Network-Level Urban Pavement Optimization Using Priority-Based Genetic Algorithm Methodology

Pavement management systems (PMS) are essential for formulating a cost-effective capital improvement plan (CIP) that adheres to budget constraints. Optimization techniques are vital in enhancing the efficiency of these plans. Among the various methods available, genetic algorithms (GA) are particularly effective at identifying optimal solutions in complex scenarios. This study introduces a GA-based priority optimization model designed to select the most beneficial road improvement projects while staying within budgetary limits. The model was applied to the extensive road network of Fort Wayne, Indiana, considering critical factors such as budget allocation, roadway classification, PASERs, treatment options, and associated costs. The results demonstrate the model’s effectiveness in prioritizing projects, ensuring that available funds are utilized to achieve maximum impact on roadway conditions. By leveraging GA, this approach not only enhances decision-making processes but also provides a robust framework for future pavement management efforts. Overall, the integration of genetic algorithms into PMS can lead to more strategic and economically sound infrastructure improvements.