IoT Devices Overhead: A Simulation Study of eHealth Solutions over

a Hospitals’ Network

Gabriel Krauss Costa

1 a

, Edvard Martins de Oliveira

1 b

, M

ario Henrique Souza Pardo

2 c

Universidade Federal de Itajub

a, Brazil

Faculdade de Tecnologia do Estado de S

ao Paulo, Brazil

Keywords:

Internet of Things, eHealth, Network Overload, Load Balance, Computational Simulation.

Abstract:

As Internet of Thing (IoT) applications for eHealth gain momentum, one aspect becomes critical: the underly-

ing network infrastructure. The efﬁcient operation of interconnected devices hinges upon a robust and reliable

network architecture, that can present formidable barriers to IoT’s potential. In this paper we analyze the

capacity of a typical hospital network infrastructure to implement new eHealth solutions, given the number of

devices required in a average setup. We use the IFogSim Simulator to model a network setup for a hospital,

selecting parameters for the devices from state-of-the-art solutions. This work is an important investigation on

the overload a collection of IoT devices may cause in a common network setup, and could be used for planning

ahead the installation of eHealth solutions. Our results show that a realistic arrange for IoT solutions might

impact signiﬁcantly the network ﬂow, energy consumption and processing time. Also, the number of gateways

reﬂects on the working capacity of the general system, turning from a distribution point to a bottleneck. The

environment provides a reliable representation, allowing the extrapolation of the scenarios.

1 INTRODUCTION

The advent of the Internet of Things (IoT) has ushered

in a new era of technological advancements, revolu-

tionizing various sectors, including healthcare. The

integration of IoT technologies within the healthcare

domain, known as eHealth, has introduced novel and

transformative opportunities to enhance patient care,

streamline clinical processes, and optimize resource

utilization (Gupta and Quamara, 2020). In particu-

lar, the installation of IoT devices in health clinics

and hospitals holds the promise of real-time monitor-

ing, data-driven decision-making, and improved pa-

tient outcomes.

As the number of IoT devices in healthcare grows,

so does the potential for network congestion and per-

formance issues (Puliaﬁto et al., 2019). Developing

countries often grapple with limited network band-

width, intermittent connectivity, and inadequate in-

frastructure (Wu et al., 2019).

Effective resource allocation within eHealth net-

works is essential to prioritize critical data and tasks.

https://orcid.org/0009-0002-3466-406X

https://orcid.org/0000-0002-2842-2155

https://orcid.org/0000-0001-8457-0753

Network overheads, for characteristics as latency and

packet loss, can jeopardize the ability to provide real-

time care, potentially leading to adverse patient out-

comes. Also, scalability is a signiﬁcant concern, as

the infrastructure must accommodate more devices

without degradation in performance (Puliaﬁto et al.,

2019). Other aspects that require attention, but that

are beyond the scope of this paper are legal regula-

tions, security, privacy, data volume and devices vari-

ety.

This study focuses on analyzing the impact of IoT

devices on network performance. A realistic simula-

tion environment is created with IFogSim (Mahmud

et al., 2021), incorporating various IoT devices, such

sensors, gateways, and data processing units. Sim-

ulation techniques assess the potential network bot-

tlenecks, latency issues, and data transfer constraints

that could emerge in real-world scenarios (Castane

et al., 2019).

To assess the network overhead, a variety of sce-

narios is designed, considering factors such as the

number of IoT devices, data transmission rates, and

trafﬁc patterns. Performance metrics includes net-

work latency, energy consumption, and processing

time, measured under different workload conditions.

he experiment also seeks to validate the effective-

176

Costa, G., Martins de Oliveira, E. and Souza Pardo, M.

IoT Devices Overhead: A Simulation Study of eHealth Solutions over a Hospitals’ Network.

DOI: 10.5220/0012631400003711

Paper published under CC license (CC BY-NC-ND 4.0)

In Proceedings of the 14th International Conference on Cloud Computing and Services Science (CLOSER 2024), pages 176-183

ISBN: 978-989-758-701-6; ISSN: 2184-5042

ness of the IFogSim framework in evaluating scenar-

ios within an eHealth context.

The experimental results demonstrate how vary-

ing the number of IoT devices, network overload,

bandwidth, and energy usage impacts the perfor-

mance of simulated eHealth IoT system. Also, it

helps observing the scalability and efﬁciency of com-

puter networks in health facilities when supporting

IoT-based monitoring services.

Through these scenarios, the experiment validate

IFogSim’s ability to accurately provide insights into

system behavior under different conditions.

Subsequent sections of this paper are organized as

follows: in Section 2 the related works are presented

and compared. Section 3 presents methodology, ma-

terials and modiﬁcations made on IFogSim. Section

4 shows the results and discussion on the experiments

ﬁnds. Finally, in Section 5 are described the conclu-

sion and future directions of this research.

2 RELATED WORK

The integration of Internet of Things (IoT) tech-

nologies in health facilities has revolutionized patient

monitoring services, leading to improved healthcare

outcomes. However, the deployment of IoT devices

introduces additional computational and communica-

tion requirements, potentially increasing the overhead

on computer networks (Gupta and Quamara, 2020).

The study in (Premkumar and Santhosh, 2022) high-

lights insufﬁcient eHealth readiness among managers

and healthcare workers. It emphasizes the impor-

tance of careful planning, execution, and monitor-

ing of eHealth initiatives to overcome obstacles and

threats.

There are several studies on the use of computer

supported technologies for fast diagnostic, precise

monitoring and data availability. In (Lv et al., 2022) is

proposed a intelligent system for prevention of infec-

tious diseases. It uses edge algorithms to generate a

model for low cost prevention strategies and enhanced

security. The authors present a generous evaluation of

their model, failing to demonstrate how the security of

patients is guaranteed.

The article (Steele and Lo, 2013) addresses the

challenges of limited bandwidth in rural and remote

areas for traditional telehealth applications, proposing

ubiquitous computing as a solution, highlighting their

potential to address healthcare challenges in such re-

gions.

The work of (Mishra et al., 2022) argues that in-

teroperability is the most challenging aspect of the

health care industry. The authors propose a system to

access, analyze, and enhance communication of pa-

tient health information while ensuring data privacy

and security. Their framework is proposed with lim-

ited functionalities and further research is expected.

The paper (Banday and Bhat, 2022) introduces a

eHealth model tailored for Neglected Tropical Dis-

eases (NTD). This type of disease is prevalent on

developing countries and such system would greatly

beneﬁt patients otherwise relegated by the major

research centers. Also, developing countries lack

well structured networks, helping understand why the

overload prediction is necessary prior to the installa-

tion of complex eHealth solutions.

The work in (Ahmed et al., 2020) presents a so-

lution using Genetic Algorithm (GA) to optimize en-

ergy consumption in Cloud IoT with numerical sim-

ulations demonstrating that the proposed approach

achieves better energy efﬁciency in handling task re-

quests, although they don’t consider the impact of the

number of devices per interaction.

An IoT-enabled deep learning framework for

breast image classiﬁcation is shown in (Gezimati and

Singh, 2023), achieving high accuracy, sensitivity,

and speciﬁcity, demonstrating its potential in health-

care applications, pointing to another example of

IoT capacities. However, detailing on the network

and power impact could be beneﬁcial to potential

adopters.

The authors in (Su et al., 2022) propose a edge

computing-based network architecture to improve the

performance of wireless body area network (WBAN)

for healthcare applications. They argue for better

Quality of Service (QoS) and Quality of Experience

(QoE) namely with latency and low energy, but their

ﬁndings for those metrics are not described. Simula-

tion has also been used to model other types of com-

plex scenarios.

The work on (Puliaﬁto et al., 2020) describes a

solution to overcome ﬂaws on mobility and service

migration for fog computing. Their results encourage

new approaches on resource provision projections.

The rise in connected IoT devices results in a sig-

niﬁcant increase in data volume, demanding real-time

responses and incurring high bandwidth costs.Various

studies focus on data collection strategies, including

remote monitoring, pre-processing, compression, and

ﬁltering, to alleviate bandwidth demands (Vilela et al.,

2020).

To the best of our knowledge, there are no simi-

lar approaches to evaluate the impact of eHealth solu-

tions on computer networks. We aim to contribute to

the literature with a model to estimate the capability

of installation of IoT devices and predict the network

behavior.

IoT Devices Overhead: A Simulation Study of eHealth Solutions over a Hospitals’ Network

177

3 METHODS

Developing countries often grapple with limited net-

work bandwidth, intermittent connectivity, and inade-

quate infrastructure, that can impede the deployment

and functionality of IoT devices (Yousaf et al., 2021).

This paper aims to shed light on these challenges and

propose using the IFogSim simulator, a cutting-edge

tool designed to simulate and analyze the deployment

of IoT devices to eHealth environments. Fog comput-

ing, characterized by decentralized data processing at

the edge of the network, holds promise in alleviating

the strain on centralized cloud resources and address-

ing network-related challenges (Puliaﬁto et al., 2019).

The necessity to address these challenges has

given rise to the application of simulation tools, such

as IFogSim, to comprehensively assess the deploy-

ment of IoT devices in healthcare settings. This sec-

tion presents arguments for the use of IFogSim, elu-

cidating its setup, importance, capacities, and the ex-

pected results it offers in terms of optimizing IoT de-

ployments for enhanced eHealth outcomes. This not

only enhances the likelihood of successful deploy-

ments but also helps preemptively identify and ad-

dress network-related bottlenecks.

The simulated environment’s classiﬁcation as

eHealth is primarily deﬁned by the integration of mul-

tiple IoT virtual devices. These devices are speciﬁ-

cally tailored to monitor ambient temperature and hu-

midity, crucial parameters managed across two dis-

tinct levels adhering to regulatory protocols and hos-

pital quality benchmarks. This infrastructure enables

the leveraging of information technologies to ensure

ongoing quality assurance and safety measures for

both staff and patients, aligning with the World Health

Organization’s (WHO) delineation of eHealth.

To evaluate the installation of IoT devices in

healthcare institutions, two simulators were analyzed:

IFogSim and IotSim Osmosis (Alwasel et al., 2021),

both implemented as extension to CloudSim (Cal-

heiros et al., 2011). The three simulators have very

similar characteristics as they have resources and

tools necessary to research, including computational

network modeling and integration of IoT sensors.

Initially, IoTSim Osmosis stood out due to its

large number of examples and base data provided by

the developer, easing the understanding of its struc-

ture, in addition to assisting in system conﬁguration.

It was used to structure and simulate the modeling of

a computational network, to send data from sensors

to processing at the edge and cloud layers. However,

when carrying out a deeper analysis of the simulator,

modeling the desired eHealth scenarios became un-

feasible, as the framework is tailored for cloud con-

tinuum applications. It is suited for IoT environments,

however its structure was found to be more rigid, with

static simulation features and harder to adapt. It has

fewer protocols and device emulation support, and

limitations in scalability for large-scale IoT deploy-

ments. Additionally, it may face challenges in ac-

curately replicating certain environmental factors or

hardware interactions (Al-Khafaji, 2022).

Changing the focus to IFogSim paid of, as it has

a simulation element for low-level infrastructure, en-

abling end-to-end modeling from user-level applica-

tions to edge computing of IoT environments, includ-

ing sensors and actuators.

3.1 The Simulator

The IFogSim simulator provides a realistic frame-

work to model and assess the network overhead in

healthcare environments (Mahmud et al., 2021).

The framework is designed to emulate the de-

ployment of IoT devices within fog computing en-

vironments, offering an invaluable platform for as-

sessing the intricate interplay between devices, net-

work infrastructure, and data processing. Leverag-

ing the principles of edge computing, IFogSim en-

ables the modeling of dynamic interactions among de-

vices, fog nodes, and cloud resources. It facilitates the

prediction of performance metrics, network latency,

and data transfer efﬁciency, thus providing a holistic

perspective on the real-world implications (Mahmud

et al., 2021).

IFogSim considers the distribution of processing

tasks across fog nodes and cloud servers. It accounts

for mobility patterns of IoT devices and offers in-

sights into data processing latency (Mahmud et al.,

2021). It offers a controlled and repeatable environ-

ment for experimentation and to take informed deci-

sions before physical implementation.

Furthermore, IFogSim accommodates the mod-

eling of mobility patterns, network topology, and

data dissemination strategies, allowing for a compre-

hensive analysis of IoT ecosystems (Mahmud et al.,

2021).

Despite the signiﬁcance of these factors in com-

puter network design, we focused our experiments

exclusively on analyzing network topology. Mobil-

ity and location principles were deliberately excluded,

earmarked for future investigations. As a result, our

experiment centered solely on devices within the hos-

pital’s physical conﬁnes.

IFogSim offers a controlled yet intricate platform

for evaluating IoT device deployments in healthcare

settings. Difﬁculties were encountered in understand-

ing the simulator classes and behavior, indicating that

CLOSER 2024 - 14th International Conference on Cloud Computing and Services Science

178

better documentation and code refactoring are wel-

come to future releases.

3.2 Models Development

Development of the simulated environment follows

the code available as examples in IFogSim packages

(Mahmud et al., 2021). The implementation is de-

rived from the TwoApps example, which implements

the simulation of two virtual reality game applications

(VR Games) aimed to verify its performance. The

new model is named OneApp, consisting of a sin-

gle application for an automated hospital environment

with IoT devices and a limited structure of data com-

munication resources at its digital network.

The main class is createApplication, responsible

for adjusting the network parameter and processing

load as the sensors generates data. Additionally, the

class also adjusts the transmission costs between lay-

ers, e.g. networking usage and processing time for the

sensors to transmit information to IoT devices.

The simulator has an general topology to indicate

the type of equipment created and the network struc-

ture. However, the main class assigns the relation

among the devices. Therefore, the devised module

describes the connections so that each Iot device is

linked to four different sensors. Here are also mod-

eled the gateways, proxy server and cloud environ-

ment, with the respective connections and data ﬂow.

The modules developed operates according to the

scheme represented in Figure 1. The sensors trans-

mit data to the IoT devices, which redirect them to

the gateways. Each gateway acts as an intermedi-

ary, routing data to a cloud server, where it is pro-

cessed and transmitted back to the IoT devices. The

organization represents a simpliﬁed hierarchy of real

world implementation for and eHealth installation on

a health clinic.

To emulate the sensors, versatile models like the

DHT22 were chosen for utilization in hospital en-

vironments, as well as the sensors ZMPT101B and

SCT-013 for monitoring equipment’s electrical net-

works. This approach allows for comprehensive anal-

ysis of environmental conditions and equipment per-

formance (Woo et al., 2018). The strategic choice

of sensors facilitates detection of system failures and

overloads, especially in settings with numerous inter-

connected devices, providing assessment of interop-

erability and equipment stability.

The description of the equipment modeled in the

simulator, along with its parameters is presented in

Table 1. To ﬁll the missing information in the techni-

cal sheets, the examples provided at (Mahmud et al.,

2021) were useful in estimating values, such as the en-

Figure 1: Infographic of components organization, modeled

on IFogSim. The data is collected on sensors, either direct

on patients or on the environment. It is transmitted to IoT

devices, and next sent to gateways. The last route the data

to cloud servers, responsible for heavier computations.

ergy consumption of some equipment. The respective

references for each machine conﬁguration are listed.

After consolidating the data relating to the de-

vices, the conﬁguration of the simulator is ready to

model a hospital network. This process served as

an initial foundation to execute the experiments with

variations to validate its portrayal of the real world.

3.3 Materials

The experiment environment was conﬁgured on

IFogSim version 2 (Mahmud et al., 2021). The toolkit

offers the following options: mobility-support, mi-

gration management, microservice orchestration, dy-

namic distributed clustering and healthcare scenarios.

Code available on github.com/GabrielKrauss/iFogSim-

IoT.

IoT Devices Overhead: A Simulation Study of eHealth Solutions over a Hospitals’ Network

179

Table 1: Devices description in the IFogSim simulation.

Each device is modeled according to the speciﬁcation in the

reference.

Device type Speciﬁcation

Gateway Raspberry Pi 4 (RaspberryPi, 2019)

IoT Device ESP32 (Google, 2023)

Cloud Host Intel Xeon E5-2696 v4 @ 2.20GHz (PassMark Software, 2023)

Proxy EGW-5200 (Dell, 2022)

Sensors

Temperature DHT22 (Aosong Eletronics, 2023)

Humidity DHT22

Voltage ZMPT101B (InnovatorsGuru, 2023)

Current SCT-013 (DataSheet39.com, 2023)

As test-bed for the experiments were used a

desktop computer with Intel Core i5-10400 CPU @

2.90GHz, 8 GB-RAM, 240 GB SSD. The Operation

System is Windows 10 64 bit.

3.4 Experiment Design

Having deﬁned the setup for the simulator, it’s nec-

essary to choose parameters to compose an evalua-

tion scenario. The parameters are listed in Table 2.

We chose to analyze the network behavior at differ-

ent conﬁgurations of the number of IoT devices, the

amount of energy consumption and the network us-

age. These details are fundamental for infrastructure

estimation and could greatly impact on the perfor-

mance of an complex eHealth system.

Clearly, there are many other parameters that

could be analyzed into a eHealth environment. Our

aim is to focus on network occupation and energy us-

age as those are the functional basis of computational

communication.

Table 2: Experiments detailing for 8 different scenarios. La-

bels: MJ = Mega joules, MB = Megabytes.

Energy Consumption

(MJ)

IoT Devices

Network

Usage (MB)

Experiment ID

Idle = 25 — Busy = 90

150

100 1

1000 2

300

100 3

1000 4

Idle = 50 — Busy = 180

150

100 5

1000 6

300

100 7

1000 8

MegaJoules is the standard energy unit in

iFogSim, serving as a reference for various measure-

ments like power (Watts), electron volts (eV), calo-

ries (cal), and kilowatt-hours (kWh). They also aid in

converting work requirements for infrastructure com-

ponents. However, experiment execution times in the

simulator may not always match real-world times due

to virtual time control mechanisms.

The eHealth scenario depicts a standard conﬁgura-

tion commonly found in healthcare settings, adhering

to parameters outlined by the WHO. Data bursts are

conﬁgured to mirror communication intervals across

multiple devices concurrently, assessing the system’s

ability to respond effectively.

The simulation utilizes a discrete model of the

spatial distribution of IoT devices within hospital set-

tings. The primary aim is to analyze the distribution

of devices across different scenarios while consider-

ing communication between devices, gateways, and

the backend cloud environment, for a comprehensive

examination of network dynamics.

To have results that reﬂect the real world, the sim-

ulator parameters were classiﬁed into two categories:

constant values and random values, as detailed in Ta-

ble 3. To ensure consistency of results, the experi-

ments were executed ten times before calculating the

results’ statistics.

The simulation incorporates transmission latency

of IoT devices. As outlined in Table 3, random in-

tervals are generated during runtime, based on device

granularity and network architecture (Figure 1). This

approach brings approximation of communication be-

haviors and network performance, considering the de-

vices’ hierarchical positions and immediate data link

access.

4 RESULTS

Having deﬁned the parameters and scenarios for the

experiments, and after performing ten executions of

each scenario, the results were collected and are pre-

sented in this section.

The reliability of the data collected is assessed by

standard error measured. The small dispersion of the

scenarios indicates consistency and stability in the re-

sults.

In Figure 2, it is possible to observe that the num-

ber of IoT devices is one of the main contributors to

the increase in the total value. The network occupa-

tion is heavier when the number of devices is higher,

as one would expect. For the size of application de-

ﬁned in the network usage and for the energy con-

sumption by device, the total network consumption

does not seem to change signiﬁcantly. The principal

aspect to impact on the overall network occupation is

the number of tasks involved, as well as the complex

data information throughout the system.

In the Figure 3 it is observed that the energy con-

sumption of IoT machines is mainly responsible for

the total energy expenditure. Therefore, when dou-

bling the number of IoT products, total energy con-

sumption shows a proportional growth. The same

pattern occurs with the energy cost of these equip-

ment, as evidenced by the difference between exper-

iments 1-2 and 5-6. Despite that the cloud environ-

ment is signiﬁcantly more powerful than the other de-

CLOSER 2024 - 14th International Conference on Cloud Computing and Services Science

180

Table 3: Parameters speciﬁcation for the experiments. Labels: MIPS = Millions of Instructions per Second, MBPS = Megabits

per second, GB = Gigabytes, MJ = Mega joules, ms = milliseconds.

IoT Device Fog Gateway Cloud Proxy Server

Quantity 150 - 300 2 1 1

Speed (MIPS)

1500 92500 6890500 2376800

RAM (GB)

4 64 32 4

Uplink (MBPS)

150 1000 16000 10000

Downlink (MBPS)

150 1000 16000 10000

Busy Power (MJ)

90 - 180 107.3 1716.8 107.3

Idle Power (MJ)

25 - 50 83.4 1331.2 83.4

Random Values (interval)

App CPU Usage (MB)

Sensors Latency

(ms)

Gateway Latency

(ms)

Proxy Latency

(ms)

IoT Device

Gateway Latency (ms)

50 - 500 0.1 - 0.6 1.0 - 15.0 1.0 - 4.0 1.0 - 4.0

Figure 2: Total network consumption per scenario, in Giga-

bytes. The task setup is the main inﬂuence for this result.

vices, its energy usage is remarkably smaller than the

IoT devices, for example. Also, its use remains sta-

ble throughout every scenario, indicating that the pro-

cessing jobs didn’t demand scaling up the servers.

Figure 3: Energy consumption by type of device, displayed

by scenario.

For the total execution time, Figure 4 shows that

the number of devices is again the most signiﬁcant

factor, due to the reduced number of gateways com-

pared to the amount of information transmitted by IoT

equipment, which ends up overloading the processes

and delays the information trafﬁc. Furthermore, the

Figure 5 shows the difference in magnitude between

the transmission time and the total simulation time is

very large, which demonstrates the insigniﬁcance of

this factor for the scenarios setup. There were found

no signiﬁcant inﬂuence for trafﬁc delays, even though

there were variations for that parameter. Therefore,

information processing time is the main agent for the

results obtained.

Figure 4: Total experiment run time, by scenario.

From the results obtained, it is evident that the val-

ues implemented in the simulator, as speciﬁed in Ta-

ble 2, have a linear impact on the results of the net-

work and energy consumption. In other words, when

doubling the number of IoT devices, it is clear that

the output value comes considerably closer to twice

what was expected. However, this phenomenon does

not manifest itself in the same way in time results:

when the initial quantity is doubled, the difference

in results is approximately four times greater in rela-

tion to the expected value. These results indicate that

depending on the network topology for the eHealth

IoT Devices Overhead: A Simulation Study of eHealth Solutions over a Hospitals’ Network

181

Figure 5: Network delay for scenario. The lines shows that

the communication on the edge of the network is slightly

faster, but not much signiﬁcant to the overall results.

IoT system, the critical parameter of execution inter-

val can suffer, generating risks for the patients and

medical team. The integration of IFogSim as a sim-

ulation framework presents a pivotal step forward in

the realization of IoT applications for eHealth.

The simulation focus on network infrastructure

and cloud computing, to assess the impact of IoT de-

ployment, especially in applications like temperature

and humidity sensing. This analysis aids planning re-

source management in the eHealth framework. Given

simulation nature, the devices, including gateways,

endpoints, proxies, and cloud components, are char-

acterized broadly and conﬁgured with varying param-

eters. This conﬁguration enables an evaluation of how

the factors inﬂuence the response variables.

5 CONCLUSIONS

The convergence of IoT and eHealth holds immense

promise for transforming healthcare delivery. How-

ever, the challenges posed by network infrastructure,

particularly in developing countries, necessitate inno-

vative solutions to ensure the optimal functioning of

IoT devices. This paper presents a model of compu-

tational simulations of IoT device installations to pre-

emptively address network-related challenges.

The results validate the accuracy of the simulation

and provide insights for designing IoT healthcare en-

vironments. Our ﬁndings demonstrate that a typical

number of devices might greatly impact on the results,

specially regarding execution time and energy expen-

diture, that can be crucial for life monitoring devices

and general costs. Even though there are machines

with far superior setups, the number of devices (cos-

tumary for eHealth setups) impacts the electric con-

sumption.

Overall, our contributions are a better understand-

ing of the implications of IoT implementation in

health facilities, speciﬁcally regarding the associated

network overhead, specially in areas with uneven or

limited bandwidth capacities. Also, the modiﬁcations

to IFogSim classes enrich the capacity of the simula-

tor to model real life scenarios.

In future works we aim to further investigate the

network occupation and energy costs with more com-

plex scenarios. Factors as network technology and

carbon emission can be evaluated, so the simulation

provides more complete representation for eHealth

services deployment. Other simulators could also be

used for comparison purposes.

ACKNOWLEDGEMENTS

The authors would like to thank Universidade Fed-

eral de Itajub

a for their support in this work. This

work is supported by Coordination for the Improve-

ment of Higher Education Personnel (CAPES) under

Programa Institucional de Bolsas de Iniciac¸

ao Cien-

tiﬁca (PIBIC).

REFERENCES

Ahmed, Z. E., Hasan, M. K., Saeed, R. A., Hassan, R., Is-

lam, S., Mokhtar, R. A., Khan, S., and Akhtaruzza-

man, M. (2020). Optimizing energy consumption for

cloud internet of things. Frontiers in Physics, 8.

Al-Khafaji, H. M. R. (2022). Improving quality indicators

of the cloud-based iot networks using an improved

form of seagull optimization algorithm. Future Inter-

net, 14(10).

Alwasel, K., Jha, D. N., Habeeb, F., Demirbaga, U., Rana,

O., Baker, T., Dustdar, S., Villari, M., James, P., So-

laiman, E., and Ranjan, R. (2021). Iotsim-osmosis: A

framework for modeling and simulating iot applica-

tions over an edge-cloud continuum. Journal of Sys-

tems Architecture, 116:101956.

Aosong Eletronics (2023). Am2302 product manual.

https://shorturl.at/aerFY. Accessed: 21-08-2023.

Banday, M. T. and Bhat, L. (2022). Towards Building

Internet-of-Things-Inclusive Healthcare for Neglected

Tropical Diseases:. In Pandey, R., Gupta, A., and

Pandey, A., editors, Advances in Medical Technolo-

gies and Clinical Practice, pages 39–75. IGI Global.

Calheiros, R. N., Ranjan, R., Beloglazov, A., Rose, C. A.

F. D., and Buyya, R. (2011). Cloudsim: a toolkit for

modeling and simulation of cloud computing environ-

ments and evaluation of resource provisioning algo-

rithms. Softw., Pract. Exper., 41(1):23–50.

Castane, G., Simonis, H., Brown, K., Lin, Y., Ozturk, C.,

Garraffa, M., and Antunes, M. (2019). Simulation-

based optimization tool for ﬁeld service planning.

pages 1684–1695.

CLOSER 2024 - 14th International Conference on Cloud Computing and Services Science

182

DataSheet39.com (2023). Sct-013-005 datasheet.

https://shorturl.at/kzV28. Accessed: 21-08-2023.

Dell (2022). Access the full potential of your edge- gen-

erated data. https://shorturl.at/hkCG2. Accessed: 21-

08-2023.

Gezimati, M. and Singh, G. (2023). Internet of things

enabled framework for terahertz and infrared cancer

imaging. Optical and Quantum Electronics, 55(1):26.

Google (2023). Google cloud. https://shorturl.at/lmFIP. Ac-

cessed: 21-08-2023.

Gupta, B. and Quamara, M. (2020). An overview of inter-

net of things (iot): Architectural aspects, challenges,

and protocols. Concurrency and Computation: Prac-

tice and Experience, 32(21):e4946. e4946 CPE-18-

0159.R1.

InnovatorsGuru (2023). Zmpt101b micro precision voltage

transformers. https://shorturl.at/abvBD. Accessed:

21-08-2023.

Lv, Z., Lou, R., and Lv, H. (2022). Edge Computing

to Solve Security Issues for Infectious Disease Intel-

ligence Prevention. ACM Transactions on Internet

Technology, 22(3):1–20.

Mahmud, M. R., Pallewatta, S., Goudarzi, M., and Buyya,

R. (2021). Ifogsim2: An extended ifogsim simula-

tor for mobility, clustering, and microservice manage-

ment in edge and fog computing environments. CoRR,

abs/2109.05636.

Mishra, R., Kaur, I., Sahu, S., Saxena, S., Malsa, N., and

Narwaria, M. (2022). Establishing Three Layer Archi-

tecture to Improve Interoperability in Medicare Using

Smart and Strategic Api Led Integration.

PassMark Software (2023). Cpu benchmarks.

https://shorturl.at/hnAMW. Accessed: 21-08-2023.

Premkumar, N. and Santhosh, R. (2022). Challenges

and issues of e-health applications in cloud and fog

computing environment. In Shakya, S., Bestak, R.,

Palanisamy, R., and Kamel, K. A., editors, Mobile

Computing and Sustainable Informatics, pages 711–

721, Singapore. Springer Nature Singapore.

Puliaﬁto, C., Gonc¸alves, D. M., Lopes, M. M., Martins,

L. L., Madeira, E., Mingozzi, E., Rana, O., and Bit-

tencourt, L. F. (2020). Mobfogsim: Simulation of

mobility and migration for fog computing. Simulation

Modelling Practice and Theory, 101:102062. Model-

ing and Simulation of Fog Computing.

Puliaﬁto, C., Mingozzi, E., Longo, F., Puliaﬁto, A., and

Rana, O. (2019). Fog computing for the internet

of things: A survey. ACM Trans. Internet Technol.,

19(2).

RaspberryPi (2019). Datasheet - raspberry pi.

https://shorturl.at/ejno0. Accessed: 21-08-2023.

Steele, R. and Lo, A. (2013). Lo, a.: Telehealth and

ubiquitous computing for bandwidth-constrained rural

and remote areas. personal and ubiquitous computing

17(3), 533-543. Personal and Ubiquitous Computing,

17.

Su, H., Pan, M.-S., Chen, H., Li, R., and Wang, W. (2022).

An edge computing-based architecture for healthcare

Internet of Things with body area networks. In Ling,

T. W., editor, International Conference on Intelligent

Systems, Communications, and Computer Networks

(ISCCN 2022), page 19, Chengdu, China. SPIE.

Vilela, P. H., Rodrigues, J. J. P. C., Righi, R. d. R., Ko-

zlov, S., and Rodrigues, V. F. (2020). Looking at fog

computing for e-health through the lens of deployment

challenges and applications. Sensors, 20(9).

Woo, M. W., Lee, J., and Park, K. (2018). A reliable iot

system for personal healthcare devices. Future Gen-

eration Computer Systems, 78:626–640.

Wu, J., Tian, X., and Tan, Y. (2019). Hospital evaluation

mechanism based on mobile health for iot system in

social networks. Computers in Biology and Medicine,

109:138–147.

Yousaf, Z., Radulescu, M., Sinisi, C. I., Serbanescu, L., and

aunescu, L. M. (2021). Towards sustainable digital

innovation of smes from the developing countries in

the context of the digital economy and frugal environ-

ment. Sustainability, 13(10).

IoT Devices Overhead: A Simulation Study of eHealth Solutions over a Hospitals’ Network

183