Data-Driven Optimization of Garbage Collection Point Locations for Efficient Urban Solid Waste Management

Abstract

Rapid urbanization and growing population density have made municipal solid waste management increasingly challenging, particularly in designing efficient and cost-effective garbage collection systems. Among the key planning decisions, the placement of Garbage Collection Points (GCPs) plays a vital role, as it influences the walking distance for residents, vehicle travel distance, fuel consumption, operational expenses, and the overall cleanliness of urban areas. However, while considerable attention has been given to optimizing waste collection routes, relatively little research has focused on determining the optimal locations of GCPs in real urban environments. To address this issue, this study formulates the GCP placement problem as a Minimum Vertex Cover (MVC) problem on an urban road network. This formulation identifies the minimum number of collection points required to provide complete coverage of all demand locations while maintaining service accessibility. To solve the problem effectively, a Hybrid Genetic Algorithm (HGA) is proposed, combining the global search capability of genetic algorithms with problem-specific local improvement techniques to enhance solution quality and convergence. The effectiveness of the proposed approach is evaluated through computational experiments on benchmark datasets and further demonstrated using a real-world case study from the Yadgir district. The results indicate that the proposed method consistently achieves complete coverage using fewer collection points, reduces vehicle travel requirements, and produces higher-quality solutions than conventional greedy and heuristic methods. These findings demonstrate that the proposed framework can serve as a practical decision-support tool for municipal authorities by enabling scalable, data-driven, and economically efficient planning of urban waste collection infrastructure. Since the approach relies on readily available geographic information, it can be adapted for waste management planning in medium-sized cities across different regions.