End-to-end learning of user equilibrium with implicit neural networks
End-to-end learning of user equilibrium with implicit neural networks
复制标题
使用隐式神经网络进行用户均衡的端到端学习
DOI：
10.1016/j.trc.2023.104085
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Grimm, Donald K.
中科院分区：
文献类型：
--
作者：
Liu, Zhichen;Yin, Yafeng;Bai, Fan;Grimm, Donald K.
本文试图通过一个“端到端”框架来改变交通网络平衡建模范式，该框架直接从多日交通流量观测中学习出行选择偏好和平衡状态。提出的框架的核心是使用深度神经网络来表示旅行者的路线选择偏好，然后将神经网络封装在规定用户均衡流量分布的变分不等式中。所提出的神经网络结构保证了平衡的存在，并适应未来路网拓扑结构的变化。然后将变分不等式作为隐式层嵌入到学习框架中，该框架将上下文特征（例如，道路网络和旅行者特征）作为输入并输出用户均衡流量分布。通过比较计算的平衡流和观测到的平衡流，可以训练神经网络。提出的端到端框架使用苏福尔斯网络的综合数据进行了演示和验证。
This paper intends to transform the transportation network equilibrium modeling paradigm via an “end-to-end” framework that directly learns travel choice preferences and the equilibrium state from multi-day link flow observations. The centerpiece of the proposed framework is to use deep neural networks to represent travelers’ route choice preferences and then encapsulate the neural networks in a variational inequality that prescribes the user equilibrium flow distribution. The proposed neural network architecture ensures the existence of equilibrium and accommodates future changes in road network topology. The variational inequality is then embedded as an implicit layer in a learning framework, which takes the context features (e.g., road network and traveler characteristics) as input and outputs the user equilibrium flow distribution. By comparing computed equilibrium flows with observed flows, the neural networks can be trained. The proposed end-to-end framework is demonstrated and validated using synthesized data for the Sioux Falls network.