Proposed Dynamic Waste Collection Route Planning Using Ant Colony Optimization (ACO): A Case Study of Lagos Metropolis

Abstract

Nigeria’s megacities are contending with the problem of waste management due to the increasing volume of waste. Traditional waste collection methods are often ineffective and time-consuming. This research attempts to answer this issue by proposing a dynamic route optimization model for a smart waste collection system in Lagos. This approach integrates static geographical data and real-time environmental considerations such as traffic and bin fill levels. Two datasets were generated to model the urban environment and facilitate adaptive re-optimization, lagos_aco_waste_dataset.csv (static waste collection data) and lagos_aco_dynamic_updates.csv (real-time traffic and bin-level updates). The system architecture integrates a Python-based ACO engine, Folium visualization, and a Flask web dashboard for real-time monitoring. The intelligent system enables efficient, data-driven route optimization and adaptive waste management in complex urban environments. This study aims to explore the viability of this dynamic approach in minimizing total travel distance, reducing fuel consumption, optimizing resource allocation, and increasing the efficiency and responsiveness of waste collection services within Lagos's complex urban environment. The findings will be useful in practice for application and benefits of intelligent route optimization for waste management sustainability in a major city.