Traffic Light Control in Vehicular Network Systems using Fuzzy Logic

Abood, Ahmed Najm · 2024 · Crossref

DOI: 10.24018/compute.2024.4.4.132

archive: archived pipeline: cataloged verified

Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)

Summary

This paper addresses the growing challenge of urban traffic congestion, which leads to increased travel times, excessive fuel consumption, and environmental hazards. The authors identify a critical limitation in traditional traffic signal management systems, which rely on fixed timing plans or basic sensors that fail to adapt to dynamic traffic conditions. To resolve this inefficiency, the study proposes a novel traffic signal control algorithm integrated into Vehicular Network Systems (VNS) using fuzzy logic. The primary objective is to design a system that dynamically adjusts signal timings and green light durations based on real-time traffic intensity data, thereby minimizing driver delay and optimizing traffic flow. The methodology focuses on a two-phase traffic signal setup at a four-street intersection, where streets are synchronized in pairs. The system utilizes input attributes such as street volume and vehicle queue length to determine optimal signal settings. The problem is formally modeled using discrete time intervals, defining queue lengths and departure rates based on signal states and saturation parameters. An uncertainty factor is incorporated to handle data variations. The proposed algorithm was implemented and evaluated using MATLAB 2022b simulations on a standard computing environment. The primary evaluation metric was the average waiting time of vehicles, calculated based on queue length and passage time per vehicle. Simulation results demonstrate that the fuzzy logic-based controller effectively stabilizes traffic flow and reduces congestion. In specific scenarios, the controller adjusted signal phases to clear backlogs, such as reducing a queue of 13 vehicles on the first street within approximately 280 seconds. Comparative analysis reveals significant improvements in efficiency. The proposed method achieved an average waiting time of 22.1 seconds (reported as 21.7 seconds in the abstract and conclusion), outperforming a reference method that recorded 26 seconds. Furthermore, the system performed better than other established approaches, including Fixed-Time Traffic Signal Systems (41 seconds), Adaptive Traffic Signal Control (32 seconds), and Deep Q-Network methods (35 seconds). The study concludes that integrating fuzzy logic into vehicular network-based traffic control significantly enhances system stability and efficiency by handling data uncertainties and adapting to real-time conditions. The reduction in average waiting times highlights the superiority of this adaptive approach over static or less flexible control methods. These findings suggest that Intelligent Transportation Systems leveraging connected vehicle data and fuzzy logic can substantially improve urban traffic management, offering a viable solution for reducing delays and improving overall transport security and efficiency.

Provenance

The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed.

Summary generated by qwen3.6-27b-prismaquant on 2026-06-26; verification: verified.

Topics

Ranked by relevance to this paper. Hover a topic for its definition.

• adaptive driving beam