KNOWLEDGE BASED TRAFFIC SIGNAL CONTROL MODEL FOR SIGNALIZED INTERSECTION

Pranevičius, Henrikas; Kraujalis, Tadas · 2012 · OpenAlex-citations

DOI: 10.3846/16484142.2012.719545

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 challenge of optimizing traffic signal control at isolated intersections to mitigate congestion and accidents caused by increasing vehicle volumes. The authors critique conventional fixed-time controllers, which rely on historical data and fail to adapt to real-time traffic fluctuations, and fuzzy logic controllers (FLC), which, while adaptive, can be complex. Motivated by the need for a system that handles uncertainty using expert knowledge, the study proposes a novel Expert Knowledge-based Controller (EKC). This method aims to provide adaptive signal timing that adjusts phase lengths in response to changing traffic conditions, offering a potentially simpler and more effective alternative to existing intelligent transportation system approaches. The proposed EKC method utilizes fuzzy set theory to model expert decision-making, functioning similarly to a human traffic controller. The system takes two primary inputs: the average queue length of vehicles at the current green phase ($Q_{green}$) and the average queue length at the next green phase ($Q_{red}$), the latter calculated from residual vehicles and new arrivals. Using specific membership functions, the controller determines the degree of association for two actions: "extend green" or "terminate green." The decision module compares these membership grades; if the urgency to extend the current green phase exceeds the urgency to terminate it, the signal is extended. Otherwise, the system switches to the next phase. The performance of the EKC was evaluated through simulations using the 'Arena' software, comparing it against a fixed-time controller (based on Webster’s optimization) and an FLC (based on Zhang et al., 2005). The simulation involved a three-approach intersection with varying traffic volumes, ranging from light (288 veh/hr) to heavy (680 veh/hr), measuring average stopped delay as the primary performance metric. The simulation results demonstrate that the EKC outperforms both fixed-time and fuzzy logic controllers under most conditions. In scenarios with equal traffic volumes across approaches, the EKC consistently produced lower average delays than the FLC and significantly lower delays than the pre-timed controller, particularly as traffic volume increased. For instance, at 580 veh/hr, the EKC reduced average delay to 62.71 seconds, compared to 77.50 seconds for FLC and 69.48 seconds for pre-timed control. In scenarios with unequal traffic volumes, the EKC also showed superior performance, achieving an overall average delay 18.67% lower than the FLC and 34.23% lower than the pre-timed controller. While the EKC and FLC performed similarly under low traffic conditions, the EKC maintained an advantage during heavy traffic flows, where the FLC sometimes produced higher delays than even the fixed-time controller. The significance of this research lies in the validation of an expert knowledge-based approach for traffic signal control that effectively handles real-time uncertainties. The findings suggest that the EKC provides a robust, adaptive solution for isolated intersections, reducing vehicle delays and improving traffic flow efficiency compared to established methods. By simplifying the decision-making process to two key queue parameters and using straightforward fuzzy membership comparisons, the EKC offers a practical implementation for intelligent transportation systems. The study concludes that this method is particularly effective in managing heavy traffic conditions, highlighting its potential for broader application in urban traffic management to enhance system efficiency and reduce congestion.

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