Robust nonlinear decision mapping approach for online bus speed control under uncertainty

The authors use nonlinear decision mapping, optimized offline, in a novel method to address online simulation-based decision making under uncertainties. Online bus speed control is a flexible and effective solution to bus bunching and can improve service level. The authors present a robust nonlinear decision mapping (RNDM) using real-time bus system states to control bus speeds and manage uncertainties in passenger demand and traffic speeds. The design process involves learning the input-output mapping relation of a nonlinear programming simulation-based optimization (NLPSO) using regression tree with AdaBoost. Crucial parameters of the regression tree fitted with AdaBoost are optimized offline using a robust simulation-based optimization (DRSO) solved by a simulation-based optimization (SO) algorithm. The resulting RNDM method effectively handles two types of uncertainties, expressed by two ambiguity sets of probability distributions, ensuring good performance in bus operations even under the worst levels of uncertainty. Numerical experiments show that the RNDM, NLPSO, and integer programming SO methods mitigate bus bunching and improve service. The RNDM method also outperforms NLPSO and IPSO in performance under uncertainties.

• Record URL:
  • http://dx.doi.org/10.1111/mice.13064
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/issn/10939687
• Authors:
  • Zheng, Liang
  • Liu, Pengjie
• Publication Date: 2024-1-15

Language

• English

Media Info

• Media Type: Web
• Features: Figures; Maps; References; Tables;
• Pagination: pp 203-221
• Serial:
  • Computer-Aided Civil and Infrastructure Engineering
  • Volume: 39
  • Issue Number: 2
  • Publisher: Blackwell Publishing
  • ISSN: 1093-9687
  • Serial URL: http://onlinelibrary.wiley.com/journal/10.1111/(ISSN)1467-8667

Subject/Index Terms

• TRT Terms: Algorithms; Automatic speed control; Buses; Computer online services; Decision making; Uncertainty
• Subject Areas: Data and Information Technology; Operations and Traffic Management; Public Transportation; Vehicles and Equipment;

Filing Info

• Accession Number: 01910905
• Record Type: Publication
• Files: TRIS
• Created Date: Mar 6 2024 4:11PM