Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Self-Organizing Railway Traffic Management

Federico Naldini, Fabio Oddi, Leo D'Amato, Grégory Marlière, Vito Trianni, Paola Pellegrini

TL;DR

This work addresses the challenge of railroad traffic perturbations by proposing a fully decentralized self-organizing railway TMS (SO-TMS) that replaces centralized optimization with local cooperation among trains. The authors formalize a modular pipeline—neighborhood identification, hypothesis generation via a RECIFE-MILP variant, hypothesis compatibility checks, adaptive consensus-based hypothesis selection, and a merge/repair stage—to produce feasible real-time traffic plans. Through a closed-loop, microscopic OpenTrack simulation of a busy Italian corridor, the SO-TMS consistently outperforms a state-of-the-art centralized baseline, leveraging instance decomposition for tractability and responsiveness. The findings support the practical viability of decentralized, explainable traffic management that preserves feasibility while improving delay performance in complex, competitive railway networks.

Abstract

Improving traffic management in case of perturbation is one of the main challenges in today's railway research. The great majority of the existing literature proposes approaches to make centralized decisions to minimize delay propagation. In this paper, we propose a new paradigm to the same aim: we design and implement a modular process to allow trains to self-organize. This process consists in having trains identifying their neighbors, formulating traffic management hypotheses, checking their compatibility and selecting the best ones through a consensus mechanism. Finally, these hypotheses are merged into a directly applicable traffic plan. In a thorough experimental analysis on a portion of the Italian network, we compare the results of self-organization with those of a state-of-the-art centralized approach. In particular, we make this comparison mimicking a realistic deployment thanks to a closed-loop framework including a microscopic railway simulator. The results indicate that self-organization achieves better results than the centralized algorithm, specifically thanks to the definition and exploitation of the instance decomposition allowed by the proposed approach.

Self-Organizing Railway Traffic Management

TL;DR

This work addresses the challenge of railroad traffic perturbations by proposing a fully decentralized self-organizing railway TMS (SO-TMS) that replaces centralized optimization with local cooperation among trains. The authors formalize a modular pipeline—neighborhood identification, hypothesis generation via a RECIFE-MILP variant, hypothesis compatibility checks, adaptive consensus-based hypothesis selection, and a merge/repair stage—to produce feasible real-time traffic plans. Through a closed-loop, microscopic OpenTrack simulation of a busy Italian corridor, the SO-TMS consistently outperforms a state-of-the-art centralized baseline, leveraging instance decomposition for tractability and responsiveness. The findings support the practical viability of decentralized, explainable traffic management that preserves feasibility while improving delay performance in complex, competitive railway networks.

Abstract

Improving traffic management in case of perturbation is one of the main challenges in today's railway research. The great majority of the existing literature proposes approaches to make centralized decisions to minimize delay propagation. In this paper, we propose a new paradigm to the same aim: we design and implement a modular process to allow trains to self-organize. This process consists in having trains identifying their neighbors, formulating traffic management hypotheses, checking their compatibility and selecting the best ones through a consensus mechanism. Finally, these hypotheses are merged into a directly applicable traffic plan. In a thorough experimental analysis on a portion of the Italian network, we compare the results of self-organization with those of a state-of-the-art centralized approach. In particular, we make this comparison mimicking a realistic deployment thanks to a closed-loop framework including a microscopic railway simulator. The results indicate that self-organization achieves better results than the centralized algorithm, specifically thanks to the definition and exploitation of the instance decomposition allowed by the proposed approach.
Paper Structure (14 sections, 7 figures, 1 table)

This paper contains 14 sections, 7 figures, 1 table.

Table of Contents

  1. Introduction
  2. Self-organization and traffic management
  3. Real-time Railway Traffic Management
  4. Self-organization process
  5. Self-organization module designs
  6. Neighborhood selection
  7. Hypothesis generation
  8. Hypothesis compatibility
  9. Hypothesis selection
  10. Merge
  11. Experimental setup
  12. Experimental results
  13. Conclusions and future work
  14. Acknowledgments

Figures (7)

  • Figure 1: Conceptual representation of the self-organized traffic management process DamNalTibTriPel20.
  • Figure 2: Top: Four trains traveling in a control area. Each train's neighborhood is indicated using the corresponding color. Bottom: sequence diagram of the self-organization process with interactions and control processes for each train DamNalTibTriPel20.
  • Figure 3: Schematic representation of the Segrate-Ospitaletto control area
  • Figure 4: Space-time diagram representing the timetable considered.
  • Figure 5: Percentage improvement of total weighted and unweighted delay of SO w.r.t CEN (left) and FCFS (right).
  • ...and 2 more figures