Digital Twins for Trafﬁc Congestion in Smart Cities: A Novel Solution

Using Data Mining Techniques

Arianna Anniciello

, Simona Fioretto

, Elio Masciari

and Enea Vincenzo Napolitano

Department of Electrical and Information Technology Engineering, University of Naples Federico II, Italy

Keywords:

Smart Cities, Digital Twins, Data Mining.

Abstract:

This article serves as a position paper that explores the complex issue of trafﬁc management in smart cities

and the challenges it presents. The problem of urban trafﬁc is particularly relevant in our modern world,

where more and more people are moving to urban environments, leading to congestion, pollution and reduced

quality of life. To address this challenge, we propose an innovative methodology based on Digital Twins.

The paper proposes an extended approach that integrates Digital Twins with other existing techniques such

as Trajectory Mining, Process Mining, and Decision Making. These techniques, which combine motion data,

process analysis, and data-driven Decision Making, can enrich the Digital Twin model, provide a deeper

understanding of trafﬁc ﬂows, and deliver more targeted and effective trafﬁc management solutions. This

proposal represents a signiﬁcant step forward in the search for innovative and sustainable solutions for urban

trafﬁc management, and lays the foundation for further research and development in this critical area.

1 INTRODUCTION

In recent years, the concept of Smart Cities has

emerged as a transformative approach to addressing

the challenges of urbanisation through the use of ad-

vanced technologies, data analytics and intelligent in-

frastructure (Yin et al., 2015). Within the context of

smart cities, one of the most pressing issues is urban

trafﬁc congestion, which poses signiﬁcant challenges

to transport systems and affects the quality of life of

residents (Napolitano, 2023).

To address this issue, the use of Digital

Twins(Batty, 2018) offers a novel and promising ap-

proach to provide comprehensive insights into traf-

ﬁc dynamics and support effective Decision Mak-

ing. Digital Twins, as virtual representations of phys-

ical objects or systems, could integrate real-time data,

simulation models and analytics to create a dynamic

digital replica of urban transport networks (El Sad-

dik, 2018). By applying Digital Twins, Smart Cities

can gain valuable insights into trafﬁc patterns, opti-

mise trafﬁc ﬂow and develop intelligent strategies to

alleviate congestion (Deren et al., 2021).

This paper aims to explore a novel application of

Digital Twins to address urban trafﬁc congestion in

https://orcid.org/0000-0002-0941-7481

https://orcid.org/0009-0006-8700-8188

https://orcid.org/0000-0002-1778-5321

https://orcid.org/0000-0002-6384-9891

the context of Smart Cities. Speciﬁcally, it focuses

on the use of Trajectory Mining, Process Mining and

Decision Making techniques in this domain. The pa-

per will explore the concept of Digital Twins and

their role in addressing urban trafﬁc congestion (Jiang

et al., 2021). It will discuss how Trajectory Min-

ing techniques can extract valuable insights from tra-

jectory data collected from vehicles, pedestrians and

other sources. In addition, it will explore the applica-

tion of Process Mining techniques to analyse and op-

timise trafﬁc ﬂow by identifying bottlenecks and inef-

ﬁciencies in transport systems (Rudskoy et al., 2021).

Furthermore, the paper will highlight the importance

of data-driven Decision Making supported by Digi-

tal Twins to enable effective congestion management

strategies. By exploring the application of Trajectory

Mining, Process Mining and Decision Making tech-

niques within the framework of Digital Twins, this

paper aims to contribute to the advancement of Smart

City transport systems. It highlights the potential of

these techniques to improve trafﬁc management, re-

duce congestion and create more efﬁcient and sustain-

able urban transport networks within Smart Cities.

2 RELATED WORK

In literature it is possible to ﬁnd research studies

which integrates Digital Twins with other support-

ing technologies, with the aim of empowering Digital

Anniciello, A., Fioretto, S., Masciari, E. and Napolitano, E.

Digital Twins for Trafﬁc Congestion in Smart Cities: A Novel Solution Using Data Mining Techniques.

DOI: 10.5220/0012208100003598

In Proceedings of the 15th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management (IC3K 2023) - Volume 3: KMIS, pages 241-248

ISBN: 978-989-758-671-2; ISSN: 2184-3228

241

Twins solutions.

In the domain of Process Mining applications

(Van Der Aalst, 2012) that support Digital Twins,

there exists a multitude of studies that focus on var-

ious application areas. In a recent study (Brock-

hoff et al., 2021), the combined utilization of Digi-

tal Twins and Process Mining is investigated, propos-

ing their integration as a means to facilitate the uti-

lization of data and models from future systems in

real-time scenarios. Another publication (Beerepoot

et al., 2023) explores the concept of ”Digital Process

Twins” , which represents the realization of Digital

Twins speciﬁcally designed for what-if process anal-

ysis. This advancement would enable the develop-

ment of sophisticated techniques for automating pro-

cess optimization. In this context, automated process

optimization refers to the ability to identify optimal

interventions within a process to either maximize or

minimize a given objective function. This objective

function is typically deﬁned in terms of one or mul-

tiple performance measures, while adhering to spe-

ciﬁc constraints. Furthermore, in the ﬁeld of architec-

ture, engineering, and construction industry, a study

(Pan and Zhang, 2021) investigates the use of Process

Mining in building information modeling (BIM). The

authors propose a Digital Twin-based framework that

integrates BIM, IoT, and Process Mining, serving as

a practical method to effectively control and optimize

complex construction processes with a high degree of

automation and intelligence.

Several applications of Trajectory Mining and

Digital Twins in Smart Cities can also be found in the

literature.

(Yan et al., 2022a) proposed the use of Digital

Twin technology to analyse and study the behaviour

patterns of real drivers and pedestrians. Through the

use of Digital Twins, a deeper understanding of traf-

ﬁc dynamics and human behaviour can be achieved,

serving as a foundation for the development of ad-

vanced safety and mobility solutions.

In their comprehensive review, Jafari et al.(Jafari

et al., 2023) emphasise the imperative of using state-

of-the-art technology to detect real-time attacks in dy-

namically evolving transport systems. They highlight

the vulnerability of human-centric transportation sys-

tems to data security threats, which necessitates the

integration of Digital Twins technology to effectively

detect and mitigate cyber and physical attacks. Con-

sequently, the use of Digital Twins ensures the es-

tablishment of a safe and reliable environment for all

stakeholders within the transportation domain. In par-

ticular, pedestrians, as an integral part of transport

systems, warrant signiﬁcant attention to ensure their

health and safety.

Du et al. (Du et al., 2021) introduced a novel

scheme for real-time trajectory prediction based on

Digital Twins, speciﬁcally tailored for platoons of

connected intelligent vehicles . By harnessing the

power of Digital Twins, accurate and up-to-date in-

formation on vehicle trajectories within a platoon can

be obtained, facilitating improved coordination and

planning of actions between connected vehicles, ul-

timately leading to increased efﬁciency and safety.

In their study, (Yu et al., 2021) present a data-

driven continuous trajectory modelling approach to

construct a Digital Twin channel. The proposed

methodology includes a data-driven modelling tech-

nique to accurately extract wireless channel charac-

teristics in speciﬁc scenarios, coupled with trajectory

modelling to efﬁciently capture the spatio-temporal

correlations of the wireless channel as user equipment

traverses it. These Digital Twin-based models provide

enhanced capabilities for wireless channel character-

isation, enabling improved wireless network design

and performance optimisation in dynamic and com-

plex environments.

Integration of Digital Twin methods in Decision

Making has been proved in different studies, also con-

sidering application on transportation optimization.

(Zhou et al., 2021) developed a DSS that explores

Digital Twinning and simulation-optimization capa-

bilities for resilience assessment with recovery action

optimization. The Digital Twin replicates detailed

port operations that cannot be captured through more

traditional mathematical modeling approaches. Digi-

tal twinning also enables the modeling of uncertainty

in the disruption events, as well as subsequent port

recovery operations.

(Jiang et al., 2022) present an urban road plan-

ning approach based on Digital Twin, multi criteria

decision making and geographic information system

called DT-MCDM-GIS, highliting how Digital Twin

methods can interpret various data into understand-

able expressions to assist urban road planning con-

sidering various factors, namely building demolition

and land use, trafﬁc congestion, driving route selec-

tion habit, air quality, and noise. (Neto et al., 2021) In

this work, a Decision Support Systems (DSS) for op-

portunistic preventive maintenance scheduling is de-

veloped based on a Digital Twin framework. (Gao

et al., 2022) investigate the application of Building

Information Modeling and Digital Twins in the trans-

portation industry, which indicates that the integration

and utilization of multiple technologies can improve

the schemes of mega engineering projects, improv-

ing the efﬁciency of such projects’ digital manage-

ment over their whole life cycle. We also believe

that it is necessary to further improve the research

KMIS 2023 - 15th International Conference on Knowledge Management and Information Systems

242

design and present the results as clearly as possible

in a future study. (Feng et al., 2023) study explores

the application of Digital Twins in Intelligent Trans-

portation Systems and establishes an innovative trans-

portation platform based on Digital Twins. It inves-

tigates the inﬂuence of the transportation network’s

adaptability on travel behavior by examining how

uncertain events impact travelers’ travel conditions.

Furthermore, a travel behavior model is developed

to enhance the effect of trafﬁc conditions on travel

by considering the impact of uncertain events, par-

ticularly in multi-modal transportation, such as cus-

tomized public transportation. The study also ad-

dresses the issue of data sharing in the Internet of

Vehicles (IoV) trafﬁc system from the perspective

of Digital Twins. To overcome the limitations of

data sharing in Blockchain technology in the IoV,

an LPMADDPG algorithm is proposed and applied

to optimize data sharing. Finally, a Digital Twins

Blockchain trafﬁc system is established and experi-

mentally veriﬁed. Their results demonstrate that the

IoV system based on Digital Twins reported here sig-

niﬁcantly optimizes data sharing and improves the

ability of the transportation network to withstand and

repair the impact of external uncertainty on the trans-

portation system. Besides, it saves more than 50 %

of the communication overhead and improves opera-

tional efﬁciency by nearly 20 % over traditional algo-

rithm.

3 DIGITAL TWINS FOR SMART

CITIES

As cities continue to grow, the challenges associated

with urban living are also expanding. To address

these issues, the concept of Smart Cities has emerged,

which involves the integration of innovative tech-

nologies to make cities more intelligent and efﬁcient.

Among the various challenges faced by cities, trans-

portation management is a crucial aspect that requires

attention. It involves the promotion of sustainable

transportation options, the development of intelligent

public transportation systems based on real-time in-

formation, the implementation of trafﬁc management

systems (TMSs) to mitigate congestion, and the incor-

poration of safety and environmentally friendly appli-

cations. To tackle these transportation-related chal-

lenges in future Smart Cities, researchers have been

actively focusing on utilizing advancements in sens-

ing, communication, and dynamic adaptive technolo-

gies. These efforts aim to enhance the efﬁciency of

existing road TMSs, enabling them to effectively ad-

dress the issues that arise in the context of evolving

cities. (Djahel et al., 2014) discuss the importance of

leveraging these technologies to make transportation

management systems more efﬁcient in the context of

Smart Cities. One approach that has gained attention

in this ﬁeld is the use of Digital Twins. Several au-

thors, including (Kumar et al., 2018) have explored

the application of Digital Twins in managing trafﬁc

congestion. The concept behind the Digital Twin is

to create a virtual representation or image that corre-

sponds to a physical asset, such as vehicles or road

infrastructure. By creating a Digital Twin of these as-

sets, it becomes possible to monitor and manage their

real-time status, behavior, and performance. This vir-

tual representation can provide valuable insights into

trafﬁc patterns, identify congestion points, and en-

able proactive decision-making to alleviate conges-

tion and enhance overall transportation management

in Smart Cities (Kumar et al., 2018). The integration

of Smart Cities involves the use of innovative tech-

nologies to address the challenges associated with ur-

ban living. Transportation management is a key area

of focus, and the utilization of Digital Twins offers a

promising approach to effectively manage trafﬁc con-

gestion by creating virtual representations of vehicles

and road infrastructure. These Digital Twins enable

real-time monitoring and Decision Making, contribut-

ing to more efﬁcient and sustainable transportation

systems in Smart Cities (Kumar et al., 2018).

3.1 Conceptual Framework

A Digital Twin is a virtual version of an object or

system that spans its lifespan, is updated from real-

time data, and aids Decision Making through simula-

tion, Machine Learning, and reasoning. By analysing

evolving client preferences, modiﬁcations, and expe-

riences, Digital Twin is already assisting ﬁrms in stay-

ing ahead of digital disruption (Javaid and Haleem,

2023).

The conceptual framework for Digital Twin tech-

nology involves three core components: the physical

asset, the digital representation, and the connection

between them. (Liu et al., 2021)

• Physical Asset:

The physical asset refers to the tangible entity in

the real world that is being represented by the Dig-

ital Twin. In the context of trafﬁc management, it

could be a transportation infrastructure, such as

roads, highways, intersections, trafﬁc signals, or

vehicles.

The physical asset generates data through various

sensors, devices, and monitoring systems, captur-

ing real-time information about its status, perfor-

mance, and environmental conditions.

Digital Twins for Trafﬁc Congestion in Smart Cities: A Novel Solution Using Data Mining Techniques

243

• Digital Representation:

The digital representation is the virtual counter-

part of the physical asset created within the Dig-

ital Twin environment. It is constructed by in-

tegrating and analyzing data collected from the

physical asset and other relevant sources.

It aims to accurately replicate the physical asset’s

characteristics and behaviors.

The digital representation consists of several key

elements:

– Geometric Model: It represents the physical

asset’s spatial dimensions, topology, and lay-

out. This includes the shape, size, location, and

connectivity of roads, intersections, and other

transportation infrastructure elements.

– Data Integration and Analytics: Various data

sources, such as sensor data, trafﬁc ﬂow in-

formation, weather data, and historical records,

are collected and integrated into the digital rep-

resentation. Advanced analytics techniques,

such as machine learning and data mining, are

applied to gain insights and extract patterns

from the data.

– Simulation and Modeling: The Digital Twin

incorporates simulation and modeling capabil-

ities to replicate the behavior of the physical

asset under different scenarios. This enables

what-if analysis, predictive modeling, and op-

timization of trafﬁc ﬂow, congestion manage-

ment, and other key performance indicators.

– Real-time Data Synchronization: The Digital

Twin continuously receives and updates real-

time data from the physical asset to maintain

its accuracy and relevance. This synchroniza-

tion ensures that the digital representation re-

ﬂects the current state of the physical asset and

enables real-time monitoring and decision mak-

ing.

• Connection and Interaction:

The connection between the physical asset and its

Digital Twin is a fundamental aspect of Digital

Twin technology. It enables bidirectional commu-

nication and interaction between the physical and

virtual realms. Through this connection, real-time

data from the physical asset is fed into the Digital

Twin, while insights, predictions, and optimized

solutions derived from the Digital Twin can be

applied to improve the performance and manage-

ment of the physical asset. This connection facil-

itates continuous monitoring, analysis, and deci-

sion making based on the Digital Twin’s insights

and recommendations.

The interaction between the physical asset and its

Digital Twin forms a closed-loop feedback sys-

tem:

– Data Collection and Integration: Real-time data

from the physical asset, such as trafﬁc volumes,

speed, and environmental conditions, is col-

lected, processed, and integrated into the Digi-

tal Twin.

– Analysis and Decision Making: The Digital

Twin analyzes the collected data, applies ad-

vanced analytics techniques, and generates in-

sights, predictions, and recommendations for

trafﬁc management decision making.(Semeraro

et al., 2021)

– Action and Control: Based on the insights and

recommendations from the Digital Twin, ap-

propriate actions can be taken in the physical

world. This may involve adjusting trafﬁc sig-

nal timings, rerouting vehicles, implementing

congestion management strategies, or optimiz-

ing infrastructure planning.

4 INTEGRATED APPROACH TO

DIGITAL TWIN TECHNOLOGY

FOR TRAFFIC MANAGEMENT

Since Digital Twins are virtual representations of

physical entities or complex systems such as build-

ings, transportation networks, infrastructures, or even

entire cities, using Trajectory Mining and Process

Mining in conjunction with Digital Twins can provide

several beneﬁts and applications in Smart Cities.

• Trajectory Mining. One of the main applica-

tions of Trajectory Mining (Zheng, 2015) with

Digital Twins could be trafﬁc (Xu et al., 2023;

Costa et al., 2014) and transport optimisation. By

analysing the trajectories of both private and pub-

lic vehicles within a city, trafﬁc patterns, critical

points, congestion and ﬂow issues can be identi-

ﬁed (Fan et al., 2022; Zhang et al., 2023). This

information can be used to identify areas for im-

provement, such as adjusting trafﬁc lights, opti-

mising routes or introducing new infrastructure.

In addition, Trajectory Mining can contribute to

the implementation of intelligent trafﬁc manage-

ment systems that can adapt to road conditions in

real time (Tong et al., 2020).

Trajectory Mining with Digital Twins can also

contribute to public safety in Smart Cities. By

analysing the trajectories of people or objects,

such as emergency vehicles or suspicious individ-

uals, anomalous behaviour or risky situations can

be identiﬁed. This information can be used to

KMIS 2023 - 15th International Conference on Knowledge Management and Information Systems

244

improve emergency management, detect critical

situations such as trafﬁc accidents or suspicious

activities in a timely manner, and assist law en-

forcement and emergency services in making de-

cisions.

• Process Mining. Process Mining is a ﬁeld of

research which focuses on the extraction of pro-

cesses from available event logs in Information

Systems. Digital twin and Process Mining are

two different ﬁeld of research, but many stud-

ies proved the efﬁcacy of their joint applica-

tion. (Brockhoff et al., 2021) afﬁrms that espe-

cially process discovery from runtime data, con-

formance checking, and process prediction using

process models at runtime are increasingly impor-

tant aspects to systematically improve the opera-

tion of Digital Twins. Process mining can play a

crucial role in supporting Digital Twins for trafﬁc

congestion management in smart cities, however

very few works apply PM to urban mobility. Cur-

rently, the topic was discussed by (Jadri

c et al.,

2020) who applied in a case study process min-

ing in smart mobility. In addition, it was found

that the research mostly involved implementation

of smart parking solution, and highlighting the

gap between the potentiality of the application and

the existing studies. A recent study (Delgado and

Calegari, 2023) assess with a real case study the

suitability of process mining for the analysis of

urban mobility problems obtaining promising re-

sults in this research.

Given the lack of studies in process mining sup-

porting Digital Twins in the context of trafﬁc con-

gestion, we believe that there are some available

open solutions using the potentiality of process

mining and that could be explored. Some of

the possible application of the technique could

include trafﬁc patterns identiﬁcation identifying

bottlenecks, and gain insights into the causes of

congestion in speciﬁc areas of a city, optimizing

trafﬁc management strategies can help city au-

thorities identify the most efﬁcient trafﬁc manage-

ment strategies to reduce congestion and improve

trafﬁc ﬂow. In addition process mining can be

used to simulate and evaluate the impact of infras-

tructure changes(Fioretto, 2023), such as the ad-

dition of new roads, trafﬁc lanes, or public trans-

portation routes.

• Decision Making. Digital Twins facilitate data-

driven Decision Making by providing a holistic

and real-time view of the urban transportation sys-

tem, offering improved situational awareness to

trafﬁc management stakeholders. By integrating

and analyzing data from various sources, Digi-

tal Twins enable Decision Support Systems (DSS)

tools to provide insights, predictions, and recom-

mendations based on real-time and historical data

analysis. Let us delve the advantages of an In-

telligent Decision Support Systems that leverage

Digital Twin technology. The integration of data

from various sources, including sensors, cameras,

and historical records, provide a comprehensive

view of the urban transportation system. Ad-

vanced analytics techniques applied within the

Digital Twin environment allow for the identiﬁ-

cation of trends, patterns, and correlations in traf-

ﬁc data. The Digital Twin of the physical trans-

portation system is not able to support the dif-

ferent management processes solely, such as re-

source allocation or infrastructure maintenance,

as it is not containing information concerning or-

ders, products, schedules, company speciﬁc prior-

ities and further data that is necessary to control

said processes. Therefore, the Twin must be in-

tegrated into a suitable decision support system

(Kunath and Winkler, 2018). When integrated

data meets real time collection, real-time moni-

toring becomes a reality. By continuously syn-

chronizing with real-time data feeds, the Digital

Twin reﬂects the current state of the physical as-

set of the Urban Transportation System. Ding et

al (Ding et al., 2023) designed a Decision Sup-

port System based on Digital Twin and Big Data

technologies and demonstrate how real-time mon-

itoring and an integrated decision support can be

established. Decision support tools, such as in-

teractive dashboards and scenario analysis inter-

faces, enhance the understanding and interpre-

tation of complex trafﬁc data and allows trafﬁc

management in Smart Cities to have an up-to-

date understanding of trafﬁc conditions, incident

occurrences, and operational metrics. Further-

more, Digital Twins can generate recommenda-

tions based on the analysis and modeling within

the Digital Twin, suggesting optimal strategies

which decision makers can explore, assessing the

potential outcomes, and make informed but timely

decisions, providing quick responses to changing

trafﬁc conditions. Some situations may require

instant intervention, especially when a standard

protocol has been designed for identiﬁed pattern.

Digital Twin facilitates the generation of alerts

and notiﬁcations based on predeﬁned thresholds

or abnormal events detected within the connected

environment. Through real-time data analysis and

comparison with established patterns, the Digi-

tal Twin can identify trafﬁc incidents, congestion

buildup, accidents, or abnormal trafﬁc behavior.

Digital Twins for Trafﬁc Congestion in Smart Cities: A Novel Solution Using Data Mining Techniques

245

When such events occur, the Digital Twin can trig-

ger automated alerts to designed users, such as

trafﬁc operators, emergency responders, or main-

tenance personnel, enabling them to take imme-

diate action and implement appropriate response

measures. Real-time data synchronization and

analysis also allow for the early detection of in-

cidents or abnormal conditions. Upon detecting

such events, the Digital Twin can automatically

generate recommendations for response strategies

(d’Ajello et al., 2022), such as rerouting traf-

ﬁc, adjusting signal timings, or dispatching emer-

gency services. These proactive responses help

minimize the impact of incidents, reduce conges-

tion, and improve safety by facilitating swift and

coordinated actions. The use of Digital Twins for

trafﬁc management provides also resource man-

agement and maintenance beneﬁts. (Yan et al.,

2022b) ﬁndings reveal that data analytics and

the visualized enterprise Digital Twin system of-

fer better practices for strategic management de-

cisions in the dynamic and constantly changing

business world by providing a constant and fre-

quent adjustment on every decision that affects

how the business performs over both operational

and strategic timescales. By leveraging real-

time data and predictive modeling, Smart Cities

can enhance situational awareness, enabling opti-

mized resource allocation in trafﬁc management.

The insights and recommendations derived from

the Digital Twin facilitate efﬁcient deployment

of trafﬁc control measures, such as adaptive sig-

nal timing, dynamic lane management, and inci-

dent response strategies. By identifying areas of

high trafﬁc demand or recurring bottlenecks, re-

sources can be strategically allocated to address

these speciﬁc areas, resulting in a more effec-

tive utilization of infrastructure and services. Ad-

ditionally, Digital Twins provide a platform for

proactive maintenance and infrastructure manage-

ment, allowing for predictive maintenance plan-

ning, optimized repair schedules, and efﬁcient al-

location of maintenance resources. These factors

collectively enable proactive responses and efﬁ-

cient allocation of resources, and contribute to

improved operational efﬁciency and reliability of

the transportation system. Digital Twin technol-

ogy also promotes collaborative Decision Making

among different stakeholders, including trafﬁc en-

gineers, city ofﬁcials, and citizens, by providing a

platform for information sharing, communication,

and participation. The adaptive nature of Digital

Twins allows for iterative improvements and ad-

justments based on real-time data and feedback.

Trafﬁc engineers, city ofﬁcials, and citizens can

access the Digital Twin platform to provide in-

put, voice concerns, and contribute suggestions.

This participatory approach allows for a diverse

range of perspectives and expertise to be con-

sidered, leading to more informed and inclusive

Decision Making. Stakeholders can review pro-

posed strategies, evaluate potential impacts, and

provide feedback, enhancing the overall effective-

ness and acceptance of decisions. Digital twins

are also inherently adaptive, allowing for itera-

tive improvements and adjustments based on real-

time data and feedback. The Digital Twin con-

tinuously synchronizes with real-time data from

the physical asset, updating the digital representa-

tion accordingly. This real-time feedback loop en-

ables stakeholders to monitor the impact of imple-

mented measures, assess their effectiveness, and

make adjustments as needed. By analyzing the

real-time data within the Digital Twin, stakehold-

ers can identify areas for improvement, ﬁne-tune

strategies, and adapt to changing conditions or

emerging challenges. The iterative nature of Dig-

ital Twins supports a continuous learning and im-

provement cycle, enhancing the effectiveness of

decision making over time.

In summary, this technology enhances decision

making by providing timely and accurate infor-

mation, facilitating efﬁcient resource allocation,

and improving the overall management of urban

transportation systems in Smart Cities. It pro-

motes collaborative decision making by enabling

information sharing, stakeholder engagement, and

participatory processes. The ability to simulate

and evaluate alternative scenarios within the Dig-

ital Twin environment further enhances decision-

making capabilities, enabling stakeholders to as-

sess the potential impacts of various strategies be-

fore implementing them in the physical world.

The adaptive nature of Digital Twins allows for

iterative improvements and adjustments based on

real-time data and feedback, fostering continuous

learning, optimization, and alignment of decisions

with the evolving needs of the transportation sys-

tem and its stakeholders in Smart Cities.

5 CONCLUSIONS

In conclusion, this position paper has examined the

application of Digital Twins in addressing urban traf-

ﬁc congestion within Smart Cities. Authors have pre-

sented a compelling argument for the adoption of Dig-

ital Twins as a transformative technology for trafﬁc

KMIS 2023 - 15th International Conference on Knowledge Management and Information Systems

246

management, highlighting their potential to provide

comprehensive insights and support effective deci-

sion making. Digital Twins offer a promising solu-

tion to the pressing issue of urban trafﬁc congestion

by integrating real-time data, simulation models, and

analytics to create dynamic digital replicas of urban

transport networks. This technology enables Smart

Cities to gain a holistic view of trafﬁc dynamics, op-

timize trafﬁc ﬂow, and develop intelligent strategies

to alleviate congestion. By leveraging Digital Twins,

cities can enhance their transportation systems, im-

prove quality of life for residents, and move closer to

their goals of sustainability and efﬁciency. Through-

out the paper, authors have advocated for the adop-

tion and further exploration of Digital Twins in traf-

ﬁc management. The integration of Trajectory Min-

ing, Process Mining, and Decision Making techniques

within the Digital Twin framework presents exciting

opportunities to optimize trafﬁc management strate-

gies, predict trafﬁc patterns, evaluate infrastructure

changes, and enhance public safety. By embracing

Digital Twins, Smart Cities can embrace innovative

approaches and leverage advanced technologies to

tackle the complexities of urban trafﬁc congestion. In

summary, Digital Twins have the potential to revolu-

tionize trafﬁc management in Smart Cities, paving the

way for more efﬁcient, sustainable, and livable urban

environments. While challenges and considerations

exist, such as data privacy and security, infrastructure

requirements, and stakeholder engagement, the ben-

eﬁts offered by Digital Twins outweigh these obsta-

cles. It is essential for policymakers, urban planners,

and researchers to recognize the transformative power

of Digital Twins and work collaboratively to harness

this technology’s full potential in shaping the future

of trafﬁc management in Smart Cities. By embracing

Digital Twins, we can build smarter, more connected,

and more efﬁcient urban transportation systems that

enhance the quality of life for residents and pave the

way for a sustainable future.

REFERENCES

Batty, M. (2018). Digital twins.

Beerepoot, I., Di Ciccio, C., Reijers, H. A., Rinderle-Ma,

S., Bandara, W., Burattin, A., Calvanese, D., Chen,

T., Cohen, I., Depaire, B., et al. (2023). The biggest

business process management problems to solve be-

fore we die. Computers in Industry, 146:103837.

Brockhoff, T., Heithoff, M., Koren, I., Michael, J., Pfeiffer,

J., Rumpe, B., Uysal, M. S., Van Der Aalst, W. M. P.,

and Wortmann, A. (2021). Process prediction with

digital twins. In 2021 ACM/IEEE International Con-

ference on Model Driven Engineering Languages and

Systems Companion (MODELS-C), pages 182–187.

Costa, G., Manco, G., and Masciari, E. (2014). Dealing

with trajectory streams by clustering and mathemati-

cal transforms. Journal of Intelligent Information Sys-

tems, 42(1):155–177.

Delgado, A. and Calegari, D. (2023). Process mining for

improving urban mobility in smart cities: Challenges

and application with open data.

Deren, L., Wenbo, Y., and Zhenfeng, S. (2021). Smart city

based on digital twins. Computational Urban Science,

1:1–11.

Ding, Y., Zhang, Z., Chen, K., Ding, H., Voss, S., Heilig,

L., Chen, Y., Chen, X., et al. (2023). Real-time mon-

itoring and optimal resource allocation for automated

container terminals: A digital twin application at the

yangshan port. Journal of Advanced Transportation,

2023.

Djahel, S., Doolan, R., Muntean, G.-M., and Murphy, J.

(2014). A communications-oriented perspective on

trafﬁc management systems for smart cities: Chal-

lenges and innovative approaches. IEEE Communi-

cations Surveys & Tutorials, 17(1):125–151.

Du, H., Leng, S., He, J., and Zhou, L. (2021). Digital twin

based trajectory prediction for platoons of connected

intelligent vehicles. In 2021 IEEE 29th International

Conference on Network Protocols (ICNP), pages 1–6.

IEEE.

d’Ajello, E., Formica, D., Masciari, E., Mattia, G., Anni-

ciello, A., Moscariello, C., Quintarelli, S., and Zac-

carella, D. (2022). Cluster algorithm for social choice.

In Joint European Conference on Machine Learning

and Knowledge Discovery in Databases, pages 227–

237. Springer.

El Saddik, A. (2018). Digital twins: The conver-

gence of multimedia technologies. IEEE multimedia,

25(2):87–92.

Fan, Z., Yang, X., Yuan, W., Jiang, R., Chen, Q., Song, X.,

and Shibasaki, R. (2022). Online trajectory predic-

tion for metropolitan scale mobility digital twin. In

Proceedings of the 30th International Conference on

Advances in Geographic Information Systems, pages

1–12.

Feng, H., Lv, H., and Lv, Z. (2023). Resilience towarded

digital twins to improve the adaptability of transporta-

tion systems. Transportation Research Part A: Policy

and Practice, 173:103686.

Fioretto, S. (2023). Process mining solutions for public ad-

ministration. In European Conference on Advances in

Databases and Information Systems, pages 668–675.

Springer.

Gao, C., Wang, J., Dong, S., Liu, Z., Cui, Z., Ma, N., and

Zhao, X. (2022). Application of digital twins and

building information modeling in the digitization of

transportation: A bibliometric review. Applied Sci-

ences, 12(21):11203.

Jadri

c, M., Pa

sali

c, I. N., and

Cuku

c, M. (2020). Pro-

cess mining contributions to discreteevent simulation

modelling. Business Systems Research: International

Digital Twins for Trafﬁc Congestion in Smart Cities: A Novel Solution Using Data Mining Techniques

247

journal of the Society for Advancing Innovation and

Research in Economy, 11(2):51–72.

Jafari, M., Kavousi-Fard, A., Chen, T., and Karimi, M.

(2023). A review on digital twin technology in smart

grid, transportation system and smart city: Challenges

and future. IEEE Access.

Javaid, M. and Haleem, A. (2023). Digital twin applications

toward industry 4.0: A review. Cognitive Robotics.

Jiang, F., Ma, L., Broyd, T., Chen, W., and Luo, H. (2022).

Digital twin enabled sustainable urban road planning.

Sustainable Cities and Society, 78:103645.

Jiang, Y., Yin, S., Li, K., Luo, H., and Kaynak, O.

(2021). Industrial applications of digital twins.

Philosophical Transactions of the Royal Society A,

379(2207):20200360.

Kumar, S. A., Madhumathi, R., Chelliah, P. R., Tao, L.,

and Wang, S. (2018). A novel digital twin-centric ap-

proach for driver intention prediction and trafﬁc con-

gestion avoidance. Journal of Reliable Intelligent En-

vironments, 4:199–209.

Kunath, M. and Winkler, H. (2018). Integrating the digi-

tal twin of the manufacturing system into a decision

support system for improving the order management

process. Procedia Cirp, 72:225–231.

Liu, M., Fang, S., Dong, H., and Xu, C. (2021). Review of

digital twin about concepts, technologies, and indus-

trial applications. Journal of Manufacturing Systems,

58:346–361.

Napolitano, E. V. (2023). Intelligent technologies for ur-

ban progress: exploring the role of ai and advanced

telecommunications in smart city evolution. In Euro-

pean Conference on Advances in Databases and In-

formation Systems, pages 676–683. Springer.

Neto, A. A., Carrijo, B. S., Brock, J. G. R., Deschamps,

F., and de Lima, E. P. (2021). Digital twin-driven

decision support system for opportunistic preventive

maintenance scheduling in manufacturing. Procedia

Manufacturing, 55:439–446.

Pan, Y. and Zhang, L. (2021). A bim-data mining integrated

digital twin framework for advanced project manage-

ment. Automation in Construction, 124:103564.

Rudskoy, A., Ilin, I., and Prokhorov, A. (2021). Digital

twins in the intelligent transport systems. Transporta-

tion Research Procedia, 54:927–935.

Semeraro, C., Lezoche, M., Panetto, H., and Dassisti, M.

(2021). Digital twin paradigm: A systematic literature

review. Computers in Industry, 130:103469.

Tong, X., Liu, Q., Pi, S., and Xiao, Y. (2020). Real-time

machining data application and service based on imt

digital twin. Journal of Intelligent Manufacturing,

31:1113–1132.

Van Der Aalst, W. (2012). Process mining: Overview and

opportunities. ACM Transactions on Management In-

formation Systems (TMIS), 3(2):1–17.

Xu, M., Ma, Y., Li, R., Qi, G., Meng, X., and Jin, H.

(2023). Traffnet: Learning causality of trafﬁc gen-

eration for road network digital twins. arXiv preprint

arXiv:2303.15954.

Yan, M., Gan, W., Zhou, Y., Wen, J., and Yao, W.

(2022a). Projection method for blockchain-enabled

non-iterative decentralized management in integrated

natural gas-electric systems and its application in dig-

ital twin modelling. Applied Energy, 311:118645.

Yan, M.-R., Hong, L.-Y., and Warren, K. (2022b). Inte-

grated knowledge visualization and the enterprise dig-

ital twin system for supporting strategic management

decision. Management Decision, 60(4):1095–1115.

Yin, C., Xiong, Z., Chen, H., Wang, J., Cooper, D., and

David, B. (2015). A literature survey on smart cities.

Sci. China Inf. Sci., 58(10):1–18.

Yu, Z., Lv, X., Rui, H., and Lin, W. (2021). Digital twin

channel: A data-driven continuous trajectory model-

ing. In 2021 IEEE 1st International Conference on

Digital Twins and Parallel Intelligence (DTPI), pages

302–305.

Zhang, X., Han, D., Zhang, X., and Fang, L. (2023).

Design and application of intelligent transportation

multi-source data collaboration framework based on

digital twins. Applied Sciences, 13(3):1923.

Zheng, Y. (2015). Trajectory data mining: an overview.

ACM Transactions on Intelligent Systems and Tech-

nology (TIST), 6(3):1–41.

Zhou, C., Xu, J., Miller-Hooks, E., Zhou, W., Chen, C.-H.,

Lee, L. H., Chew, E. P., and Li, H. (2021). Analyt-

ics with digital-twinning: A decision support system

for maintaining a resilient port. Decision Support Sys-

tems, 143:113496.

KMIS 2023 - 15th International Conference on Knowledge Management and Information Systems

248