| Summary: | This study critically reviews the scientific literature regarding machine-learning approaches for optimizing smart bin collection in urban environments. Usually, the problem is modeled within a dynamic graph framework, where each smart bin’s changing waste level is represented as a node. Algorithms incorporating Reinforcement Learning (RL), time-series forecasting, and Genetic Algorithms (GA) alongside Graph Neural Networks (GNNs) are analyzed to enhance collection efficiency. While individual methodologies present limitations in computational demand and adaptability, their synergistic application offers a holistic solution. From a theoretical point of view, we expect that the GNN-RL model dynamically adapts to real-time data, the GNN-time series predicts future bin statuses, and the GNN-GA hybrid optimizes network configurations for accurate predictions, collectively enhancing waste management efficiency in smart cities.
|
|---|