English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Parking, matching, scheduling, and routing are common problems in trainmaintenance. In particular, train units are commonly maintained and cleaned atdedicated shunting yards. The planning problem that results from suchsituations is referred to as the Train Unit Shunting Problem (TUSP). Thisproblem involves matching arriving train units to service tasks and determiningthe schedule for departing trains. The TUSP is an important problem as it isused to determine the capacity of shunting yards and arises as a sub-problem ofmore general scheduling and planning problems. In this paper, we consider thecase of the Dutch Railways (NS) TUSP. As the TUSP is complex, NS currently usesa local search (LS) heuristic to determine if an instance of the TUSP has afeasible solution. Given the number of shunting yards and the size of theplanning problems, improving the evaluation speed of the LS brings significantcomputational gain. In this work, we use a machine learning approach thatcomplements the LS and accelerates the search process. We use a Deep GraphConvolutional Neural Network (DGCNN) model to predict the feasibility ofsolutions obtained during the run of the LS heuristic. We use this model todecide whether to continue or abort the search process. In this way, thecomputation time is used more efficiently as it is spent on instances that aremore likely to be feasible. Using simulations based on real-life instances ofthe TUSP, we show how our approach improves upon the previous method onprediction accuracy and leads to computational gains for the decision-makingprocess.

Data-driven Policy on Feasibility Determination for the Train Shunting Problem