.png){kind=icon}
.png){kind=icon}
Return
A multiobjective single bus corridor scheduling using machine learning-based predictive models
.png){kind=icon}
OA
AI
DOI：10.1080/00207543.2020.1766716.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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.
Keywords:
bus scheduling
multi-objective optimisation
combinatorial optimisation
machine learning
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
7.3
Papers:
1.1W
Citations:
3.7W
Organization
View more organizations