Integration of Edge, Cloud, and Big Data Analytics for Intelligent Transportation Systems
BigDataStream Mining · 30.06.2025 · 1 (2) · 29
DOI: 10.70023/sahd/b123 ↗Kurz gefasst
Fachartikel in der Zeitschrift BigDataStream Mining, online erschienen am 30.06.2025. Verfasst von Sara Hosseini und 1 weiteren Autor:innen.
Abstract (Originalsprache)
The rapid rise of cities and vehicle traffic has made transportation networks more complex, leading to long-lasting problems such as congestion, slow incident response, inefficient resource use, and higher emissions. Because they rely on centralized cloud-based processing, traditional ITSs struggle to handle large volumes of real-time data due to latency, limited bandwidth, and scalability issues. These limitations underscore the imperative for an intelligent and distributed computing architecture. This research introduces an ITS framework (ECBDA-ITS) that amalgamates Edge, Cloud, and Big Data Analytics to address these challenges. The proposed method leverages cloud computing layers to facilitate the storage of massive amounts of data, optimize global traffic, and train complex models. Edge computing nodes are placed close to data sources to handle real-time data collection, filtering, and analytics that are sensitive to latency. Big data analytics methods are used to extract meaningful information from various transportation data at both levels. Some of these methods are stream processing in real time and using machine learning to estimate traffic. The experimental results show that the ECBDA-ITS framework significantly improves system performance. The results show that the end-to-end latency, accuracy of traffic predictions, speed of incident detection, and scalability of the system are all far better than those of traditional cloud-only ITS infrastructures. The distributed processing method also has the benefit of placing less burden on the network and making it easier to make real-time judgments. The integration of cloud infrastructure, big data analytics, and edge computing can finally deliver a scalable, viable solution for next-generation Intelligent Transportation Systems. The proposed ECBDA-ITS architecture is ideal for managing mobility in smart cities because it combines global intelligence with rapid response capabilities. To make the system more efficient and reliable, further research is needed on how to combine privacy-preserving learning with autonomous vehicle coordination.
Zitieren
APA
Hosseini, S., & Hassan, M. (2025). Integration of Edge, Cloud, and Big Data Analytics for Intelligent Transportation Systems. BigDataStream Mining, 1(2), 29. https://doi.org/10.70023/sahd/b123
Vancouver
Hosseini S, Hassan M. Integration of Edge, Cloud, and Big Data Analytics for Intelligent Transportation Systems. BigDataStream Mining. 2025;1(2):29. doi:10.70023/sahd/b123
BibTeX
@article{Hosseini2025,
author = {Hosseini, Sara and Hassan, Mahmoud},
title = {Integration of Edge, Cloud, and Big Data Analytics for Intelligent Transportation Systems},
journal = {BigDataStream Mining},
year = {2025},
volume = {1},
number = {2},
pages = {29},
doi = {10.70023/sahd/b123}
}
EUVIMED