<b>Equilibrium-Traffic-Networks</b>

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.ReferencesA hybrid deep-learning-metaheuristic framework for bi-level network design problemsGitHub Repository: HDLMF_GIN-GA<br>

本仓库包含为Bahman Madadi与Gonçalo H. de Almeida Correia发表于《专家系统及其应用（Expert Systems with Applications）》的研究《混合深度学习-元启发式框架求解双层网络设计问题（A hybrid deep-learning-metaheuristic framework for bi-level network design problems）》所生成的三类图数据集。
该数据集用于训练与评估相关模型，以求解知名“科研用交通网络（transport networks for research）”仓库中的三类交通网络（苏福尔斯Sioux-Falls、马萨诸塞东部Eastern-Massachusetts及阿纳海姆Anaheim）的用户均衡（User Equilibrium, UE）问题。
推荐使用本次更新新增的PyTorch Geometric（pyg）数据集，以规避与不同版本DGL（Deep Graph Library）可能出现的兼容性问题。两类数据集底层数据完全一致，现有代码库可兼容新增数据集，仅需确保数据集名称与配置文件中的名称匹配即可。
详细信息可参阅"Metadata.md"文件。
参考文献：《混合深度学习-元启发式框架求解双层网络设计问题（A hybrid deep-learning-metaheuristic framework for bi-level network design problems）》，GitHub仓库：HDLMF_GIN-GA