A Hybrid Traffic Controller System based on Flower Pollination Algorithm and Type-2 Fuzzy Logic Optimized with Crow Search Algorithm for Signalized Intersections

KORKMAZ, Ersin; AKGUNGOR, Ali Payıdar · 2022 · Crossref

DOI: 10.21203/rs.3.rs-563478/v1

archive: archived pipeline: cataloged verified

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

Summary

This study addresses the challenge of optimizing traffic signal control at intersections to minimize vehicle delay and improve intersection performance amidst increasing urban traffic density. Traditional fixed-time and actuated controllers often fail to balance safety and efficiency, while existing artificial intelligence approaches typically optimize only signal timing, neglecting the impact of phase plans and sequences. The authors propose a Hybrid Traffic Signal Controller (HTSC) that simultaneously optimizes phase plans, phase sequences, and signal timing. This system integrates the Flower Pollination Algorithm (FPA) for phase and cycle length optimization with a Type-2 Fuzzy Logic controller, optimized by the Crow Search Algorithm (CSA), for dynamic signal timing adjustments. The research employs a modular simulation framework developed in MATLAB using the KU-Trsim microscopic traffic simulation program. The system operates in two main modules: a phase optimization module and a signal timing optimization module. The phase optimization module uses the FPA to determine the optimal number of phases (2, 3, or 4), phase sequence, and cycle length based on intersection geometry and traffic volumes, utilizing the Highway Capacity Manual (HCM) delay formula as the objective function. Safety constraints are enforced, such as requiring separate phases for left turns if conflicting traffic volumes exceed specific thresholds. The signal timing module uses CSA-optimized Type-2 Fuzzy Logic to adjust green times dynamically based on real-time queue lengths and vehicle counts. The system was tested across nine different traffic conditions and four intersection geometries. The results demonstrate that the HTSC significantly outperforms existing control methods. Compared to a fixed-time traffic controller, the HTSC achieved approximately a 32% improvement in performance. It also showed superior performance compared to a controller using only FPA for phase optimization (FPA_TSC) and an optimized Type-1 Fuzzy Logic controller (Type-1 FL-TSC), with improvements of 5% and 6%, respectively. The study highlights that the simultaneous optimization of phase plans and signal timing allows the system to adapt more effectively to stochastic traffic conditions than methods optimizing timing alone. The significance of this work lies in the development of a dynamic control approach that addresses the limitations of previous systems by integrating phase and timing optimization. The HTSC contributes to reducing vehicle delays, emissions, and fuel consumption while minimizing driver dissatisfaction. The authors conclude that this hybrid approach offers a fast, high-performance alternative for intersection control, suitable for implementation by highway and municipal authorities. The study validates the effectiveness of combining meta-heuristic algorithms (FPA and CSA) with advanced fuzzy logic (Type-2) to handle the uncertainties inherent in traffic flow management.

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