Optimizing City’s Service Routes for Road Repairs

Abstract

Reoccurring freeze and thaw cycles and damp conditions from rain, ice, and snow damage roadways and result in potholes throughout the city area. Auto damages caused by the potholes can add up to thousands of dollars per vehicle. Besides, pothole resolution is one of the most expensive street maintenance strategies. Most of the cities have established social data networks (i.e., Open Data KC 311 in Kansas City) for residents to report potholes to mitigate the problem. Although rudimentary patching policies are defined by the road condition’s volume and significance in many cities, it does not provide the optimized resolution routes. In this paper, we propose a practical framework for optimizing the resolution route schedule using open data, including the pothole locations, traffic situations, weather conditions, type of patch or other repair needed, crew availability, etc. We have analyzed the past 13 years of pothole data from the Open Data KC 311 in Kansas City. According to our analysis, we have recognized spatiotemporal pothole characteristics in the density and designed a cluster-based heuristic algorithm named Traveling Pothole Crew (TPC) by enhancing an NP-hard Traveling Salesperson Problem (TSP) algorithm. TPC classifies potholes into layers of clusters. TPC traverses the shortest possible pothole route within a cluster. Furthermore, it identifies the starting and ending potholes in each cluster group to optimize the distance among clusters. This proposed solution has shown effective optimization in terms of traveling distance and computation time. Our analysis indicates that the TPC algorithm reduces the traversing distance and is faster in computation time than typical TSP algorithms for daily resolution scheduling.