Optimizing Public Transit Networks: A 5G/6G Approach to Smart Traffic Solutions

Abstract

Public transportation (PT) systems play a vital role in urban mobility, yet the lack of synchronization between trip planning resources often leads to user frustration and potential shifts towards private vehicle usage, exacerbating traffic congestion and environmental concerns. This paper proposes leveraging 5G/6G networks to enhance communication within PT networks, addressing issues of timetable accuracy, route management, and environmental monitoring. Through continuous data transmission from vehicles to the mobile communication network, aided by AI algorithms in Network Data Analytics Function (NWDAF) precise arrival time predictions, real-time route adjustments, and environmental data capture are facilitated. This innovative approach aims to improve the reliability and accessibility of PT, ultimately fostering sustainable urban development and enhancing societal well-being.

Full text

Optimizing Public Transit Networks:
A 5G/6G Approach to Smart Trac Solutions
Maryam Arabshahi 1, Sanket Partani 2
1German Research Center for Articial Intelligence (DFKI)
2RPTU University of Kaiserslautern-Landau
Abstract
Public transportaon (PT) systems play a vital role in urban mobility, yet the lack of synchronizaon
between trip planning resources oen leads to user frustraon and potenal shis towards private
vehicle usage, exacerbang trac congeson and environmental concerns. This paper proposes
leveraging 5G/6G networks to enhance communicaon within PT networks, addressing issues of
metable accuracy, route management, and environmental monitoring. Through connuous data
transmission from vehicles to the mobile communicaon network, aided byAI algorithms in Network
Data Analycs Funcon (NWDAF) precise arrival me predicons, real-me route adjustments, and
environmental data capture are facilitated. This innovave approach aims to improve the reliability
and accessibility of PT, ulmately fostering sustainable urban development and enhancing societal
well-being.
Introduction
Public transportaon services in cies have mulple methods for planning trips - mobile applicaons,
paper metables at bus stops, digital displays indicang arrival mes, or mapping services like Google
Maps. However, these resources oen lack synchronizaon, leading to frustraon among users.
Discrepancies may arise between planned trip details and real-me bus arrivals, parcularly when
disrupons such as road construcons occur, temporarily rendering certain bus stops inaccessible.
Unfortunately, these changes are not promptly reected in mapping applicaons or ulity-developed
apps. Previous studies have indicated that users experience more dissasfacon from unexpected
delays compared to ancipated delays [5]. This can potenally steer them towards private vehicle
usage instead of PT, which in turn exacerbates trac congeson, extends commute mes, and ele-
vates levels of air polluon, contribung to environmental degradaon and public health concerns
[2]. Moreover, trac congeson and polluon entail economic ramicaons such as producvity
losses, increased fuel consumpon, and infrastructural damage [9]. The next generaon of wireless
communicaon technologies, i.e., B5G/6G, are being developed with sustainability at its core. This
implies that these networks should not only enhance communicaon but also catalyze sustainable
development across various sectors. NWDAF, introduced as a pivotal component of the 5G Core
Network (CN) architecture, includes advanced data analycs capabilies to meet the demands of
emerging applicaons and services. This 3GPP standardized method collects data from across the
communicaon system, enabling comprehensive analysis and seamlessly integrates AI/ML models.
We aim to leverage these technologies to opmize PT services in any urban region. By providing
real-me and accurate arrival me predicons to the users, we aim to reduce the inconsistencies
and consequently, provide the user with beer planning, travelling and re-scheduling opons.
Figure 1. NWDAF in 5G/6G Core monitors the PT services
Methodology
Data Collecon:
A boom-up approach is used to predict the arrival mes of PT services. This approach primarily
entails gathering vehicular trac informaon such as posion, speed, etc. from all (acve)
connected vehicles, including PT services in the city.
Predicve Analycs with NWDAF:
With the availability of real-me data at the CN, NWDAF is leveraged to predict changes in PT
schedule for each stop in the city and subsequently, transmit this informaon to the users.
NWDAF can accurately predict bus arrival mes (a(t)) by factoring in the current coordinates
(C(t)) of the bus at me t, constant minimum travel me between consecuve stops (m) and any
delays from the trac condions (T(t)) in the city – signalized juncons, trac density per lane
during peak/o-peak hours, etc. (Formula 1)
a(t) = f(C(t), m, T (t)) (1)
Graph-Based Trac Predicon:
Modelling and predicng trac behaviour has always been a complex task. We propose to
predict the trac condions by realizing the city roads as a graph, with juncons as nodes and
streets as arcs. It can be further divided into manageable sub-graphs by clustering nodes based
on their coordinates (see Figure 2). Based on the latest informaon from all connected vehicles,
the me of the day and the locaon of dierent buildings in the city, trac density on all arcs can
be predicted for each sub-graph and consequently, any delays in the PT schedule can be
computed.
Acknowledgemnet
The authors acknowledge the nancial support by the German Federal Ministry for Educaon and
Research (BMBF) within the project Open6GHub {16KISK003K}.
Results
Our experimentaon focused on simulang trac paerns within Kaiserslautern, a representave
city in Germany, during one hour of the morning rush hour. To conduct our analysis, we employed
SUMO (Simulaon of Urban Mobility) [6], a widely-ulized tool for urban mobility simulaon. Ad-
dionally, we ulized data from OpenStreetMapato construct a realisc use-case scenario. Our
simulaon incorporated ve disnct bus lines traversing a network of 50 bus stops within the city.
Through rigorous examinaon of the simulaon output data, we observed signicant disparies in
me delays experienced across the various bus stops. Notably, these delays ranged from a minimum
of -3301.0 seconds to a maximum of 2699.0 seconds. To provide a comprehensive understanding
of the observed delays, we computed the average delay me for each bus stop. The results, illus-
trated in Figure 3, highlight the distribuon of delay mes across the network. Notably, the mean
delay across all bus stops was calculated to be 42.1 seconds. These ndings underscore the inherent
variability in modelling transit performance within urban environments and provide valuable insights
into potenal areas for opmizaon.
Figure 2. Clustered nodes in Kaiserslautern, Germany using K-Means
Figure 3. Bus arrival me delay at 50 bus stops.
Conclusion and Future Work
This paper presents an innovave approach ulizing 5G/B5G/6G technology to enhance PT com-
municaon networks. This is sll a work in progress that aims to address crical challenges such
as RTI accuracy, route planning and management, and environmental monitoring. As part of future
work, we will focus on several key areas. Firstly, we will connue simulang the trac model in the
example city and implement various mobility scenarios. By applying AI algorithms, we aim to idenfy
changes in PT behavior and dynamically adjust routes and schedules to opmize eciency. Addi-
onally, we plan to ulize AI algorithms to idenfy mul-modal hotspots in the city in real-me. This
informaon, combined with data collected from PT by NWDAF, will enable city management to not
only opmize routes and stop locaons, but also provide more modes for travelling, thereby, improv-
ing overall urban mobility. Furthermore, by leveraging insights into PT behavior and city hotspots,
Mobile Network Operators (MNOs) can opmize network slicing and resource allocaon, ensuring
service connuity and improving user experience.
References
[1] American Public Health Associaon et al. The hidden health costs of transportaon. American Public Health Associaon, 2010.
[2] Linda Bailey, Patricia L Mokhtarian, and Andrew Lile. The broader connecon between public transportaon, energy conservaon and
greenhouse gas reducon. Technical report, ICF Internaonal Fairfax, VA, 2008.
[3] Candace Brakewood and Kari Watkins. A literature review of the passenger benets of real-me transit informaon. Transport Reviews,
39(3):327–356, 2019.
[4] Teije Gorris. CIVITAS INSIGHT: Real-me informaon for public transport, 2020.
[5] Hiroyuki Iseki and Brian D. Taylor. Not all transfers are created equal: Towards a framework relang transfer connecvity to travel
behaviour. Transport Reviews, 29(6):777–800, 2009.
[6] Pablo Alvarez Lopez, Michael Behrisch, Laura Bieker-Walz, Jakob Erdmann, Yun-Pang Flöeröd, Robert Hilbrich, Leonhard Lücken,
Johannes Rummel, Peter Wagner, and Evamarie Wießner. Microscopic trac simulaon using sumo. In The 21st IEEE Internaonal
Conference on Intelligent Transportaon Systems. IEEE, 2018.
[7] Sarah Jo Peterson. The Transportaon Research Board, 1920⬔ 2020: Everyone Interested Is Invited. Naonal Academies Press, 2019.
[8] Ramjee Prasad and Rute C Soa. 6G Visions for a Sustainable and People-centric Future: From Communicaons to Services, the CONASENSE
Perspecve. CRC Press, 2023.
[9] David Schrank, Tim Lomax, and S Turner. Urban mobility report texas transportaon instute. Texas: Texas Transportaon Instute, 2009.
[10] Salih Sevgican, Meriç Turan, Kerim Gökarslan, H. Birkan Yilmaz, and Tuna Tugcu. Intelligent network data analycs funcon in 5g cellular
networks using machine learning. Journal of Communicaons and Networks, 22(3):269–280, 2020.
ahps://www.openstreetmap.org/copyright
maryam.arabshahi@dfki.de partani@eit.uni-kl.de https://www.open6ghub.de https://www.dfki.de