Lyudmila VOLOSHCHUK, PhD (Engin.), Assoc. Prof.
ORCID ID: 0000-0002-2510-0038
e-mail: lavstumbre@gmail.com
Odessa I. I. Mechnikov National University, Odesa, Ukraine
Oleksandr SBITNEV, PhD Student
ORCID ID: 0009-0008-6311-612X
e-mail: alexsbitnev99@gmail.com
Odessa I. I. Mechnikov National University, Odesa, Ukraine
DOI: https://doi.org/10.17721/AIT.2024.1.10
Abstract
B a c k g r o u n d . This paper presents a new architecture for an intelligent transportation system (ITS) that leverages Internet of Things (IoT) technologies and the Azure cloud platform. The scientific novelty lies in the development of an architecture that integrates edge computing, cloud services, and machine learning algorithms for adaptive traffic management based on real-time data. The proposed architecture efficiently processes traffic flow information, performs modeling, and automatically adjusts traffic signals to reduce congestion. The effectiveness of the architecture has been validated through a series of experiments focused on vehicle recognition, traffic signal optimization, and real-time monitoring of the traffic situation.
M e t h o d s . The methods used include computer simulation modeling for managing the intelligent transportation system, reinforcement learning for training the system, and computer vision techniques for vehicle recognition.
R e s u l t s . The proposed ITS architecture is based on IoT technologies, enabling real-time data collection and analysis of road traffic. The developed system was tested in various urban areas with different levels of traffic load. The experiments demonstrated that t he system can adaptively adjust traffic signals based on traffic analysis, significantly improving road capacity and reducing congestion.
C o n c l u s i o n s . The results of the experiments confirmed the effectiveness of the proposed intelligent transportation system architecture. Future research may focus on enhancing the system by incorporating more advanced artificial intelligence algorithms for automating traffic signal management decisions.
K e y w o r d s : intelligent transportation system, cloud platform, transportation system optimization, IoT system architecture design.
Published
2024-12-20
How to Cite
Lyudmila VOLOSHCHUK, Oleksandr SBITNEV “ HYBRID CLOUD-BASED INTELLIGENT TRAFFIC MONITORING IOT SYSTEM FOR A RESIDENTIAL AREA” Advanced Information Technology, vol.1(3), pp. 83–96, 2024
Issue
Advanced Information Technology № 1 (3), 2024
Section
Network and internet technologies
References
El-Tantawy, S., Abdulhai, B., & Abdelgawad, H. (2014). Design of reinforcement learning parameters for seamless application of adaptive traffic signal control. Journal of Intelligent Transportation Systems, 18(3), 227-245.
Hunt, P. B., Robertson, D. I., & Bretherton, R. D. (1981). SCOOT – A traffic responsive method of coordinating signals. TRL Laboratory Report, 1014. Katerna, O. (2019). Intelligent transport system: The problem of definition and the formation of the classification system. Economic Analysis, 29(2), 33-43.
Klyuev, S. O., Tsymbal, S. V., & Sihonin, A. E. (2023). Development of intelligent transport systems. Bulletin of Mechanical Engineering and Transport, 2(18),80-84. https://doi.org/10.31649/2413-4503-2023-18-2-80-86
Sbitnev, O. Yu. (2022). Research and development of cloud-based control systems for IoT networks (Master’s thesis). Odessa. Wiering, M., & van Otterlo, M. (2012). Reinforcement learning: State-of-the-art. Springer.
Gayratov, Z. K., Kilichov, J. R., & Toshpulatov, A. (2022). Basic definitions of twelve layer IoT architecture for smart city. In International Scientific and Technical Conference: Digital Technologies: Problems and Solutions of Practical Implementation in the Industry.
Danshyna, S. Yu., Nechausov, A. S., & Andrieiev, S. M. (2022). Information technology of transport infrastructure monitoring based on remote sensing data. Радіоелектроніка, інформатика, управління, 4, 7–14. https://doi.org/10.15588/1607-3274-2022-4-7