Machine Learning Predictions for Traffic Equilibria in Road Renovation Scheduling

TL;DR

This paper explores machine learning models, especially XGBoost, to predict traffic congestion from road renovations, aiming to reduce reliance on computationally intensive simulations in maintenance planning.

Contribution

It introduces a surrogate modeling approach using machine learning to efficiently predict traffic impacts of road maintenance, outperforming traditional heuristics and other models.

Findings

XGBoost achieves a MAPE of 11%, outperforming other models.

Most regression models do not surpass the Costliest Subset Heuristic, except XGBoost.

The approach can significantly reduce computational costs in large-scale traffic planning.

Abstract

Accurately estimating the impact of road maintenance schedules on traffic conditions is important because maintenance operations can substantially worsen congestion if not carefully planned. Reliable estimates allow planners to avoid excessive delays during periods of roadwork. Since the exact increase in congestion is difficult to predict analytically, traffic simulations are commonly used to assess the redistribution of the flow of traffic. However, when applied to long-term maintenance planning involving many overlapping projects and scheduling alternatives, these simulations must be run thousands of times, resulting in a significant computational burden. This paper investigates the use of machine learning-based surrogate models to predict network-wide congestion caused by simultaneous road renovations. We frame the problem as a supervised learning task, using one-hot encodings, engineered traffic features, and heuristic approximations. A range of linear, ensemble-based, probabilistic, and neural regression models is evaluated under an online learning framework in which data progressively becomes available. The experimental results show that the Costliest Subset Heuristic provides a reasonable approximation when limited training data is available, and that most regression models fail to outperform it, with the exception of XGBoost, which achieves substantially better accuracy. In overall performance, XGBoost significantly outperforms alternatives in a range of metrics, most strikingly Mean Absolute Percentage Error (MAPE) and Pinball loss, where it achieves a MAPE of 11% and outperforms the next-best model by 20% and 38% respectively. This modeling approach has the potential to reduce the computational burden of large-scale traffic assignment problems in maintenance planning.