Application of Multi-Objective Optimization Algorithms in Urban Infrastructure

Urban infrastructure faces challenges like resource constraints and growing demands amid urbanization. This study adopts a multi-objective optimization algorithm: non-dominated sorting prioritizes genetic operations on highlevel individuals to approach the Pareto frontier, while congestion distance maintains population diversity for uniformly distributed optimal solutions. A model is built with clarified goal weights and constraints. Results show the algorithm enhances planning efficiency and benefits, improving service quality, cutting costs, and reducing environmental impacts. Experiments reveal conflicts: when construction costs drop from 250M to 180M yuan, traffic congestion relief falls from 30 % to 20 %, and pollution reduction from 500 to 300 tons, highlighting trade-offs in infrastructure planning.