An Optimized Fog Computing Architecture for Real-Time Traffic Management in Intelligent Transportation Systems

International Journal of Computer Science and Technology | Vol. 1, No. 4, April 2020 | pp. 25–32

Research Article

Title: An Optimized Fog Computing Architecture for Real-Time Traffic Management in Intelligent Transportation Systems

Names of Authors: Marco Rossi¹, Elena Bianchi², and Giovanni Moretti³

Authors’ Affiliations:
¹Department of Computer, Control, and Management Engineering, Sapienza University of Rome, Rome, Italy
²Department of Information Engineering, University of Pisa, Pisa, Italy
³Department of Electronic Systems, Polytechnic University of Milan, Milan, Italy

Abstract: Intelligent transportation systems (ITS) generate massive volumes of real-time vehicular telemetry and video surveillance data that overwhelm centralized cloud infrastructures due to excessive network bandwidth consumption and propagation latency. Offloading time-critical traffic control operations to decentralized fog computing nodes deployed along roadways provides a viable solution for ultra-low latency processing. However, dynamic vehicular mobility and heterogeneous resource allocations create significant challenges in task scheduling and load balancing across distributed fog layers. This paper presents an optimized, context-aware fog computing architecture designed for real-time traffic signal optimization and congestion prediction. The architecture utilizes a dynamic multi-tier task offloading algorithm based on priority-queue scheduling and reinforcement learning to distribute computational workloads between local roadside units (RSUs) and central cloud servers. Analytical models incorporate parameters such as queue length, packet arrival rates measured in packets/sec, and processing capacity measured in gigahertz (GHz). Real-world trace-driven simulations demonstrate that the proposed fog framework reduces end-to-end latency by 41.6% and decreases wide-area network bandwidth utilization by 53.2% compared to pure cloud-centric paradigms. Furthermore, dynamic traffic light phase adjustments improve average vehicle intersection throughput by 18.9% during peak commuting hours. The results illustrate that distributed fog orchestration enhances responsiveness and scalability in modern smart city transportation networks.

Keywords: Fog computing, Intelligent transportation systems, Task offloading, Real-time processing, Reinforcement learning, Smart cities

Manuscript Timeline: Received: January 12, 2020; Revised: February 20, 2020; Accepted: March 18, 2020; Published: April 1, 2020

Citation: Rossi, M., Bianchi, E., & Moretti, G. (2020). An optimized fog computing architecture for real-time traffic management in intelligent transportation systems. International Journal of Computer Science and Technology, 1(4), 25–32. DOI: 10.46882/2020/IJCST/000004

Subscribe to read the full article: https://internationalscholarsjournals.org/subscribe-to-read