Equilibrium-Traffic-Networks

This repository contains three graph datasets generated for the study "A hybrid deep-learning-metaheuristic framework for bi-level network design problems" by Bahman Madadi and Gonçalo H. de Almeida Correia, published in Expert Systems with Applications. The datasets are generated and used to train and evaluate models for solving the User Equilibrium (UE) problem on three transportation networks (Sioux-Falls, Eastern-Massachusetts, and Anaheim) from the well-known "transport networks for research" repository.

It is recommended to use the pytorch geometric (pyg) datasets (added in the latest update) to avoid potential compatibility issues with different versions of dgl. The underlying data is the same and the existing code base works with new datasets. You only need to make sure the dataset names mathc the names in the config files.

Detailed information can be found in the "Metadata.md" file.

References

• A hybrid deep-learning-metaheuristic framework for bi-level network design problems
• GitHub Repository: HDLMF_GIN-GA