文章背景与核心概要
网络级道路养护规划需要在大规模路网容量缩减的情况下，反复评估平衡交通流。传统的交通流分配模型虽然成熟，但其重复求解过程计算成本极高，难以直接嵌入到复杂的养护调度优化框架中。
本文针对这一计算瓶颈，提出了一种数据驱动的代理模型，直接从起点-终点（OD）需求近似平衡路段流量，并以基于优化的平衡解作为真实标签。通过美国新泽西州纽瓦克地区的真实交通数据案例研究，验证了该方法的有效性，为未来的养护调度框架提供了一种可扩展的基础组件。
Optimal Scheduling of Road Maintenance Jobs Considering Impact on Traffic Flows
arXiv: 2608.14491
Date: August 14, 2026
Subject: Systems and Control (eess.SY); Artificial Intelligence (cs.AI)
arXiv: 2608.14491
Date: August 14, 2026
Subject: Systems and Control (eess.SY); Artificial Intelligence (cs.AI)
Summary
This paper addresses the computational challenges associated with network-level road maintenance planning. Traditional methods require repeated evaluations of equilibrium traffic flows under varying road capacities, which is often too slow for practical scheduling frameworks. The authors propose a data-driven surrogate model that approximates equilibrium arc flows directly from origin-destination demand. By using optimization-based equilibrium solutions as ground truth, the model provides a scalable solution for maintenance scheduling. The effectiveness of this approach is validated through a real-world case study in the Newark, New Jersey area.
Summary
This paper addresses the computational challenges associated with network-level road maintenance planning. Traditional methods require repeated evaluations of equilibrium traffic flows under varying road capacities, which is often too slow for practical scheduling frameworks. The authors propose a data-driven surrogate model that approximates equilibrium arc flows directly from origin-destination demand. By using optimization-based equilibrium solutions as ground truth, the model provides a scalable solution for maintenance scheduling. The effectiveness of this approach is validated through a real-world case study in the Newark, New Jersey area.
Authors
- Charitha Nandepu
- Lohitha Kalepu
- Gabriele Ciavarella
- SangWoo Park
Authors
- Charitha Nandepu
- Lohitha Kalepu
- Gabriele Ciavarella
- SangWoo Park
Abstract
Network-level maintenance planning requires repeated evaluations of equilibrium traffic flows under road capacity reductions. While equilibrium traffic assignment models are well established, their repeated solution quickly becomes computationally prohibitive and challenging to embed within maintenance scheduling problems. This paper investigates data-driven surrogate models that approximate equilibrium arc flows directly from origin-destination demand, using optimization-based equilibrium solutions as ground truth. A real-world case study based on traffic data from the Newark, New Jersey area demonstrates the effectiveness of the proposed approach as a scalable building block for future maintenance scheduling frameworks.
Abstract
Network-level maintenance planning requires repeated evaluations of equilibrium traffic flows under road capacity reductions. While equilibrium traffic assignment models are well established, their repeated solution quickly becomes computationally prohibitive and challenging to embed within maintenance scheduling problems. This paper investigates data-driven surrogate models that approximate equilibrium arc flows directly from origin-destination demand, using optimization-based equilibrium solutions as ground truth. A real-world case study based on traffic data from the Newark, New Jersey area demonstrates the effectiveness of the proposed approach as a scalable building block for future maintenance scheduling frameworks.
Additional Information
- Comments: Case Study paper presented in IISE Annual Conference and Expo 2026.
- DOI: https://doi.org/10.48550/arXiv.2608.14491
- License: Creative Commons Attribution 4.0 International
Additional Information
- Comments: Case Study paper presented in IISE Annual Conference and Expo 2026.
- DOI: https://doi.org/10.48550/arXiv.2608.14491
- License: Creative Commons Attribution 4.0 International
Access Paper
Access Paper