Urban Traffic Flow Optimization Algorithm
About this article
DOI:
https://doi.org/10.14419/2bkxz345Keywords:
Swarm Intelligence; Metaheuristic Optimization; Traffic Flow Dynamics; Adaptive Search; Driver Behavior ModelingAbstract
Swarm intelligence algorithms inspired by natural and artificial systems have demonstrated strong capability in solving complex optimiza-tion problems. This study proposes a novel population-based metaheuristic, termed the Urban Traffic Flow Optimization Algorithm (UTFOA), which is inspired by adaptive decision making and self-organized traffic dynamics observed in modern urban environments. In the proposed framework, each search agent is modeled as an autonomous driver navigating toward an optimal route under dynamically evolving traffic conditions. The algorithm captures three fundamental traffic behaviors, namely route exploration, adaptive following, and congestion avoidance, and formulates them as mathematical operators that jointly balance global exploration and local exploitation. In addition, traffic pressure and driver experience mechanisms are incorporated to regulate adaptive behavior throughout the iterative search process. Theoretical analysis indicates that the proposed algorithm preserves population diversity, satisfies global convergence conditions under Markov chain theory, and exhibits controllable computational complexity. The proposed model introduces a human-inspired perspective for designing adaptive optimization algorithms.
References
S. Mirjalili, Evolutionary Algorithms and Swarm Intelligence: Principles, Analysis, and Applications. Springer, 2019.
J. Zhang, “Spotted Deer Optimization Algorithm,” Applied Engineering Letters, vol. 10, no. 2, pp. 109–124, 2025. https://doi.org/10.46793/aeletters.2025.10.2.5.
F. A. Hashim and A. G. Hussien, “Snake Optimizer: A novel meta-heuristic optimization algorithm,” Knowledge-Based Systems, vol. 242, p. 108320, 2022. https://doi.org/10.1016/j.knosys.2022.108320.
J. O. Agushaka, A. E. Ezugwu, and L. Abualigah, “Gazelle Optimization Algorithm,” Neural Computing and Applications, vol. 35, no. 5, pp. 4099–4131, 2023. https://doi.org/10.1007/s00521-022-07854-6.
T. S. Ayyarao, N. S. S. Ramakrishna, and R. M. Elavarasan, “War Strategy Optimization Algorithm,” IEEE Access, vol. 10, pp. 25073–25105, 2022. https://doi.org/10.1109/ACCESS.2022.3153493.
View more references (3)
S. Gupta and B. S. Yıldız, “Comparison of metaheuristic optimization algorithms for constrained engineering design,” Expert Systems with Applications, vol. 183, p. 115351, 2021. https://doi.org/10.1016/j.eswa.2021.115351.
S. O. Oladejo and S. Mirjalili, “Hiking Optimization Algorithm: A Human-Based Metaheuristic Approach,” Knowledge-Based Systems, vol. 296, p. 111880, 2024. https://doi.org/10.1016/j.knosys.2024.111880.
J.-S. Pan and S.-C. Chu, “Gannet Optimization Algorithm,” Mathematics and Computers in Simulation, vol. 202, pp. 343–373, 2022. https://doi.org/10.1016/j.matcom.2022.06.007.