Development of a genetic algorithm (GA)–based optimization tool for determining the optimal multiyear pavement repair schedule is described. The problem of finding the best multiyear work plan can be modeled as a combinatorial optimization problem, the objective of which is to achieve the highest possible average network condition for a given budget and operating constraints. Two GAs and a dynamic programming (DP) approach were implemented to determine multiyear repair schedules. The DP method resulted in optimal solutions, but it suffers from rigidity and inability to handle large-scale problems. The GA techniques obtained solutions that were near optimal and maintained flexibility and scalability. The GAs implemented were of two types: simple and preconstrained. The simple GA uses constraints when searching for solutions. The preconstrained GA uses constraints that limit which repair can be selected before searching for solutions to attain better efficiency.
