Algorithm of Intelligent Urban Traffic

Boguto, Denys Gennadiyovich; Kadomskiy, Kirilo Kostantinovich; Nikolyuk, Peter Karpovich; Pidgurska, Anastasia Igorivna · 2019 · DOAJ

DOI: 10.26565/2304-6201-2019-42-02

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 persistent problem of urban traffic congestion in large metropolises, identifying road intersections as the primary source of bottlenecks. The authors propose a two-phase intelligent traffic regulation system designed to optimize vehicle movement both at individual intersections and across the entire city network. The motivation stems from the limitations of current GPS navigation technologies, which typically calculate geometrically optimal routes rather than time-optimal ones based on real-time traffic dynamics. The methodology involves a combination of hardware sensors and algorithmic software. In the first phase, piezoelectric sensors (specifically RoadTrax BL) are embedded in road surfaces at intersections to register vehicle wheel pairs. These sensors are categorized as input or output devices, counting vehicles entering or leaving specific road segments between adjacent intersections. This data feeds into a City Traffic Management System (CTMS) that dynamically adjusts traffic light phases. A Java-based program calculates the duration of red, yellow, and green lights for horizontal and vertical directions based on the real-time traffic load ratio, ensuring that more congested directions receive longer green phases. In the second phase, the system plans optimal routes for individual vehicles using the A*-algorithm. The urban road network is modeled as a weighted graph where edge weights represent vehicle impedance, calculated dynamically from the ratio of vehicles entering versus leaving a road segment. The system updates these weights every 10 seconds to reflect current traffic conditions. The algorithm minimizes travel time by selecting paths with the lowest impedance, effectively avoiding blocked or congested lanes. The authors provide Java code implementations for both the traffic light regulator and the A*-search algorithm. Testing of the routing algorithm on a graph with up to 150 vertices and 430 edges demonstrated an execution time of 4.58 seconds, with an algorithmic complexity of O(n). The significance of this work lies in its potential to synchronize traffic flows and eliminate congestion by shifting from static or geometric routing to dynamic, time-based optimization. By integrating stationary sensor data with mobile GPS information, the system offers a real-time, online mode of traffic control that radically differs from existing navigation systems. The authors conclude that this technology can significantly reduce travel times, improve the efficiency of urban transport arteries, and elevate city traffic management to a qualitatively new level through complete synchronization of vehicle movements.

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.

• traffic density