What is it about?

Short-term roadway work zone scheduling, with a duration of a few hours, is a challenging problem. Scheduling these projects during the peak hour can save extra costs associated with labor and equipment. However, this can raise serious issues regarding the exacerbation of congestion on the streets. Therefore, a framework has been developed to study this trade-off. Since solving this problem using the conventional solution algorithms is computationally expensive, machine learning is integrated to provide a novel algorithm so that this problem can be addressed in a timely manner. In the end, more information is given about the impacts of scheduling and how crews are assigned to different projects.

Featured Image

Why is it important?

The city agency implements several infrastructure maintenance road projects on a routine basis. The majority of these projects last only a few hours. Although their impacts on travellers might seem negligible at first glance, statistics have shown that they continue to pose a major cause of nonrecurring congestion in urban areas. Efficient scheduling of these short-term projects can benefit both the city agency and road users. In this research, a novel machine learning algorithm, which is more efficient compared to conventional methods, has been proposed to study this trade-off.

Read the Original

This page is a summary of: A methodology for scheduling within‐day roadway work zones using deep neural networks and active learning, Computer-Aided Civil and Infrastructure Engineering, September 2022, Wiley,
DOI: 10.1111/mice.12921.
You can read the full text:



The following have contributed to this page