Adaptive Time-Based Clustering for Optimizing Bus Fleet Management: A Case Study on İzmir’s Public Transportation System

Authors : Nurhan Dudaklı, Behice Meltem Kayhan, Ümit Kuvvetli

Pages : 362-387

Doi:10.26650/JTL.2025.1609360

View : 80 | Download : 163

Publication Date : 2025-11-11

Article Type : Research Paper

Abstract :This study introduces an adaptive time-based clustering strategy to optimize bus fleet requirements in public transportation systems by leveraging passenger boarding data from İzmir\\\'s network. Addressing key challenges in scheduling and fleet sizing, the proposed method uses the K-Means clustering algorithm to segment boarding densities into optimally determined time intervals specific to each bus line and direction. By adapting the number and boundaries of time intervals to actual demand patterns across weekdays and weekends, the model offers a more responsive and efficient allocation of fleet resources. The results demonstrate that the adaptive clustering approach significantly outperforms the conventional fixed-interval strategy, reducing both maximum and average bus requirements while maintaining service quality. This improvement is especially notable for high-demand or highly variable lines, where resource flexibility is critical. While the study shows promising results, it also acknowledges limitations such as the exclusion of passenger waiting times and the diversity of the fleet composition. Future research may include integrating alternative clustering algorithms, incorporating alighting data, and developing multi-criteria operational planning models. These enhancements will further support the evolution of data-driven, adaptive planning tools for more efficient and sustainable urban transport systems.
Keywords : Public Transportation Optimization, Adaptive Clustering, Frequency setting, Bus Fleet Management

ORIGINAL ARTICLE URL