heart attacks, blood pressure problems, and accident-related re-
covery, dictate how quickly a patient receives medical care. WSN, in which sensors are applied to the
body for the patient’s benefit in any emergency, can enhance health monitoring for any person residing
in smart cities. In this system, the patient health data can be reached to medical professionals via the
FANET system with the fusion of WBAN (Kumar et al., 2020a).
Smart Weather Monitoring
Weather monitoring is a constant in everyone’s life. Agriculture, industry, construction, and several other
industries are among those affected significantly by the state of the environment. The impact is primarily
measured in agriculture and industry, though. IoT and WSN technology uses various sensors to track
changes in the weather and climate, including CO2 levels in the atmosphere, temperature, humidity,
wind speed, wetness, light intensity, and UV radiation (Sripath Roy et al., 2018).
Smart Fire/Smoke Detection
Cities are bordered by forests, agricultural land, or open places where fires might occur, posing a threat
to human life and causing the extinction of many resources. Furthermore, a fire and smoke detection
system requires precise, quick, and real-time response mechanisms to make the best decision and promptly
notify the appropriate individuals. Wireless sensor technology, UAVs, and cloud computing can all be
used to create a fire detection system. Some image processing techniques are also incorporated into the
proposed fire detection system to identify the fire event better and use it as a whole (Mahgoub et al., 2020).
Smart Parking
People nowadays find it difficult to find parking spaces in their daily lives. According to a recent as-
sessment, by 2035, the global car population would have risen to almost 1.6 billion people. Thus, IoT
and UAV-based intelligent parking systems in smart cities are the keys to minimising traffic congestion
(Khanna and Anand, 2016).

59
A Systematic Approach of a Flying Ad-hoc Network for Smart Cities
Flying Ad-hoc Network
A Flying Ad-hoc Network (FANET) is an autonomous technology which is creating a self-organized
wireless network via Unmanned Arial Vehicles (UAVs) (Bekmezci et al., 2013). Without a fixed infra-
structure in this network, multiple UAVs can connect at 5.8GHz within a constrained range.
Additionally, FANET is based on the premise that every UAV is viewed as sentient and outfitted with
cutting-edge processing tools, sensors, cameras, computer devices, and other smart gadgets like digital
maps. These intelligent devices enhance FANET’s technical capability for flexible work in extremely
complicated environments (Khare et al., 2022; Kumar et al., 2021b). Fundamentally, FANET overcomes
Figure 2. FANET architecture

60
A Systematic Approach of a Flying Ad-hoc Network for Smart Cities
the limitations of earlier conventional networks in some crucial areas, such as military, mountains, ocean,
hazardous conditions, etc., or may be impacted by disasters like earthquakes, tsunamis, hurricanes, etc.
In such dire circumstances, FANETs emerge as a viable option utilizing UAVs for search, monitoring,
and rescue operations to prevent human casualties and financial loss (Kumar et al., 2020b).According
to any mission carried out by UAVs in a FANET architecture (Figure 2), two networking modes must
be enabled: first, UAV-to-UAV (U2U) communication, also known as ad-hoc communication, in which
all UAVs may connect or via other UAVs and second, UAV-to-Infrastructure (U2I) communication also
known as cellular mode communication, either individually or more UAVs can connect to the infra-
structure such as ground station, UAV-control centre, satellites etc. (Oubbati et al., 2017; Kumar et al.,
2018; Srivastava and Prakash, 2021a; Kumar et al., 2023).
FANET APPLICATIONS IN FUTURE SMART CITIES
This section covers a number of FANET applications for smart cities. These applications benefit smart
cities by enhancing service performance and citizens’ quality of life (Figure 3).
Figure 3. FANET scenarios with different applications

61
A Systematic Approach of a Flying Ad-hoc Network for Smart Cities
Health Monitoring Planning
In the current state of public safety, the most promising upcoming technologies include IoT, fog comput-
ing, UAVs, FANET, ML algorithms, and web services. The utilisation of these cutting-edge technologies
has the potential to significantly enhance, maintain, and support human life (Martínez-Pérez et al., 2013;
Mukhopadhyay et al., 2021; Dhaka et al., 2021; Kumar et al 2022). However, the availability of primary
healthcare services 24X7 to the patient is essential for every smart city. Currently, FANET technology
research is focusing on different health monitoring preparation. The Wireless Body Area Sensor Network
(WBAN) and FANET can also improve contact between medical professionals and patients. In damaged
areas where the connection is problematic, this preparation can be enhanced by using WBAN to track
patients by sending Personal Health Information (PHI) to the healthcare centre via FANET (S et al.,
2022; Kumar et al., 2020a). These concepts provide high-quality care early on and respond quickly to
patients in an emergency. A novel MP-OLSR (Radu et al., 2018) routing strategy is proposed for video
streaming, data processing and service provisioning to a central management system with the help of
FANET. The proposed methodology improved life-threatening incident prevention while also supporting
rescue teams in organizing and conducting critical public safety measures. In addition, when incidents
within the smart city hinder or halt ground movement, FANET can provide comparable emergency help
to persons in public facilities.
Traffic Management System
Traffic Management System (TMS) is the core operational mission of smart cities. One of the main ob-
jectives of the TMS is to reduce incident response delay, ensure the safety of response crews, complete
thorough site investigation, and accelerate the incident recovery. Thorough site surveys and medical
examinations of major accidents are the most critical and time-consuming steps in the TMS. They are
necessary to facilitate subsequent safety analysis and medical treatment. Recently, FANET has become a
potential technology to design intelligent traffic planning in smart cities. Multiple UAVs communication
can help monitor and analyze traffic and subsequently reduce the duration of site surveying (Salvo et al.,
2014; Khan et al., 2020). FANET may also track, monitor, and enforce the posted speed limit and other
traffic violations and shady behaviour by moving vehicles. These vehicle-related data are collected and
transmitted in real time to the closest base station, where it is passed on to the appropriate authorities
for legal action. TMS can circumvent the limitations of conventional monitoring systems via FANET
due to its ease of use, portability, and capacity to cover large areas.
Infrastructure Investigation
Recently, the use of FANET has been overgrowing across various civil application domains, including
real-time investigation in inaccessible locations that are hard to reach by humans, such as tank, flue, and
roof inspections, power transmission line inspections, buildings, bridges and vital construction sites.
Construction-site investigation planning is a crucial sector that employs multi-UAV networks such as
FANET for enhanced performance, velocity, and precision of information. As a result, the investigator
human can track all sites with greater visibility and work progress without being physically present
(Greenwood et al., 2019). Furthermore, before estimating a project’s cost, site visits to the proposed
project site are essential. Site visits can be time-consuming for estimating teams, especially working

62
A Systematic Approach of a Flying Ad-hoc Network for Smart Cities
under tight deadlines. Vehicle access to portions of a greenfield site may be restricted by environmental
barriers such as fences and ditches, necessitating foot travel. The UAV can travel much faster than a person
on foot while simultaneously acquiring aerial photo and video site documentation. FANET technique
can be launched on the site and take high-resolution photos and videos of large areas. A group of UAVs
can fly close to the ground to inspect the area for construction budget issues. Additionally, FANET can
deliver precise details about the state of infrastructures by gathering visual data in pictures and videos
and transferring those details to the intended location (Ham et al., 2016). Where security personnel are
typically used for site safety, this technology can also be used at night for security purposes. However,
there is not enough study on FANET technology for applications in future smart city design for infra-
structure assessment. This method might offer a more comprehensive investigation focus, greater mistake
toleration, and quicker operation completion.
Disaster Management
The ability of search and rescue personnel to react quickly during a natural catastrophe is crucial to
saving the lives of persons in the impacted areas. Since the airborne assessment can swiftly access the
impacted areas and gather photographs and videos of the current situation, it provides the most effective
and rapid situational awareness (Zhou et al., 2020). As a result, the research and development community
for disaster management has begun to pay more attention to FANET. (Arafat et al., 2018). However,
routing mechanisms are critical for information dissemination between patients and medical profession-
als in emergencies such as earthquakes, flooding, and other natural disasters. As a result, authors (Radu
et al., 2018) introduced a FANET emergency application system for the MP-OLSR approach, collect-
ing fire dynamics data from UAVs and then communicating safety instructions to people at risk via a
central management system. The experimental results imply that MP-OLSR is appropriate for FANET
scenarios, especially emergency applications, where mobility is high and response times are confined
in real time. During emergency missions, however, UAVs must send various disaster data quickly. As a
result, the authors (Khan et al., 2019) presented urgency-aware scheduling to efficiently transmit high
and low-priority packets with minimal transmission queue delays. Based on behavioural studies of bird
flocking, the authors analyse several UAV situations for disaster management and suggest a bio-inspired
mechanism for cluster formation and maintenance for N number of UAVs. A priority-based route selec-
tion mechanism was also used for data transfer in a FANET cluster. Experimental findings explore that
the suggested mechanism outperforms existing mechanisms in the presence of assessment criteria such
as queuing time, delay, forward message percentage, and fairness.
Wireless Coverage
FANET recently demonstrated a promising advanced technology that could enhance urban intelligence,
human well-being, and economic efficiency. In regions where a specific type of communication infra-
structure is required, FANET can deploy connectivity via several UAVs. Autonomously operated smart
UAVs are being utilised as aerial communication relays to effectively and efficiently transport data ac-
quired by one site to another and extend the communication range of relaying nodes with faster data rates.
In addition, when cellular networks are down due to crises like earthquakes or floods, many UAVs can
be deployed to provide wireless coverage for indoor users inside a high-rise building. Furthermore, the
current economic availability of UAVs has made it simple to build a massive communication network.

63
A Systematic Approach of a Flying Ad-hoc Network for Smart Cities
To avoid communication link interruption in this network, a relay UAV must carefully maintain links
with its neighbours. UAVs have been used in various settings as relays to connect isolated electronics.
Ayyagari et al. (1996), suggested a network design that deployed airborne unmanned relay devices to form
similar “cellular towers” in the sky to construct rapidly deployable and broadband wireless networks.
Security
Integrating UAVs with IoTs, RFID, Cloud Computing, and video streaming has boosted FANET technol-
ogy’s importance in public safety. Recently, in wealthy countries, UAV networks like FANET have been
seriously explored as a tool for improving national security, such as border monitoring. UAVs can be
deployed in huge numbers to provide complete border monitoring coverage due to their low cost. These
gadgets can include cameras, GPS, computational devices, and live streaming capabilities, among other
sensors. A UAV can be set to patrol the borders autonomously using on-board GPS or by connecting
with ground equipment. Human operators can also control them to respond to incidents. UAVs can be
used as a deterrent to criminal activity and provide sensing capabilities. Along with smart cities, intel-
ligent police systems will also be the consideration norm. The police forces will be equipped with the
latest technologies so that the security problems that are now complex can be resolved with ease using
this network. A network of UAVs can be a reliable tool for crime prevention. Further, they can also be
effectively employed in investigation procedures. A well-trained and networked swarm of UAVs on
surveillance can be highly effective against criminals. In addition, in the future smart cities, police can
be empowered if a FANET will be deployed in dangerous or inaccessible areas like borders, sea, and
war sites on their behalf. The FANET is superior to its predecessors due to its minimum hardware cost,
simplicity of implementation, and availability in any circumstance. Figure 4 depicts further monitoring
and other typical smart city applications (Radu et al., 2018b; Shakhatreh et al., 2019).
Figure 4. Monitoring and other popular FANET applications

64
A Systematic Approach of a Flying Ad-hoc Network for Smart Cities
MAJOR ISSUES AND CHALLENGES IN FANET
Despite several technological advancements in UAVs, FANET still has many limitations, challenges,
issues, and other constraints that can affect the network’s performance. This section has shown some
issues, as depicted in Figure 5, and then significant challenges related to FANET are discussed. Al-
though many analysts and researchers have proposed different methods and techniques for improving
the utilization of FANET, due to its unique characteristics of UAVs (Gupta et al., 2016), FANET still
has many problems, issues and challenges.
High Mobility
In FANET, selecting appropriate mobility models is likewise a difficult task. Nodes in MANET always
travel in particular places, while VANET nodes move on the road, but FANET nodes fly in the sky,
which is quite far from the land. The mobility model is regular because UAVs follow a preset path in
some FANET applications (Bekmezci et al., 2013). Due to various mission modifications, the flight plan
is not predetermined (the plan is recalculated), directly impacting FANET’s mobility model.
High Reliability
The FANET environment can also assist in transmitting sensitive city information that requires untroubled
and secure data delivery in a timely and reliable manner. FANET achieves its reliability notion by build-
ing an ad hoc network between UAVs. UAVs’ communication links break or fail due to high speed of
Figure 5. FANET related issues

65
A Systematic Approach of a Flying Ad-hoc Network for Smart Cities
UAVs, regular topological changes, and vast distances between them. As a result, high reliability is also
a challenge in constructing any smart city in FANET (Zafar et al., 2017).
Routing
Routing protocols are the essential part of FANET for information dissemination between UAVs and
control all the data flow processes for UAVs and other connected devices. Although several state-of-the-
art routing approaches are already available for traditional ad-hoc networks like MANET and VANET,
these approaches partially fail in the FANETs environment because of the high speed of UAVs and the
highly dynamic nature of network topology (Wheeb et al., 2022; Rahmani et al., 2022). Consequently,
new efficient and effective path planning approaches are required to improve information sharing between
UAVs. Reliable and on-time delivery of rescue information is essential for mission-critical applications
like disaster rescue operations. A realistic network for UAV communication has become critical in de-
veloping trustworthy FANETs (Kumar et al., 2020c). Therefore, a stable and efficient routing protocol
with higher packet delivery, throughput, link duration time, bounded routing overhead, packet loss, and
communication delay are required.
Path Scheduling
During some critical FANET missions, each UAV may deviate from its earlier path due to dynamic and
atmospheric changes such as weather conditions, updating UAVs, fixed obstacles (mountains, high-rise
buildings), and active threats so on. A new path should be determined dynamically (Bekmezci et al.,
2013). Consequently, FANET requires specific novel approaches and techniques for dynamic path plan-
ning so that UAVs can connect, talk to one another and cooperate (Kumar et al., 2020b).
Quality of Service (QoS)
There are numerous applications for smart cities where FANET is used to transmit GPS location, complex
images, live videos, text files, and many more. However, UAV’s movement and link outage affect the
QoS metrics. As a result, efficient data delivery techniques and novel coding schemes are required to
improve real-time data quality services in such a network and address issues such as throughput, delay,
message transition rate, and packet loss (Zafar et al., 2017).
Size
Size is a significant factor when determining which UAV is best for a mission. One of the most funda-
mental challenges is the size of lightweight UAVs’ ability to carry a high-weight payload, which limits
UAVs’ ability to maintain an integrated system made up of numerous sensors, IoT devices, cameras,
and other components.
Security Issues
Ensuring confidentiality, availability, and integrity of information during the communication between
the UAVs, security is one of the significant issues faced by FANET (Chriki et al., 2019). Very small

66
A Systematic Approach of a Flying Ad-hoc Network for Smart Cities
UAVs or mini-UAVs are sometimes preferred in various FANET applications to address the security
issue. However, they are easily stolen, which is another issue. Furthermore, in some cases, unauthorized
individuals (hackers) may control a specific portion of UAVs or even an entire network. Therefore, there
is a need to resolve such issues by research-oriented task from the security point of view for FANET.
Energy Constraint
UAVs’ energy consumption in FANETs is one of the most critical challenges for time-taking missions.
Usually, UAVs are battery fuelled, which is utilized for various 3D on-board information dissemination
tasks like health or traffic monitoring in smart cities (Kumar et al., 2021a). On the other hand, due to
the limited battery lifetime, usually less than one hour, a decision must be made as to whether UAVs can
perform on-board data analysis or data should be stored for later analysis (Oubbati et al., 2019). Their
economic impact is more significant when UAVs can stay in the air for longer in FANET. For instance,
they can effectively carry out infrastructure surveillance while covering a greater region in 3D mapping
applications and delivering more information to farther-off locations. On the other hand, UAVs must
frequently return to the charging station for recharging when FANET is used to cover a big area.
Environment and Weather Condition
The environment and weather conditions are also necessary when operating UAVs in FANET. Weather
presents a challenging and critical task when natural or man-made disasters occur, such as tsunamis,
torrential rain, wildfires, or hurricanes. UAVs may fail to complete their missions in such instances due
to hazardous weather conditions (Thibbotuwawa et al., 2020). However, UAVs will be more effective if
they are not constrained by weather in time-sensitive tasks such as emergency response, law enforcement,
and package delivery. As a result, some sophisticated approaches are necessary for environmental and
weather unpredictability resistance.
NEW APPROACHES
Other advanced technologies and services, such as the internet of things (IoT) (Singh, 2018; Farhan et
al., 2021), machine learning (ML) (Mehta et al., 2022), artificial intelligence (AI) (Rawat et al., 2022),
cloud computing, reinforcement learning (RL) (Sutton et al., 1988), fog computing (Abdulkareem et
al., 2019), blockchain (Bhushan et al., 2020) and big data analytics (Kumar, 2016), are required for the
development and operation of innovative city services in addition to FANET. Many FANET applications
(Bujari et al., 2017; Srivastava and Prakash, 2021b) covered in this chapter require these technologies.
AI and ML Based FANET Technology
The significance of achieving low latency and quick data processing for real-time applications has
recently prompted the incorporation of AI and ML characteristics into revolutionary UAV technology
(Hameed et al., 2022). UAVs and machine learning have increased the ability to operate and monitor
activities from afar. AI-based solutions aid in the resolution of complicated challenges relating to many
elements of FANET. The advantages of AI in UAVs are numerous. FANET is also one of the exciting

67
A Systematic Approach of a Flying Ad-hoc Network for Smart Cities
new uses for next-generation wireless networks and fifth-generation (5G) wireless networks. In order
to extend the lifetime of a 5G network, lower energy consumption, and fewer broken links, authors
(Khan et al., 2020) proposed an AI-based strategy called reinforcement learning to identify the optimal
between nodes by taking UAVs with higher residual energy and stability into consideration. FANET’s
implementation of computational intelligence has lately gained popularity as a learning-based networking
technique that takes advantage of conscious nodes’ potential for learning to make smarter networking
decisions (Rovira-Sugranes et al., 2022). AI and ML based decision-making techniques play a vital role
in determining the effective and stable route in the networks and improving performance accordingly
(Wei et al., 2022). A powerful and effective solution that changed the analysis of big data gathered from
sensors and smart devices in smart cities is the combination of ML with UAV network technology.
Through its application in numerous fields, this technology can significantly raise the standard of living.
UAV-based communications in FANET can also benefit from machine learning approaches to improve
the design and functional features such as channel modelling, resource management, location, security,
and many more applications for smart cities. Table 1 shows the current AI and machine learning-based
routing algorithms.
Furthermore, with new technology trends, UAV networks are getting closer to urban areas, especially
people’s lives. However, due to the versatile nature of UAVs, information dissemination is the main
issue in FANET. Therefore, to maximize UAV connectivity and reduce the number of hops between
the source and target for data dissemination, the authors (He et al., 2020) presented fuzzy logic RL-
oriented routing approach. A practical and dependable network is required for remote management and
observation of mobile robotic equipment. To decrease routing overhead and message delivery ratio in
high-mobility scenarios, authors (Jung et al., 2017) developed a unique ML-based geographic routing
strategy termed QGeo. Furthermore, mobile robotic networks exhibit tremendous mobility; hence, cur-
rent routing paradigms frequently fail to adjust their decision-making to the inherent dynamics of the
network architecture. The PARRoT technique, a novel machine learning-enabled routing protocol that
utilises mobility control information for incorporating knowledge about the future motion of the mobile
agents into the routing process, was proposed by authors (Sliwa et al., 2021) to address these difficulties.
The suggested method increases robustness and reduces end-to-end delay.
Table 1. Recent AI and ML based routing approaches
References Proposed AI and ML based approaches
Jung et al., 2017 Q-learning oriented location routing approach
Khan et al., 2020 RL-based routing in 5G networks
He et al., 2020 Fuzzy Logic RL-based routing approach
Sliwa et al., 2021 A novel machine learning-enabled routing approach
Wei et al., 2022 A Boltzmann machine optimizing routing approach
Hameed et al., 2022 Biologically inspired dragonfly approach through ML
Rovira-Sugranes et al., 2022 Survey article on AI-enabled routing approaches

68
A Systematic Approach of a Flying Ad-hoc Network for Smart Cities
IoT based UAVs for FANET
The IoT is a network of physical devices that allows them to connect and exchange messages, including
sensors, actuators, and vehicles. IoT allows different physical devices in smart cities to be integrated into a
metropolitan network. IoT smart cities applications are smart city applications that are based on this type
of network. These applications operate by utilising IoT components and other required systems (Alsamhi
et al., 2019). UAVs have recently become one of the fastest-growing fields, with applications in various
industries (Qi et al., 2019). UAVs made up of small, low-power sensors play an essential role in the IoT.
These sensors are low-energy gadgets that cannot communicate over great distances. As a result, in an
IoT environment, UAVs act dynamically to collect data and deliver it to other devices beyond the range
of connection. Deployment at remote sites, the capacity to carry variable payloads, re-programmability
during activities, and the ability to sense anything from anywhere, especially in metropolitan areas, are
advantages of the UAV over IoT. Smart cities comprise intelligent things that can increase life quality,
save lives, and work as a sustainable resource ecosystem automatically and jointly (Mutlag et al., 2019).
To attain these sophisticated collaborative technologies, such as UAVs and IoT, smart cities must improve
their connection, energy efficiency, and quality of service (Alsamhi et al., 2019). IoT-based UAVs, also
known as Flying IoT in FANET, have several advantages, including reaching great heights, producing
high resolution photographs at a minimum cost, and responding rapidly in any situation. In addition, this
technology is used for monitoring sports and health care (Khan et al., 2021). Table 2 shows the most
recent developments in IoT-based UAVs for FANET.
Future Directions
Furthermore, due to recent technological advancements, the following key indicators (Table 3) can also
play a vital role in designing an intelligent infrastructure for smart cities via FANET.
Table 2. Recent IoT-based UAVs approaches for FANET
References Proposed IoTs based approaches
Datta et al., 2018 IoT-orinted UAV approach for emergency services
Motlagh et al., 2019 Task assignment approach for UAV-oriented IoT Platform
Labib et al., 2019 Internet of UAVs for traffic monitoring
Giyenko et al., 2019 Smart UAV placements in smart cities through IoT services
Alsamhi et al., 2019 Survey on collaborative UAVs and IoTs for improving of smart cities
Sheet et al., 2020 IoT-enabled UAV architecture for control system
Israr et al., 2021 IoT-enabled UAVs for inspection of constr uction sites

69
A Systematic Approach of a Flying Ad-hoc Network for Smart Cities
CONCLUSION
FANET technology will change the world and transform smart cities in the coming years due to the waste
utilisation of UAVs. FANET incorporates modern technological advancements such as the IoT, AI, ML,
Reinforcement Learning, Big Data, Cloud Computing, and many more. Combining with smart cities
will result in a sustainable and tranquil living environment. The systematic application areas of FANET
in smart cities were presented in this study. However, various unresolved issues and obstacles must be
considered with the development and application of FANET technology for smart cities. Further effort
is required in the future path of FANET in smart cities. Finally, FANET technology and smart cities can
hugely impact and benefit any country when applied correctly and efficiently.
REFERENCES
Abdulkareem, K. H., Mohammed, M. A., Gunasekaran, S. S., Al-Mhiqani, M. N., Mutlag, A. A., Mo-
stafa, S. A., Ali, N. S., & Ibrahim, D. A. (2019). A Review of Fog Computing and Machine Learning:
Concepts, Applications, Challenges, and Open Issues. IEEE Access: Practical Innovations, Open Solu-
tions, 7, 153123–153140. doi:10.1109/ACCESS.2019.2947542
Table 3. Future directions for smart cities through FANET
New direction Description
ü Flying IoT and Cloud-based solution UAVs are an emerging form of new flying IoT devices. The cloud-based solutions can
provide full network connectivity capabilities in FANET.
ü Fuzzy Logic based FANET solution Fuzzy Logic based routing solutions can improve the link connectivity between the
UAVs in FANET for emergency information dissemination.
ü Fuzzy Logic and UAV-based agriculture
monitoring
Agricultural UAVs with fuzzy logic based concepts are becoming tools for providing
farmers with a wealth of information about their crops and completing specific
farming missions promptly.
ü Secure framework for urban areas using
blockchain technology
A new security framework can integrate blockchain technology with smart devices
such as UAVs to provide a secure framework in an intelligent environment.
ü Blockchain-based architecture for the Internet
of Flying in urban areas
A blockchain-based distributed Internet of Flying network can improve the smart city
transportation system.
ü UAVs-assisted PHI collection of on-board
patient
UAVs equipped with various sensors can safely acquire real-time, high-resolution PHI
data from on-board patients.
ü ML-based UAV-assisted intelligent
transportation architecture
The combination of UAVs and machine learning offers a viable solution for
transportation monitoring in smart cities.
ü Fusion of FANET and RL in health
monitoring planning
Combined FANET and RL based scheme can facilitate improved monitoring and
timely medical services.
ü Fusion of UAVs and AI in public safety AI-based drone systems can act as CCTV cameras for public safety.
ü Fusion of FANET, AI and DL technology for
smart grid and combating pollution
AI and DL based techniques can enhance and improve the reliability and resilience
of smart grids and combat pollution systems with the help of UAV networks in urban
areas.
ü FANET and AI-based collaborative livelihood
approach for visually impaired public
The visually impaired public can take advantage of AI-based approaches and enhance
the communication between persons via the FANET environment.

70
A Systematic Approach of a Flying Ad-hoc Network for Smart Cities
Alsamhi, S. H., Ma, O., Ansari, M. S., & Almalki, F. A. (2019). Survey on Collaborative Smart Drones
and Internet of Things for Improving Smartness of Smart Cities. IEEE Access: Practical Innovations,
Open Solutions, 7, 128125–128152. doi:10.1109/ACCESS.2019.2934998
Arafat, M. Y., & Moh, S. (2018). Location-Aided Delay Tolerant Routing Protocol in UAV Networks for
Post-Disaster Operation (Vol. 6). Institute of Electrical and Electronics Engineers (IEEE). doi:10.1109/
ACCESS.2018.2875739
Ayyagari, A., Harrang, J. P., & Ray, S. (1996). Airborne information and reconnaissance network. Pro-
ceedings of MILCOM’96 IEEE Military Communications Conference, (pp. 230-234). IEEE. 10.1109/
MILCOM.1996.568619
Bekmezci, I., Sahingoz, O. K., & Temel, S. (2013). Flying Ad-Hoc Networks (FANETs): A survey. Ad
Hoc Networks, 11(3), 1254–1270. doi:10.1016/j.adhoc.2012.12.004
Bhushan, B., Khamparia, A., Sagayam, K. M., Sharma, S. K., Ahad, M. A., & Debnath, N. C. (2020).
Blockchain for smart cities: A review of architectures, integration trends and future research directions.
Sustainable Cities and Society, 61, 102360. doi:10.1016/j.scs.2020.102360
Bujari, A., Calafate, C. T., Cano, J. C., Manzoni, P., Palazzi, C. E., & Ronzani, D. (2017). Flying ad-
hoc network application scenarios and mobility models. International Journal of Distributed Sensor
Networks, 13(10), 155014771773819. doi:10.1177/1550147717738192
Chriki, A., Touati, H., Snoussi, H., & Kamoun, F. (2019). FANET: Communication, mobility models
and security issues. Computer Networks, 163, 106877. doi:10.1016/j.comnet.2019.106877
Datta, S. K., Dugelay, J. L., & Bonnet, C. (2018, October). IoT Based UAV Platform for Emergency
Services. 2018 International Conference on Information and Communication Technology Convergence
(ICTC). IEEE. 10.1109/ICTC.2018.8539671
Dhaka, M., Sharma, D. P., Sharma, S. K., & Dixit, A. (2021). An Analysis of Electronic Health Record
System in Healthcare Services in Cloud: A Review Perspective. International Conference on Computa-
tional Performance Evaluation (ComPE), (pp. 886-892). IEEE. 10.1109/ComPE53109.2021.9751995
Farhan, L., Hameed, R. S., Ahmed, A. S., Fadel, A. H., Gheth, W., Alzubaidi, L., Fadhel, M. A., & Al-
Amidie, M. (2021). Energy Efficiency for Green Internet of Things (IoT) Networks: A Survey. Network
(Bristol, England), 1(3), 279–314. doi:10.3390/network1030017
Giyenko, A., & Cho, Y. I. (2016, October). Intelligent UAV in smart cities using IoT. 2016 16th Interna-
tional Conference on Control, Automation and Systems (ICCAS). IEEE. 10.1109/ICCAS.2016.7832322
Goodchild, A., & Toy, J. (2018). Delivery by drone: An evaluation of unmanned aerial vehicle technology
in reducing CO 2 emissions in the delivery service industry. Transportation Research Part D, Transport
and Environment, 61, 58–67. doi:10.1016/j.trd.2017.02.017
Greenwood, W. W., Lynch, J. P., & Zekkos, D. (2019). Applications of UAVs in Civil Infrastructure.
Journal of Infrastructure Systems, 25(2), 04019002. doi:10.1061/(ASCE)IS.1943-555X.0000464
Grizhnevich, A. (2021, July 20). IoT for Smart Cities: Use Cases and Implementation Strategies. Sci-
enceSoft. https://www.scnsoft.com/blog/iot-for-smart-city-use-cases-approaches-outcomes

71
A Systematic Approach of a Flying Ad-hoc Network for Smart Cities
Ham, Y., Han, K. K., Lin, J. J., & Golparvar-Fard, M. (2016). Visual monitoring of civil infrastructure
systems via camera-equipped Unmanned Aerial Vehicles (UAVs): A review of related works. Visualiza-
tion in Engineering, 4(1), 1. doi:10.118640327-015-0029-z
Hameed, S., Minhas, Q. A., Ahmad, S., Ullah, F., Khan, A., Khan, A., Uddin, M. I., & Hua, Q. (2022).
Connectivity of Drones in FANETs Using Biologically Inspired Dragonfly Algorithm (DA) through Ma-
chine Learning. Wireless Communications and Mobile Computing, 2022, 1–11. doi:10.1155/2022/5432023
He, C., Liu, S., & Han, S. (2020, February). A Fuzzy Logic Reinforcement Learning-Based Routing
Algorithm For Flying Ad Hoc Networks. 2020 International Conference on Computing, Networking
and Communications (ICNC). IEEE. 10.1109/ICNC47757.2020.9049705
Israr, A., Abro, G. E. M., Sadiq Ali Khan, M., Farhan, M., & Bin Mohd Zulkifli, S. A. (2021). Internet
of Things (IoT)-Enabled Unmanned Aerial Vehicles for the Inspection of Construction Sites: A Vision
and Future Directions. Mathematical Problems in Engineering, 2021, 1–15. doi:10.1155/2021/9931112
Jo, J., Jo, B., Kim, J., Kim, S., & Han, W. (2020). Development of an IoT-Based Indoor Air Quality
Monitoring Platform. Journal of Sensors, 2020, 1–14. doi:10.1155/2020/8749764
Joshi, S., Saxena, S., Godbole, T., & Shreya. (2016). Developing Smart Cities: An Integrated Framework.
Procedia Computer Science, 93, 902–909. doi:10.1016/j.procs.2016.07.258
Jung, W. S., Yim, J., & Ko, Y. B. (2017). QGeo: Q-Learning-Based Geographic Ad Hoc Routing Proto-
col for Unmanned Robotic Networks. IEEE Communications Letters, 21(10), 2258–2261. doi:10.1109/
LCOMM.2017.2656879
Khan, A., Aftab, F., & Zhang, Z. (2019). UAPM: An urgency-aware packet management for disaster
management using flying ad-hoc networks. China Communications, 16(11), 167–182. doi:10.23919/
JCC.2019.11.014
Khan, I. U., Hassan, M. A., Alshehri, M. D., Ikram, M. A., Alyamani, H. J., Alturki, R., & Hoang, V. T.
(2021). Monitoring System-Based Flying IoT in Public Health and Sports Using Ant-Enabled Energy-Aware
Routing. Journal of Healthcare Engineering, 2021, 1–11. doi:10.1155/2021/1686946 PMID:34306586
Khan, M. F., & Yau, K. L. A. (2020, August). Route Selection in 5G-based Flying Ad-hoc Networks
using Reinforcement Learning. 2020 10th IEEE International Conference on Control System, Comput-
ing and Engineering (ICCSCE). IEEE. 10.1109/ICCSCE50387.2020.9204944
Khan, N. A., Jhanjhi, N., Brohi, S. N., Usmani, R. S. A., & Nayyar, A. (2020). Smart traffic moni-
toring system using Unmanned Aerial Vehicles (UAVs). Computer Communications, 157, 434–443.
doi:10.1016/j.comcom.2020.04.049
Khanna, A., & Anand, R. (2016). IoT based smart parking system. International Conference on Internet
of Things and Applications (IOTA), (pp. 266-270). IEEE. 10.1109/IOTA.2016.7562735
Khare, M., Gupta, S., Rathore, A. S., Tunwal, B., Kumar, S. & Rathore, N. K. (2022). FANETs in Wild-
life Monitoring: Applications and Challenges. i-Manager’s Journal on Electronics Engineering,12(4),
27-35. doi:10.26634/jele.12.4.19105

72
A Systematic Approach of a Flying Ad-hoc Network for Smart Cities
Kumar, S. (2016, December 28–29). A survey of Research Challenges in Big Data Era [Paper presenta-
tion]. 2nd International Conference on Computers and Management (ICCM-2016), Kota, Rajasthan, India.
Kumar, S., & Bansal, A. (2020b). Performance Investigation of Topology-Based Routing Protocols in
Flying Ad-Hoc Networks Using NS-2. In R. Rao, V. Jain, O. Kaiwartya, & N. Singh (Eds.), IoT and Cloud
Computing Advancements in Vehicular Ad-Hoc Networks (pp. 243–267). IGI Global. doi:10.4018/978-
1-7998-2570-8.ch013
Kumar, S., Bansal, A., & Raw, R. S. (2020a). Health Monitoring Planning for On-Board Ships Through
Flying Ad Hoc Network. In: Pati, B., Panigrahi, C., Buyya, R., Li, KC. (Ed.) Advanced Computing and
Intelligent Engineering. Advances in Intelligent Systems and Computing, 1089 (pp. 391-402). Springer,
Singapore. doi:10.1007/978-981-15-1483-8_33
Kumar, S., Bansal, A., & Raw, R. S. (2020c). Analysis of Effective Routing Protocols for Flying Ad-Hoc
Networks. [IJSVST]. International Journal of Smart Vehicles and Smart Transportation, 3(2), 1–18.
doi:10.4018/IJSVST.2020070101
Kumar, S., Rathore, N. K., Prajapati, M & Sharma, S. K. (2022). SF-GoeR: an emergency information
dissemination routing in flying ad-hoc network to support healthcare monitoring, Journal of Ambient
Intelligence and Humanize Computing, Springer Nature. doi:10.1007/s12652-022-04434-3
Kumar, S., & Raw, R. S. (2018). Improvement of Railway Transportation System Using IoT Applica-
tions and Services. In B. Mishra & R. Kumar (Eds.), Big Data Management and the Internet of Things
for Improved Health Systems (pp. 120–141). IGI Global. doi:10.4018/978-1-5225-5222-2.ch008
Kumar, S., & Raw, R. S. (2018) Flying Ad-Hoc Networks (FANETs): Current State, Challenges and
Potentials. 12th INDIACom-2018, 5th International Conference on Computing for Sustainable Global
Development, (pp. 4233-4238). IEEE.
Kumar, S., Raw, R. S., & Bansal, A. (2021a). Minimize the routing overhead through 3D cone shaped
location-aided routing protocol for FANETs. International Journal of Information Technology, 13(1),
89–95. doi:10.100741870-020-00536-3
Kumar, S., Raw, R. S., & Bansal, A. (2021c). Energy and Direction Aware Routing Protocol for Flying
Ad Hoc Networks. In S.K. Sabut, A.K. Ray, B. Pati, & U.R. Acharya (Eds) Proceedings of International
Conference on Communication, Circuits, and Systems. Lecture Notes in Electrical Engineering, 728 (pp.
371-378). Springer, Singapore. 10.1007/978-981-33-4866-0_46
Kumar, S., Raw, R. S., & Bansal, A. (2023). LoCaL: Link-oriented cone-assisted location routing in flying
ad hoc networks. International Journal of Communication Systems, 36(2), e5375. doi:10.1002/dac.5375
Kumar, S., Raw, R. S., Bansal, A., Mohammed, M. A., Khuwuthyakorn, P., & Thinnukool, O. (2021b).
3D Location Oriented Routing in Flying Ad-Hoc Networks for Information Dissemination. IEEE Ac-
cess: Practical Innovations, Open Solutions, 9, 137083–137098. doi:10.1109/ACCESS.2021.3115000
Labib, N. S., Danoy, G., Musial, J., Brust, M. R., & Bouvry, P. (2019). Internet of Unmanned Aerial
Vehicles—A Multilayer Low-Altitude Airspace Model for Distributed UAV Traffic Management. Sen-
sors (Basel), 19(21), 4779. doi:10.339019214779 PMID:31684133

73
A Systematic Approach of a Flying Ad-hoc Network for Smart Cities
Mahgoub, A., Tarrad, N., Elsherif, R., Ismail, L., & Al-Ali, A. (2020). Fire Alarm System for Smart
Cities Using Edge Computing. 2020 IEEE International Conference on Informatics, IoT, and Enabling
Technologies (ICIoT). 10.1109/ICIoT48696.2020.9089653
Martínez-Pérez, B., de la Torre-Díez, I., & López-Coronado, M. (2013). Mobile Health Applications
for the Most Prevalent Conditions by the World Health Organization: Review and Analysis. Journal of
Medical Internet Research, 15(6), e120. doi:10.2196/jmir.2600 PMID:23770578
Mehta, S., Bhushan, B., & Kumar, R. (2022). Machine Learning Approaches for Smart City Applications:
Emergence, Challenges and Opportunities. In V. E. Balas, V. K. Solanki, & R. Kumar (Eds.), Recent
Advances in Internet of Things and Machine Learning. Intelligent Systems Reference Library (Vol. 215,
pp. 147–163). Springer. doi:10.1007/978-3-030-90119-6_12
Mohanty, A., Mohanty, S. K., Jena, B., Mohapatra, A. G., Rashid, A. N., Khanna, A., & Gupta, D.
(2022). Identification and evaluation of the effective criteria for detection of congestion in a smart city.
IET Communications, 16(5), 560–570. doi:10.1049/cmu2.12344
Motlagh, N. H., Bagaa, M., & Taleb, T. (2019). Energy and Delay Aware Task Assignment Mecha-
nism for UAV-Based IoT Platform. IEEE Internet of Things Journal, 6(4), 6523–6536. doi:10.1109/
JIOT.2019.2907873
Mukhopadhyay, A., & Ganguly, D. (2020). FANET based Emergency Healthcare Data Dissemination.
2020 Second International Conference on Inventive Research in Computing Applications (ICIRCA).
IEEE. 10.1109/ICIRCA48905.2020.9183223
Mutlag, A. A., Abd Ghani, M. K., Arunkumar, N., Mohammed, M. A., & Mohd, O. (2019). Enabling
technologies for fog computing in healthcare IoT systems. Future Generation Computer Systems, 90,
62–78. doi:10.1016/j.future.2018.07.049
Oubbati, O. S., Lakas, A., Zhou, F., Güneş, M., & Yagoubi, M. B. (2017). A survey on position-based
routing protocols for Flying Ad hoc Networks (FANETs). Vehicular Communications, 10, 29–56.
doi:10.1016/j.vehcom.2017.10.003
Qi, F., Zhu, X., Mang, G., Kadoch, M., & Li, W. (2019). UAV Network and IoT in the Sky for Future
Smart Cities. IEEE Network, 33(2), 96–101. doi:10.1109/MNET.2019.1800250
Radu, D., Cretu, A., Avram, C., Astilean, A., & Parrein, B. (2018b). Video content transmission in a
public safety system model based on flying Ad-hoc networks. 2018 IEEE International Conference on
Automation, Quality and Testing, Robotics (AQTR). IEEE. 10.1109/AQTR.2018.8402713
Radu, D., Cretu, A., Parrein, B., & Yi, J. (2018a). Flying Ad Hoc Network for Emergency Applications
connected to a Fog System. Emerging Internet, Data & Web Technologies (EIDWT), (pp.675-686),
Tirana, Albania. doi:. ffhal-01763827 doi:10.1007/978-3-319-75928-9_60ff
Rahmani, M. R., Ali, S., Yousefpoor, E., Yousefpoor, M. S., Javaheri, D., Lalbakhsh, P., Ahmed, O. H.,
Hosseinzadeh, M., & Lee, S.-W. (2022). OLSR+: A new routing method based on fuzzy logic in flying ad-
hoc networks (FANETs). Vehicular Communications, 36(6), 100489. doi:10.1016/j.vehcom.2022.100489

74
A Systematic Approach of a Flying Ad-hoc Network for Smart Cities
Rawat, B., Bist, A. S., Apriani, D., Permadi, N. I., & Nabila, E. A. (2022). AI Based Drones for Security
Concerns in Smart Cities. [ATM]. APTISI Transactions on Management, 7(2), 125–130. doi:10.33050/
atm.v7i2.1834
Rovira-Sugranes, A., Razi, A., Afghah, F., & Chakareski, J. (2022). A review of AI-enabled routing
protocols for UAV networks: Trends, challenges, and future outlook. Ad Hoc Networks, 130, 102790.
doi:10.1016/j.adhoc.2022.102790
S., Kumar, S., Sharma, S. K., Ahmad, S. K. & Singh, P. (2022). Simulation-based performance evalua-
tion of VANET routing protocols under Indian traffic scenarios. ICIC Express Letters,16(1), pp. 67–74.
doi:10.24507/icicel.16.01.67
Salvo, G., Caruso, L., & Scordo, A. (2014). Urban Traffic Analysis through an UAV. Procedia: Social
and Behavioral Sciences, 111, 1083–1091. doi:10.1016/j.sbspro.2014.01.143
Shakhatreh, H., Sawalmeh, A. H., Al-Fuqaha, A., Dou, Z., Almaita, E., Khalil, I., Othman, N. S., Khre-
ishah, A., & Guizani, M. (2019). Unmanned Aerial Vehicles (UAVs): A Survey on Civil Applications
and Key Research Challenges. IEEE Access: Practical Innovations, Open Solutions, 7, 48572–48634.
doi:10.1109/ACCESS.2019.2909530
Sheet, A., al Bazzaz, F., Bashi, O., & Al-Dabagh, M. (2020). IoT Based UAV Platform for Far Distance
control system. Proceedings of the Proceedings of the 1st International Multi-Disciplinary Conference
Theme: Sustainable Development and Smart Planning. IEEE. 10.4108/eai.28-6-2020.2297949
Siddiqi, M. H., Draz, U., Ali, A., Iqbal, M., Alruwaili, M., Alhwaiti, Y., & Alanazi, S. (2021). FANET:
Smart city mobility off to a flying start with self‐organized drone‐based networks. IET Communications.
Advance online publication. doi:10.1049/cmu2.12291
Singh, P. (2018). Internet Of Things Based Health Monitoring System: Opportunities And Challenges.
International Journal of Advanced Research in Computer Science, 9(1), 224–228. doi:10.26483/ijarcs.
v9i1.5308
Sliwa, B., Schuler, C., Patchou, M., & Wietfeld, C. (2021, April). PARRoT: Predictive Ad-hoc Routing
Fueled by Reinforcement Learning and Trajectory Knowledge. 93rd Vehicular Technology Conference
(VTC2021-Spring). IEEE. 10.1109/VTC2021-Spring51267.2021.9448959
Sripath Roy, K., Sowmya, S., Manasa, M., Alekhya, D., & Abhinav, P. (2018). Decentralized weather
monitoring system for smart cities. International Journal of Engineering & Technology, 7(2.20), 67.
doi:10.14419/ijet.v7i2.20.11755
Srivastava, A., & Prakash, J. (2021a). Future FANET with application and enabling techniques: Anatomiza-
tion and sustainability issues. Computer Science Review, 39, 100359. doi:10.1016/j.cosrev.2020.100359
Srivastava, A., & Prakash, J. (2021b). Role of Antenna in Flying Adhoc Networks Communication:
Provocation and Open Issues. In A. Abraham, V. Piuri, N. Gandhi, P. Siarry, A. Kaklauskas, & A. Madu-
reira (Eds.), Intelligent Systems Design and Applications. ISDA 2020. Advances in Intelligent Systems
and Computing (Vol. 1351, pp. 711–721). Springer., doi:10.1007/978-3-030-71187-0_65

75
A Systematic Approach of a Flying Ad-hoc Network for Smart Cities
Sutton, R. S., & Barto, A. G. (1988). Reinforcement learning: An introduction. IEEE Transactions on
Neural Networks, 16, 285–286.
Thibbotuwawa, A., Bocewicz, G., Radzki, G., Nielsen, P., & Banaszak, Z. (2020). UAV Mission Planning
Resistant to Weather Uncertainty. Sensors (Basel), 20(2), 515. doi:10.339020020515 PMID:31963338
Trindade, E. P., Hinnig, M. P. F., da Costa, E. M., Marques, J. S., Bastos, R. C., & Yigitcanlar, T. (2017).
Sustainable development of smart cities: A systematic review of the literature. Journal of Open Innova-
tion, 3(1), 11. Advance online publication. doi:10.118640852-017-0063-2
Wei, X., Huang, W., & Yang, H. (2022). A Boltzmann machine optimizing dynamic routing for FANETs.
Soft Computing, 26(22), 12385–12391. doi:10.100700500-022-07104-w
Wheeb, A. H. (2022). Flying Ad hoc Networks (FANET): Performance Evaluation of Topology Based
Routing Protocols. [iJIM]. International Journal of Interactive Mobile Technologies, 16(04), 137–149.
doi:10.3991/ijim.v16i04.28235
Zafar, W., & Khan, B. M. (2017). A reliable, delay bounded and less complex communication protocol for
multicluster FANETs. Digital Communications and Networks, 3(1), 30–38. doi:10.1016/j.dcan.2016.06.001
Zhou, J., Yang, J., & Lu, L. (2020). Research on Multi-UAV Networks in Disaster Emergency Communi-
cation. IOP Conference Series. Materials Science and Engineering, 719(1), 012054. doi:10.1088/1757-
899X/719/1/012054