Computing: Looking Back and Moving Forward

Muhammed Golec

and Sukhpal Singh Gill

School of Electronic Engineering and Computer Science, Queen Mary University of London, London, U.K.

{m.golec, s.s.gill}@qmul.ac.uk

Keywords:

Modern Computing, Cloud Computing, Fog Computing, Edge Computing, Serverless Computing, Quantum

Computing.

Abstract:

The Internet and computer commercialization have transformed the computing systems area over the past sixty

years, affecting society. Computer systems have evolved to meet diverse social needs thanks to technological

advances. The Internet of Things (IoT), cloud computing, fog computing, edge computing, and other emerg-

ing paradigms provide new economic and creative potential. Therefore, this article explores and evaluates

the elements impacting the advancement of computing platforms, including both long-standing systems and

frameworks and more recent innovations like cloud computing, quantum technology, and edge AI. In this arti-

cle, we examine computing paradigms, domains, and next-generation computing systems to better understand

the past, present, and future of computing technologies. This paper provides readers with a comprehensive

overview of developments in computing technologies and highlights promising research gaps for the advance-

ment of future computing systems.

1 INTRODUCTION

Revolutionary developments such as the discovery

of ﬁre, the invention of writing, and the printing

press have shaped human history. One of these de-

velopments is computing technologies, which ﬁnd a

place in almost every ﬁeld today (Gill et al., 2024b).

Finance, where daily transactions are carried out,

healthcare, where patient records are kept and anal-

yses are performed, and social media areas can be

given as some examples (Golec et al., 2021). One of

the revolutionary developments in information tech-

nology is Artiﬁcial Intelligence (AI), which can think

like a human and perform certain tasks for now. Be-

cause it can be applied to many ﬁelds, it has the ad-

vantage of being faster and more effective than hu-

mans in solving complex problems (Iftikhar et al.,

2023). It is thought that if AI is integrated with quan-

tum computing, another technologically revolution-

ary development, it can increase the quality of life for

humanity in many areas (Gill et al., 2024a).

This article gives readers a general perspective

by examining the developments in the computing

paradigm from the past to the present, current tech-

nology applications, trends, and challenges, and next-

generation computing concepts. Figure 1 shows an

https://orcid.org/0000-0003-0146-9735

https://orcid.org/0000-0002-3913-0369

overview of the advancements in computing systems

and technologies. First, existing technologies and do-

mains such as Internet of Things (IoT), Blockchain,

and quantum computing are examined. We then dis-

cuss how these technologies shape computing. In the

last part, we will examine new generation computing

trends and challenges, such as Industry 4.0 and Quan-

tum Internet, which are the future of computing.

2 COMPUTING PARADIGMS

In this section, we examine the main paradigms to

better explain the evolution in computing technology.

2.1 Grid Computing

To complete complicated activities or ﬁnd solutions

to big issues, grid computing is a distributed comput-

ing paradigm that permits the sharing and coordinated

use of the same networked computing resources (Gill

et al., 2024b). Many different ﬁelds, such as weather

forecasting and the ﬁnancial industry, utilize it for

quick ﬁxes like risk assessments and the examination

of massive volumes of data. Several beneﬁts of this

paradigm have drawn the interest of both academic

and private-sector researchers, including the follow-

ing (Jacob et al., 2005):

Golec, M. and Gill, S.

Computing: Looking Back and Moving Forward.

DOI: 10.5220/0012855200003764

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

In Proceedings of the 21st International Conference on Smart Business Technologies (ICSBT 2024), pages 7-14

ISBN: 978-989-758-710-8; ISSN: 2184-772X

COMPUTING SYSTEMS

PARADIGMS

Cloud Computing

Fog Computing

Edge Computing

Serverless Computing

Quantum Computing

TECHNOLOGIES AND IMPACT AREAS

NEW TRENDS

IoT

Autoscaling

Virtualization

Fault Tolerance

Energy Efficiency

Security and Privacy

AI-driven Computing

Large Scale Machine

Learning

Edge AI

Industry 4.0

Quantum Internet

Grid Computing

Microservices

Software-defined

Networks

Blockchain

Federated Learning

QoS and SLA

Figure 1: The Overview of Advancements in Computing Systems and Technologies.

• The Ability to Scale: Resources can be adjusted in

size to meet shifting demands and workloads.

• The Use of Resources: Distributed resources are

pooled to enhance resource utilization, which

lowers the free capacity to maintain optimal ef-

ﬁciency.

• The Economy of Cost: Using available resources,

we can solve tasks requiring a lot of computing

at a low cost, eliminating the need for specialized

infrastructure.

In addition to these advantages, it still brings chal-

lenges that need to be solved, such as risks to security,

complexity, and variability in performance.

2.2 Cloud Computing

In contrast to traditional computing systems, Infor-

mation Technology (IT) based this paradigm allows

computing resources to be pooled and made avail-

able over the Internet, and transactions to take place

on distant servers (Golec et al., 2023d). Many do-

mains of civil and commercial applications, including

web and enterprise applications, have widely adopted

cloud computing. Users can beneﬁt in a number of

ways, including (i) cost savings through a reduction

in hardware and infrastructure expenses, (ii) resource

scalability to adapt to variations in demand, and (iii)

access from any location with Internet access (Mu-

rugesan et al., 2024). However, it also presents draw-

backs such as resource management, privacy, and se-

curity issues that require attention.

Three main categories typically classify different

cloud delivery models, which offer consumers vary-

ing degrees of service (Golec et al., 2023a):

• IaaS (Infrastructure as a Service): In this ser-

vice model, consumers rent cloud service provider

(CSP) resources such as virtual machines and

storage. CSPs are responsible for the server’s in-

frastructure operations, while users are only re-

sponsible for infrastructure management.

• PaaS (Platform as a Service): It’s a service

paradigm that keeps customers away from in-

frastructure management so they may concentrate

solely on developing applications. A PaaS ap-

proach gives users access to the required devel-

opment environments and software tools.

• FaaS (Function as a Service): This completely

isolates users from infrastructure and service ad-

ministration. This relieves users of all infrastruc-

ture management responsibilities and allows them

to concentrate entirely on developing code. Un-

der this service paradigm, users upload single-

function bits of code to the platform using an

event-driven architecture.

ICSBT 2024 - 21st International Conference on Smart Business Technologies

2.3 Fog Computing

With the increase in IoT-based applications, the

amount of data that needs to be processed has reached

gigantic proportions. Research shows that there will

be 24 billion enterprise IoT connections by 2030

(Vailshery, 2024). When cloud systems utilize re-

mote servers, an increase in data processing leads

to a decrease in Quality of Service (QoS) parame-

ters like latency (Golec et al., 2023c). Fog comput-

ing is emerging as an alternative to cloud computing

to solve this problem. Fog computing expedites re-

sponse times by situating data processing and stor-

age near the data generation sources (Iftikhar et al.,

2022b). Time-sensitive applications and Industrial In-

ternet of Things (IIoT), which process large amounts

of data, beneﬁt greatly from this approach. While

it offers users beneﬁts like reduced latency and en-

hanced security by bringing processing power closer

to the data source, it also presents challenges like re-

source constraints and compatibility issues due to the

use of heterogeneous and distributed devices.

2.4 Edge Computing

The concept of edge computing emerged to solve

problems such as bandwidth and latency in solutions

such as cloud computing, where processing power

and storage move away from the data source (Nand-

hakumar et al., 2024). For this reason, edge devices

such as sensors and smartphones are positioned close

to data sources. Today, it has wide usage areas such as

IIoT and time-sensitive healthcare applications (Walia

et al., 2024). Edge computing provides advantages

such as (i) Reducing latency by moving the process-

ing power closer to the data source, (ii) Reducing un-

necessary bandwidth usage because it only transmits

data that requires high processing power to the cloud,

and (iii) Providing data security because it processes

the data locally (Iftikhar et al., 2022a). In addition

to these advantages, it brings challenges such as re-

source management, security and privacy, and coor-

dinated work arising from the distributed architecture

of IoT, which are still waiting to be solved.

The reasons and goals of Fog computing and Edge

computing are very similar. For this reason, the two

concepts are often confused. When both IT models

are examined carefully, it is seen that they differ from

each other as follows (Buyya and Srirama, 2019):

• Although both computing models aim to reduce

latency and unnecessary bandwidth usage, the

main difference between them is related to where

data is processed and stored. In fog computing,

data processing locations are closer to the data

source than in cloud, but further away than in edge

computing. Examples are gateways and city data

centers. In edge computing, the place of data pro-

cessing is usually IoT and mobile devices where

data is produced.

• Fog computing is often used in large-scale sys-

tems such as IIoT, where data processing and stor-

age are handled at a middleware. Edge computing

has a more distributed approach.

2.5 Serverless Computing

Cloud computing has introduced delivery models

with various advantages since the day it was ﬁrst in-

troduced. More information about these models is

given in Section 2.2. One of these delivery models is

Serverless computing, which isolates server mainte-

nance and infrastructure management from customers

and combines Backend as a Service (BaaS) and Func-

tion as a Service (FaaS) services (Golec et al., 2023d).

In this way, customers can focus only on code de-

velopment by being isolated from all infrastructure

management processes. Serverless computing ﬁrst

emerged in 2014 when Amazon Web Services intro-

duced the Lambda model. This service model uses an

event-driven architecture and code developers write

their codes as functions. Today, serverless-based ap-

plications are used in a wide variety of ﬁelds such as

ﬁnance and education.

It has the following advantages over traditional

cloud service models (such as IaaS, and PaaS) (Golec

et al., 2021):

• The pay-as-you-go pricing model charges only ac-

cording to the time resources are used,

• The auto-scalability feature allows for the dy-

namic increase or decrease of computing re-

sources in response to an increasing number of

requests,

• Ease of management, complete isolation of infras-

tructure operations from customers.

In addition to all these advantages, studies con-

tinue in the academy and private sector to solve chal-

lenges such as cold start latency, security and privacy,

and monitoring and debugging.

2.6 Quantum Computing

It is a computing paradigm in quantum physics that

works based on the principle of using particles in su-

perposition, called qubits and has recently attracted

attention in academia (Gill et al., 2024a). It has the

potential to solve problems that require a long time

Computing: Looking Back and Moving Forward

to be solved in a very short time compared to classi-

cal computers where all operations are processed with

binary bit (0 and 1) logic (Gill et al., 2022a). For this

reason, it can be used in complex areas such as Cryp-

tography, AI, and Molecular Biology that require high

processing power.

Quantum computers have advantages over clas-

sical computers such as parallel processing ability,

quantum superposition, and quantum teleportation.

Thanks to these advantages, it provides advantages

such as high speed, parallel processing, and new al-

gorithm discoveries (Gill, 2024). On the other hand,

quantum computers are still in the research phase and

must overcome the challenges described below to be-

come widely available (O’brien, 2007):

• High Cost: Creating a more powerful quantum

computer is directly proportional to the number

of qubits to be added. However, adding qubits is

very costly.

• Quantum-Induced Challenges: Quantum comput-

ers, which operate on the principles of quantum

mechanics, involve sensitive processes such as en-

suring qubit stability and quantum errors. Due

to these technical difﬁculties, quantum computers

have not yet been produced on a large scale.

• Insulation and Cooling: Quantum stability and

Quantum errors are very quickly affected by envi-

ronmental factors such as heat and noise. There-

fore, insulation and cooling technologies must be

developed to provide these conditions.

3 COMPUTING TECHNOLOGIES

AND IMPACT AREAS

Computing technologies have made a huge impact in

various research ﬁelds and transformed the way of

working. Some of these areas are examined under

subheadings in this section.

3.1 QoS and SLA

Quality of Service (QoS) refers to metrics such as

latency, throughput and response rate used to show

the performance of an application or network ser-

vice. Service Level Agreement (SLA) is an agreement

made between a service/application and customers

that guarantees the quality and reliability of the ser-

vice. Computing technologies have various impacts

on QoS & SLA (Golec et al., 2023c).

• Security and Privacy: Computing technologies

support SLA with security methods to ensure the

security of applications and user privacy.

• Efﬁciency: Computing technologies can improve

QoS parameters with high-capacity processors

and infrastructure to increase the performance of

applications.

• Application Flexibility: Computing technologies

can make services/applications more ﬂexible by

increasing resources to meet demand ﬂuctuations.

3.2 IoT

All devices that can connect to the Internet and com-

municate data with each other are called IoT (Sen

and Yamin, 2021). It has many uses in civilian and

military areas, from smart home appliances to au-

tonomous vehicles. Computer technologies have a

very wide impact on IoT.

• Data Analytics: IoT devices analyze the data col-

lected through sensors and obtain valuable infor-

mation as a result of this analysis. For example, in

an IIoT scenario where production is monitored,

predictive maintenance can detect the engine that

will fail and thus prevent production disruption.

• Smart Health Applications: Patient monitoring

and disease diagnosis studies are carried out using

IoT devices and sensors. In this way, it is aimed

to prevent unnecessary health expenses and fatal

diseases through early and accurate diagnosis.

• Smart City Applications: Includes sustainable so-

lutions such as city infrastructure and energy man-

agement, such as trafﬁc lights in cities and energy

optimization in homes.

3.3 Autoscaling

The concept of autoscaling refers to the automatic in-

crease or decrease of system resources to meet de-

mand ﬂuctuations, which is frequently used in com-

puting technologies (Golec et al., 2023c). Generally,

it occurs when launching new instances during de-

mand ﬂuctuations in order to meet SLAs in cloud ser-

vices. This is also necessary for resource and cost

optimization of applications and services.

3.4 Virtualization

It is a computing technology that allows the resources

in a system to be used efﬁciently and divided into dif-

ferent operating systems (Chiueh and Brook, 2005).

It is especially popular in IaaS-based delivery models

provided to users by major cloud providers.

ICSBT 2024 - 21st International Conference on Smart Business Technologies

3.5 Fault Tolerance

It refers to measures that can tolerate service interrup-

tions caused by errors that may occur in a system. It

includes backup processes called Redundant Array of

Independent Disks (RAID) in cloud systems to pre-

vent data loss due to interruptions that may occur in

the system (Plank, 1997; Chouikhi et al., 2015).

3.6 Energy Efﬁciency

It refers to a system performing the same work with

less energy. Values such as energy spent while per-

forming a task and CO

emissions are critical in re-

ducing environmental pollution (Golec et al., 2023a;

Feng et al., 2012). This has led to the proposal of new

technological advances such as green IoT and green

cloud computing.

3.7 Security and Privacy

Security and privacy are two of the most fundamen-

tal problems in IT systems. Security includes com-

prehensive issues such as unauthorized access to a

system and theft or modiﬁcation of data in the sys-

tem. Privacy refers to all situations that may jeopar-

dize user privacy, such as biometric data (Golec et al.,

2022; De Guzman et al., 2019).

3.8 Microservices

It refers to a form of architecture designed to make

applications more ﬂexible and easier to develop. Es-

sentially, it aims to divide and develop the applica-

tion into smaller and independent applications (Golec

et al., 2023d; Pallewatta et al., 2023). By dividing the

application into smaller services, advantages such as

debugging and the ability to use different technologies

for each scenario are provided.

3.9 Software-Deﬁned Networks

Software-deﬁned Networks (SDN) is a centralized

and software-oriented management approach to en-

sure more efﬁcient management of resources in a net-

work (Fernandes et al., 2018). Computing technolo-

gies have various impacts on SDNs.

• Ease of Network Operation: SDN provides trafﬁc

optimization and dynamic resource allocation to

increase the operational capability of the network

(Sarabia-J

acome et al., 2024).

• Network Scaling: SDN ensures the scalability of

the infrastructure to increase the efﬁciency of net-

work resources (Dhadhania et al., 2024).

• QoS and SLA Improvement: SDN provides opti-

mization in trafﬁc management to improve QoS

and SLA in network applications (Wang et al.,

2016).

3.10 Blockchain

It is a computing technology that essentially consists

of interconnected blocks containing the hash of the

previous block and can be thought of as a digital

ledger (Golec et al., 2023b). The data in each block

is connected to each other with the hash value of the

previous block and a new hash value is obtained for

the next block. In this way, any change in any data

in the blocks affects all blocks, and data immutability

is ensured. Blockchain technologies are used in many

areas today (Doyle et al., 2022; Reyna et al., 2018):

• Financial Sector: Blockchain provides a decen-

tralized platform for digital assets such as cryp-

tocurrencies (Bitcoin etc.). This eliminates inter-

mediaries in buying and selling transactions, en-

suring safe transfers.

• Smart Contracts: These are contracts that are de-

centralized and kept on the blockchain network

(CR et al., 2024). As a result, all transactions

are public. In addition, trust and data security are

ensured between the parties by taking advantage

of the data immutability advantage provided by

Blockchain.

• Product Supply: Quality control is increased by

monitoring supply chains with blockchain-based

systems and fraud can be reduced with the prin-

ciple of data immutability (Wang et al., 2024). In

this way, conﬁdence in supply chains and com-

mercial activities can be increased.

• Identity Authentication and Voting: With

blockchain-based voting systems, user privacy

is ensured by storing personal data securely

(Hossain Faruk et al., 2024). Additionally,

manipulations in elections held in countries can

be prevented.

3.11 Federated Learning

Federated Learning (FL) is a Machine Learning (ML)

technique used in distributed architectures (Li et al.,

2020). While in ML techniques a centralized system

is used for model training, in FL distributed devices

are used for model training. FL, a ﬁeld of computing

technologies, has a variety of advantages (Mammen,

2021):

• Security and Privacy: Since a central system is

Computing: Looking Back and Moving Forward

not used when training FL models, data security

and user privacy risks are lessened.

• Fast Training: Model training is faster because

FL is trained in distributed systems close to data

sources.

• Accessibility: Since FL are trained in dis-

tributed systems, model training is also possible

in Internet-limited environments.

4 NEXT GENERATION

COMPUTING: CHALLENGES

AND NEW TRENDS

This section brieﬂy discusses next-generation com-

puting paradigms, their challenges and new trends.

4.1 AI-Driven Computing

AI-driven computing is the integration of AI, ML,

and Natural Language Processing (NLP) models into

computer systems to process big data and produce so-

lutions for complex models (Firouzi et al., 2022). It

brings many advantages to the system into which it is

integrated (Gill et al., 2022b):

• Prediction Performance: It is important to ana-

lyze data in areas such as ﬁnance and health and

make predictions with high performance. AI-

driven computing increases prediction success

rates, resulting in a noticeable increase in risk as-

sessments.

• Cost and Efﬁciency: AI-driven computing can re-

duce costs and increase production efﬁciency by

preventing interruptions in production processes,

such as predictive maintenance scenarios.

• Opportunities: With its innovative solutions, AI-

driven computing has the potential to create new

business areas and expertise.

Apart from all these advantages, AI-driven com-

puting also includes challenges such as ethical issues

and new algorithms for optimization in complex op-

erations.

4.2 Large Scale Machine Learning

Traditional ML techniques trained on large datasets

have low model performance due to factors such

as hyperparameter setting, computational power, and

large features. As a result, it is necessary to use tech-

niques such as parallel computing for ML models in

large data sets. Large-scale machine learning methods

provide advantages such as improving prediction per-

formance and optimizing transaction cost and speed

(Wang et al., 2020). Besides these advantages, chal-

lenges such as feature selection and ensuring data in-

tegrity are still waiting to be investigated (Liu et al.,

2024).

4.3 Edge AI

AI-based applications are generally processed in cen-

tralized systems with high processing power. Edge AI

is an approach that proposes to process data close to

the data source, such as IoT and smartphones (Bibri

et al., 2024). This is because it provides advantages

such as lower latency, and security, and reduces un-

necessary bandwidth usage compared to centralized

systems such as the cloud (Singh and Gill, 2023). On

the other hand, Edge AI systems offer lower process-

ing power and storage space than cloud-based sys-

tems. Also, since it has a distributed architecture,

it also brings with it challenges such as the mainte-

nance and management of devices and resource man-

agement.

4.4 Industry 4.0

It is the use of new computing technologies such as AI

and IoT by integrating them into production processes

to make production more efﬁcient and economical

(Teoh et al., 2021). Predictive maintenance is a good

example of an Industry 4.0 application. By using sen-

sors and ML models, errors are detected in advance

in predictive maintenance scenarios, and production

disruptions are prevented. Likewise, production op-

timization is achieved through data analysis methods

using data received from sensors. Thus, by enhancing

service quality, we can promptly respond to customer

demands. In addition to all these advantages, it should

not be forgotten that Industry 4.0 brings with it prob-

lems that still need to be solved, such as cost, cyber

security, and integration.

4.5 Quantum Internet

It is an Internet model that works with quantum prin-

ciples (Wehner et al., 2018). It is expected to replace

the classical Internet in the future with its higher se-

curity and speed. In the Quantum Internet, quantum

cryptography is used to ensure security in communi-

cation protocols. Compared to the classical Internet,

much faster communication speeds are achieved with

quantum teleportation techniques. In addition to all

these advantages, quantum computing, and the quan-

tum Internet are still in the research phase. And its

ICSBT 2024 - 21st International Conference on Smart Business Technologies

integration for long-distance communications is still

a challenge (Li et al., 2024).

5 CONCLUSIONS

Computing technologies continue to shape human

history with the transformations they offer from the

past to the present. This effect can be seen every-

where, from healthcare applications like early diag-

nosis and medical imaging to military vehicles like

unmanned planes. Additionally, technologies such as

IoT and AI continue to trend with the opportunities

they offer in various industries and processes. Quan-

tum technologies, one of the next-generation devel-

opments in computing and still in their infancy, have

recently attracted attention for their potential to shape

the future. However, embracing these next-generation

trends and dealing with their challenges will require

separate efforts. In this paper, we take an overview

of computing technologies from the past to the future

and highlight challenges for researchers.

ACKNOWLEDGEMENTS

Muhammed Golec would express his thanks to the

Ministry of Education of the Turkish Republic, for

their support and funding.

REFERENCES

Bibri, S. E., Krogstie, J., Kaboli, A., and Alahi, A. (2024).

Smarter eco-cities and their leading-edge artiﬁcial in-

telligence of things solutions for environmental sus-

tainability: A comprehensive systematic review. En-

vironmental Science and Ecotechnology, 19:100330.

Buyya, R. and Srirama, S. N. (2019). Fog and edge comput-

ing: principles and paradigms. John Wiley & Sons.

Chiueh, S. N. T.-c. and Brook, S. (2005). A survey on vir-

tualization technologies. Rpe Report, 142.

Chouikhi, S., El Korbi, I., Ghamri-Doudane, Y., and

Saidane, L. A. (2015). A survey on fault tolerance in

small and large scale wireless sensor networks. Com-

puter Communications, 69:22–37.

CR, A., Pani, A. K., and Kumar, P. (2024). Blockchain-

enabled smart contracts and the internet of things: Ad-

vancing the research agenda through a narrative re-

view. Multimedia Tools and Applications, pages 1–51.

De Guzman, J. A., Thilakarathna, K., and Seneviratne, A.

(2019). Security and privacy approaches in mixed re-

ality: A literature survey. ACM Computing Surveys

(CSUR), 52(6):1–37.

Dhadhania, A., Bhatia, J., Mehta, R., Tanwar, S., Sharma,

R., and Verma, A. (2024). Unleashing the power of

sdn and gnn for network anomaly detection: State-of-

the-art, challenges, and future directions. Security and

Privacy, 7(1):e337.

Doyle, J., Golec, M., and Gill, S. S. (2022). Blockchainbus:

A lightweight framework for secure virtual machine

migration in cloud federations using blockchain. Se-

curity and Privacy, 5(2):e197.

Feng, D., Jiang, C., Lim, G., Cimini, L. J., Feng, G., and

Li, G. Y. (2012). A survey of energy-efﬁcient wireless

communications. IEEE Communications Surveys &

Tutorials, 15(1):167–178.

Fernandes, E. L., Antichi, G., Castro, I., and Uhlig, S.

(2018). An sdn-inspired model for faster network

experimentation. In Proceedings of the 2018 ACM

SIGSIM Conference on Principles of Advanced Dis-

crete Simulation, pages 29–32.

Firouzi, F., Farahani, B., and Marin

sek, A. (2022). The con-

vergence and interplay of edge, fog, and cloud in the

ai-driven internet of things (iot). Information Systems,

107:101840.

Gill, S. S. (2024). Quantum and blockchain based server-

less edge computing: A vision, model, new trends

and future directions. Internet Technology Letters,

7(1):e275.

Gill, S. S. et al. (2024a). Quantum computing: Vision and

challenges. arXiv preprint arXiv:2403.02240.

Gill, S. S., Kumar, A., Singh, H., Singh, M., Kaur, K., Us-

man, M., and Buyya, R. (2022a). Quantum comput-

ing: A taxonomy, systematic review and future direc-

tions. Software: Practice and Experience, 52(1):66–

114.

Gill, S. S., Wu, H., Patros, P., Ottaviani, C., Arora, P., Pu-

jol, V. C., Haunschild, D., Parlikad, A. K., Cetinkaya,

O., Lutﬁyya, H., et al. (2024b). Modern computing:

Vision and challenges. Telematics and Informatics Re-

ports, page 100116.

Gill, S. S., Xu, M., Ottaviani, C., Patros, P., Bahsoon, R.,

Shaghaghi, A., Golec, M., Stankovski, V., Wu, H.,

Abraham, A., et al. (2022b). Ai for next generation

computing: Emerging trends and future directions. In-

ternet of Things, 19:100514.

Golec, M., Chowdhury, D., Jaglan, S., Gill, S. S., and Uh-

lig, S. (2022). Aiblock: Blockchain based lightweight

framework for serverless computing using ai. In

2022 22nd IEEE International Symposium on Clus-

ter, Cloud and Internet Computing (CCGrid), pages

886–892. IEEE.

Golec, M., Gill, S. S., Cuadrado, F., Parlikad, A. K., Xu,

M., Wu, H., and Uhlig, S. (2023a). Atom: Ai-powered

sustainable resource management for serverless edge

computing environments. IEEE Transactions on Sus-

tainable Computing.

Golec, M., Gill, S. S., Golec, M., Xu, M., Ghosh, S. K.,

Kanhere, S. S., Rana, O., and Uhlig, S. (2023b).

Blockfaas: Blockchain-enabled serverless computing

framework for ai-driven iot healthcare applications.

Journal of Grid Computing, 21(4):63.

Computing: Looking Back and Moving Forward

Golec, M., Iftikhar, S., Prabhakaran, P., Gill, S. S., and Uh-

lig, S. (2023c). Qos analysis for serverless comput-

ing using machine learning. In Serverless Computing:

Principles and Paradigms, pages 175–192. Springer.

Golec, M., Ozturac, R., Pooranian, Z., Gill, S. S., and

Buyya, R. (2021). Ifaasbus: A security-and privacy-

based lightweight framework for serverless comput-

ing using iot and machine learning. IEEE Transac-

tions on Industrial Informatics, 18(5):3522–3529.

Golec, M., Walia, G. K., Kumar, M., Cuadrado, F.,

Gill, S. S., and Uhlig, S. (2023d). Cold start la-

tency in serverless computing: A systematic review,

taxonomy, and future directions. arXiv preprint

arXiv:2310.08437.

Hossain Faruk, M. J., Alam, F., Islam, M., and Rahman,

A. (2024). Transforming online voting: a novel sys-

tem utilizing blockchain and biometric veriﬁcation for

enhanced security, privacy, and transparency. Cluster

Computing, pages 1–20.

Iftikhar, S., Gill, S. S., Song, C., Xu, M., Aslanpour, M. S.,

Toosi, A. N., Du, J., Wu, H., Ghosh, S., Chowdhury,

D., et al. (2023). Ai-based fog and edge computing:

A systematic review, taxonomy and future directions.

Internet of Things, 21:100674.

Iftikhar, S., Golec, M., Chowdhury, D., Gill, S. S., and Uh-

lig, S. (2022a). Fogdlearner: A deep learning-based

cardiac health diagnosis framework using fog comput-

ing. In Proceedings of the 2022 Australasian Com-

puter Science Week, pages 136–144. ACM.

Iftikhar, S., Raj, U., Tuli, S., Golec, M., Chowd-

hury, D., Gill, S. S., and Uhlig, S. (2022b).

Tesco: Multiple simulations based ai-augmented

fog computing for qos optimization. In 2022

IEEE Smartworld, Ubiquitous Intelligence &

Computing, Scalable Computing & Communica-

tions, Digital Twin, Privacy Computing, Meta-

verse, Autonomous & Trusted Vehicles (Smart-

World/UIC/ScalCom/DigitalTwin/PriComp/Meta),

pages 2092–2099. IEEE.

Jacob, B., Brown, M., Fukui, K., Trivedi, N., et al. (2005).

Introduction to grid computing. IBM redbooks, pages

3–6.

Li, L., Fan, Y., Tse, M., and Lin, K.-Y. (2020). A review

of applications in federated learning. Computers &

Industrial Engineering, 149:106854.

Li, Y., Zhang, H., Zhang, C., Huang, T., and Yu, F. R.

(2024). A survey of quantum internet protocols from

a layered perspective. IEEE Communications Surveys

& Tutorials.

Liu, J., Liu, M., Liu, J.-P., Ye, Z., Wang, Y., Alexeev, Y.,

Eisert, J., and Jiang, L. (2024). Towards provably

efﬁcient quantum algorithms for large-scale machine-

learning models. Nature Communications, 15(1):434.

Mammen, P. M. (2021). Federated learning: Opportunities

and challenges. arXiv preprint arXiv:2101.05428.

Murugesan, S. S., Velu, S., Golec, M., Wu, H., and Gill,

S. S. (2024). Neural networks based smart e-health

application for the prediction of tuberculosis using

serverless computing. IEEE Journal of Biomedical

and Health Informatics.

Nandhakumar, A. R., Baranwal, A., Choudhary, P., Golec,

M., and Gill, S. S. (2024). Edgeaisim: A toolkit

for simulation and modelling of ai models in edge

computing environments. Measurement: Sensors,

31:100939.

O’brien, J. L. (2007). Optical quantum computing. Science,

318(5856):1567–1570.

Pallewatta, S., Kostakos, V., and Buyya, R. (2023). Place-

ment of microservices-based iot applications in fog

computing: A taxonomy and future directions. ACM

Computing Surveys, 55(14s):1–43.

Plank, J. S. (1997). A tutorial on reed–solomon coding for

fault-tolerance in raid-like systems. Software: Prac-

tice and Experience, 27(9):995–1012.

Reyna, A., Mart

ın, C., Chen, J., Soler, E., and D

ıaz, M.

(2018). On blockchain and its integration with iot.

challenges and opportunities. Future generation com-

puter systems, 88:173–190.

Sarabia-J

acome, D., Gim

enez-Ant

on, S., Liatiﬁs, A., Grasa,

E., Catal

an, M., and Pliatsios, D. (2024). Progressive

adoption of rina in iot networks: Enhancing scalability

and network management via sdn integration. Applied

Sciences, 14(6):2300.

Sen, A. A. A. and Yamin, M. (2021). Advantages of us-

ing fog in iot applications. International Journal of

Information Technology, 13:829–837.

Singh, R. and Gill, S. S. (2023). Edge ai: a survey. Internet

of Things and Cyber-Physical Systems, 3:71–92.

Teoh, Y. K., Gill, S. S., and Parlikad, A. K. (2021). Iot and

fog-computing-based predictive maintenance model

for effective asset management in industry 4.0 using

machine learning. IEEE Internet of Things Journal,

10(3):2087–2094.

Vailshery, L. S. (2024). Global iot connections 2030, by

application.

Walia, G. K., Kumar, M., and Gill, S. S. (2024). Ai-

empowered fog/edge resource management for iot ap-

plications: A comprehensive review, research chal-

lenges, and future perspectives. IEEE Communica-

tions Surveys & Tutorials, 26(1):619–669.

Wang, D., Ding, H., Yang, Y., Mi, Z., Liu, L., and Xiong, Z.

(2016). Qos and sla aware web service composition

in cloud environment. KSII Transactions on Internet

and Information Systems (TIIS), 10(12):5231–5248.

Wang, M., Fu, W., He, X., Hao, S., and Wu, X. (2020).

A survey on large-scale machine learning. IEEE

Transactions on Knowledge and Data Engineering,

34(6):2574–2594.

Wang, Y., Gao, J., Cheng, T., Gong, Y., and Wu, T.-H.

(2024). Does blockchain technology need to be intro-

duced in the closed-loop supply chain based on prod-

uct lifecycle management? Computers & Industrial

Engineering, 188:109881.

Wehner, S., Elkouss, D., and Hanson, R. (2018). Quan-

tum internet: A vision for the road ahead. Science,

362(6412):eaam9288.

ICSBT 2024 - 21st International Conference on Smart Business Technologies