Forecasting and Mitigating Disruptions in Public Bus Transit Services

Chaeeun Han, Jose Paolo Talusan, Dan Freudberg, Ayan Mukhopadhyay, Abhishek Dubey, Aron Laszka

Proceedings of the 23rd Conference on Autonomous Agents and MultiAgent Systems, AAMAS 2024, Auckland, New Zealand 2024 AAMAS '24

PDF

Why This Matters

Public transit agencies struggle with unexpected service disruptions caused by vehicle breakdowns, accidents, and other incidents. Traditional approaches rely on reactive responses that degrade passenger experience and increase operational costs. This work is innovative because it combines predictive modeling with proactive resource positioning, enabling agencies to anticipate problems and position substitutes in advance. The data-driven approach learns from historical disruption patterns to make increasingly accurate predictions.

What We Did

This paper presents a comprehensive software system for managing disruptions in public transit through combined forecasting and mitigation strategies. The approach includes statistical and machine learning models to predict the likelihood of service disruptions, algorithms for selecting optimal locations to station substitute buses, and a simulation environment for validating solutions. The system integrates data-driven disruption forecasting with optimization for positioning reserve resources, enabling transit agencies to proactively respond to anticipated problems rather than reacting after failures occur.

Key Results

The forecasting models successfully predict disruptions with reasonable accuracy on real transit data from a mid-sized US city. The optimization algorithms identify substitute bus positioning strategies that minimize the impact of predicted disruptions on passenger experience and operational efficiency. Integration of forecasting with optimization creates a complete disruption management system that transit agencies can deploy, showing how modern machine learning can be applied to practical transit operations challenges.

Full Abstract

Cite This Paper

@inproceedings{talusan2024AAMAS,
  author = {Han, Chaeeun and Talusan, Jose Paolo and Freudberg, Dan and Mukhopadhyay, Ayan and Dubey, Abhishek and Laszka, Aron},
  booktitle = {Proceedings of the 23rd Conference on Autonomous Agents and MultiAgent Systems, {AAMAS} 2024, Auckland, New Zealand},
  title = {Forecasting and Mitigating Disruptions in Public Bus Transit Services},
  year = {2024},
  address = {Richland, SC},
  publisher = {International Foundation for Autonomous Agents and Multiagent Systems},
  series = {AAMAS '24},
  acceptance = {20},
  abstract = {Public transportation systems often suffer from unexpected fluctuations in demand and disruptions, such as mechanical failures and medical emergencies. These fluctuations and disruptions lead to delays and overcrowding, which are detrimental to the passengers' experience and to the overall performance of the transit service. To proactively mitigate such events, many transit agencies station substitute (reserve) vehicles throughout their service areas, which they can dispatch to augment or replace vehicles on routes that suffer overcrowding or disruption. However, determining the optimal locations where substitute vehicles should be stationed is a challenging problem due to the inherent randomness of disruptions and due to the combinatorial nature of selecting locations across a city. In collaboration with the transit agency of a mid-size U.S. city, we address this problem by introducing data-driven statistical and machine-learning models for forecasting disruptions and an effective randomized local-search algorithm for selecting locations where substitute vehicles are to be stationed. Our research demonstrates promising results in proactive disruption management, offering a practical and easily implementable solution for transit agencies to enhance the reliability of their services. Our results resonate beyond mere operational efficiency---by advancing proactive strategies, our approach fosters more resilient and accessible public transportation, contributing to equitable urban mobility and ultimately benefiting the communities that rely on public transportation the most.},
  contribution = {colab},
  keywords = {transit disruptions, forecasting, predictive maintenance, proactive management, resource allocation, service reliability, data-driven optimization, emergency response},
  location = {Auckland, New Zealand},
  numpages = {9}
}
Quick Info
Year 2024
Series AAMAS '24
Keywords
transit disruptions forecasting predictive maintenance proactive management resource allocation service reliability data-driven optimization emergency response
Research Areas
transit emergency ML for CPS middleware
Search Tags

Forecasting, Mitigating, Disruptions, Public, Transit, Services, transit disruptions, forecasting, predictive maintenance, proactive management, resource allocation, service reliability, data-driven optimization, emergency response, transit, emergency, ML for CPS, middleware, 2024, Han, Talusan, Freudberg, Mukhopadhyay, Dubey, Laszka, AAMAS24