Energy Efficient Dynamic Driving Technique Modeling with Flower Pollination and Grey Wolf Optimization Algorithms in Urban Rail Transportation
- 24 July 2025
- journal article
- Published by SAGE Publications in Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology
- Vol. 50 (4) , 1173-1197
Abstract
Energy efficiency and management studies in rail transport worldwide have focused on optimizing reducing traction energy consumption, which accounts for a significant portion of operating costs. The development of energy-efficient driving techniques and the recovery of braking energy offer significant potential for reducing traction energy consumption and costs in rail systems. This study introduces a novel Energy-Efficient Dynamic Driving Technique (EEDDT) model, designed to optimize speed profiles and travel dynamics of rail vehicles by minimizing traction energy consumption (MTEC), maximizing regenerative braking energy production (MRBEP), and minimizing total travel time (MTT). The proposed model incorporates a multi-objective optimization framework and leverages two advanced metaheuristic algorithms—the Flower Pollination Algorithm (FPA) and Grey Wolf Optimizer (GWO)—to determine optimal acceleration, cruising, coasting, and braking regimes. In contrast to existing approaches, the model integrates real-world operational factors, including gradient effects, speed-dependent resistance, horizontal curvature constraints, and passenger load variability, enhancing simulation accuracy and applicability. The model is validated through empirical data collected from a 4.6 km segment of the Samsun urban tramway system consisting of seven stations. Simulation results demonstrate that the EEDDT model achieves up to a 48.95% reduction in total energy consumption, a 137.60% increase in regenerative energy recovery, and 99.62% travel time adherence compared to conventional driving strategies. The findings confirm the practical viability of the EEDDT framework in enhancing energy efficiency in urban rail networks, with FPA demonstrating superior performance in constraint optimization. Overall, this study contributes a scalable, data-driven, and optimization-based approach to sustainable urban rail operations.Keywords
This publication has 27 references indexed in Scilit:
- Optimisation of Train Timetables for Regenerative Braking2023
- Rail train operation energy-saving optimization based on improved brute-force searchApplied Energy, 2022
- Control strategy of hybrid energy storage in regenerative braking energy of high-speed railwayEnergy Reports, 2022
- Nature-inspired algorithms for feed-forward neural network classifiers: A survey of one decade of researchAin Shams Engineering Journal, 2020
- Train operation optimization with adaptive differential evolution algorithm based on decompositionIEEJ Transactions on Electrical and Electronic Engineering, 2019
- Grey wolf optimizer: a review of recent variants and applicationsNeural Computing and Applications, 2017
- Review of energy-efficient train control and timetablingEuropean Journal of Operational Research, 2017
- Grey Wolf OptimizerAdvances in Engineering Software, 2014
- Operating speed pattern optimization of railway vehicles with differential evolution algorithmInternational Journal of Automotive Technology, 2013
- Flower Pollination Algorithm for Global Optimization2012