Open AccessDeep Learning to Handle Congestion in Vehicle Routing Problem: A Review
Author(s) -
Darmawan Satyananda,
Ahmed K.A. Abdullah
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/2129/1/012023
Subject(s) - benchmark (surveying) , traffic congestion , computer science , routing (electronic design automation) , vehicle routing problem , cover (algebra) , deep learning , artificial intelligence , computer network , transport engineering , engineering , mechanical engineering , geodesy , geography
This paper reviews the implementation design of Deep Learning in Vehicle Routing Problem. Congestion and traffic condition are usually avoided in Vehicle Routing Problem due to its modeling complexity, and even the benchmark datasets only cover essential conditions. In the real situation, the traffic condition is varied, and congestion is the worst part. To model the real life, the delivery route must consider these situations. The vehicle needs information on traffic prediction in future time to avoid congestion. The prediction needs historical traffic data, which is very large. Deep Learning can handle the enormous size and extract data features to infer the prediction.