Predictive analysis-based sustainable waste management in smart cities using IoT edge computing and blockchain technology

Effective waste management has become the key challenge in developing smart cities with the increase in population. Traditional waste management systems are often inefficient, which leads to unnecessary trips, high operational costs, difficulties in tracking waste, and the inefficient use of resources. The proposed work aims to integrate real-time predictive analysis-based waste collection and disposal processes using federated learning with blockchain, overcoming the challenges specified. Initially, IoT sensors were installed in waste bins across different sites to monitor the depth of waste accumulated. Local edge gateways preprocess the collected data, which the random forest model analyzes to determine the bin status. The aggregated data is sent to a global model that predicts overall waste generation trends. Furthermore, the processed data is securely recorded on a blockchain network combined with smart contracts, accessed through a decentralized application called D-App, which gives real-time updates for scheduling waste collection, performs efficient communication with users and stakeholders to access real-time data to monitor bin status, and track waste collection trucks. As a result, the model predicts bin status with 99.25 % accuracy using an RF algorithm and blockchain helped achieve a user trust level by 95 %. Thus, the proposed work reduces operational expenses, optimizes waste collection routes, makes better decisions, and provides a scalable solution for sustainable waste management.