Partition problem for optimizing the deployment of incident response

Incidents occurring on a freeway system can cause significant impact over traffic flows, such as long-duration and large-scale congestion and potential danger to the driving environment. Hence, prompt incident response is critical for freeway management. The objective of this study is to investigate the deployment of freeway incident response teams through the optimal partitioning of freeway segments, so as to attain the efficiency of dispatch and routing. Based on the analysis of historical incident data and response records, this study first visualizes the spatiotemporal pattern of incident occurrence over a GIS map. The factors that are significantly associated with the frequency of incident occurrence are further identified, and the possible causality is discussed thereupon. Considering the association and the structure of the freeway network, this study develops a partition problem, where each incident response team is located near a certain ramp and generally responsible for a set of freeway segments. Upon the expected incident occurrence during different planning horizons or time-of-day periods, the partition problem determines the freeway segments belonging to each incident response team in a time-dependent context, seeking to minimize total mileages traveled while balancing the workloads over the response teams. The visualization of the partitioning result can be used by a control center, as the reference for online dispatching and routing incident response teams. Combined with real-time freeway monitoring within a GIS-based deployment system, the time-dependent partitioning enable freeway administrators to more flexibly and efficiently address various incident scenarios, such as trip chains for multiple incidents of different emergency levels, based on better understanding of freeway incident characteristics. ? 2017 American Society of Civil Engineers.