A multiobjective single bus corridor scheduling using machine learning-based predictive models

Many real-life optimisation problems, including those in production and logistics, have uncertainties that pose considerable challenges for practitioners. In spite of considerable efforts, the current methods are still not satisfactory. This is primarily caused by a lack of effective methods to deal...

Full description

Bibliographic Details
Main Authors: Chen, Bing, Bai, Ruibin, Li, Jiawei, Liu, Yueni, Xue, Ning, Ren, Jianfeng
Format: Article
Language:English
Published: 2020
Subjects:
Online Access:https://eprints.nottingham.ac.uk/61341/
_version_ 1848799862781378560
author Chen, Bing
Bai, Ruibin
Li, Jiawei
Liu, Yueni
Xue, Ning
Ren, Jianfeng
author_facet Chen, Bing
Bai, Ruibin
Li, Jiawei
Liu, Yueni
Xue, Ning
Ren, Jianfeng
author_sort Chen, Bing
building Nottingham Research Data Repository
collection Online Access
description Many real-life optimisation problems, including those in production and logistics, have uncertainties that pose considerable challenges for practitioners. In spite of considerable efforts, the current methods are still not satisfactory. This is primarily caused by a lack of effective methods to deal with various uncertainties. Existing literature comes from two isolated research communities, namely the operations research community and the machine learning community. In the operations research community, uncertainties are often modelled and solved through techniques like stochastic programming or robust optimisation, which are often criticised for their over conservativeness. In the machine learning community, the problem is formulated as a dynamic control problem and solved through techniques like supervised learning and/or reinforcement learning, which could suffer from being myopic and unstable. In this paper, we aim to fill this research gap and develop a novel framework that takes advantages of both short-term accuracy from mathematical models and high-quality future forecasts from machine learning modules. We demonstrate the practicality and feasibility of our approach for a real-life bus scheduling problem and two controlled bus scheduling instances that are generated artificially. To our knowledge, the proposed framework represents the first multi-objective bus-headway-optimisation method for non-timetabled bus schedule with major practical constraints being considered. The advantages of our proposed methods are also discussed, along with factors that need to be carefully considered for practical applications. © 2020, © 2020 Informa UK Limited, trading as Taylor & Francis Group.
first_indexed 2025-11-14T20:42:25Z
format Article
id nottingham-61341
institution University of Nottingham Malaysia Campus
institution_category Local University
language English
last_indexed 2025-11-14T20:42:25Z
publishDate 2020
recordtype eprints
repository_type Digital Repository
spelling nottingham-613412020-08-19T05:51:56Z https://eprints.nottingham.ac.uk/61341/ A multiobjective single bus corridor scheduling using machine learning-based predictive models Chen, Bing Bai, Ruibin Li, Jiawei Liu, Yueni Xue, Ning Ren, Jianfeng Many real-life optimisation problems, including those in production and logistics, have uncertainties that pose considerable challenges for practitioners. In spite of considerable efforts, the current methods are still not satisfactory. This is primarily caused by a lack of effective methods to deal with various uncertainties. Existing literature comes from two isolated research communities, namely the operations research community and the machine learning community. In the operations research community, uncertainties are often modelled and solved through techniques like stochastic programming or robust optimisation, which are often criticised for their over conservativeness. In the machine learning community, the problem is formulated as a dynamic control problem and solved through techniques like supervised learning and/or reinforcement learning, which could suffer from being myopic and unstable. In this paper, we aim to fill this research gap and develop a novel framework that takes advantages of both short-term accuracy from mathematical models and high-quality future forecasts from machine learning modules. We demonstrate the practicality and feasibility of our approach for a real-life bus scheduling problem and two controlled bus scheduling instances that are generated artificially. To our knowledge, the proposed framework represents the first multi-objective bus-headway-optimisation method for non-timetabled bus schedule with major practical constraints being considered. The advantages of our proposed methods are also discussed, along with factors that need to be carefully considered for practical applications. © 2020, © 2020 Informa UK Limited, trading as Taylor & Francis Group. 2020-05-28 Article PeerReviewed application/pdf en cc_by https://eprints.nottingham.ac.uk/61341/1/ilovepdf_merged%20%283%29.pdf Chen, Bing, Bai, Ruibin, Li, Jiawei, Liu, Yueni, Xue, Ning and Ren, Jianfeng (2020) A multiobjective single bus corridor scheduling using machine learning-based predictive models. International Journal of Production Research . pp. 1-16. ISSN 0020-7543 Bus Scheduling; Multi-Objective Optimisation; Combinatorial Optimisation;Machine Learning http://dx.doi.org/10.1080/00207543.2020.1766716 doi:10.1080/00207543.2020.1766716 doi:10.1080/00207543.2020.1766716
spellingShingle Bus Scheduling; Multi-Objective Optimisation; Combinatorial Optimisation;Machine Learning
Chen, Bing
Bai, Ruibin
Li, Jiawei
Liu, Yueni
Xue, Ning
Ren, Jianfeng
A multiobjective single bus corridor scheduling using machine learning-based predictive models
title A multiobjective single bus corridor scheduling using machine learning-based predictive models
title_full A multiobjective single bus corridor scheduling using machine learning-based predictive models
title_fullStr A multiobjective single bus corridor scheduling using machine learning-based predictive models
title_full_unstemmed A multiobjective single bus corridor scheduling using machine learning-based predictive models
title_short A multiobjective single bus corridor scheduling using machine learning-based predictive models
title_sort multiobjective single bus corridor scheduling using machine learning-based predictive models
topic Bus Scheduling; Multi-Objective Optimisation; Combinatorial Optimisation;Machine Learning
url https://eprints.nottingham.ac.uk/61341/
https://eprints.nottingham.ac.uk/61341/
https://eprints.nottingham.ac.uk/61341/