On enabling collaborative non-intrusive load monitoring for sustainable smart cities.

Improving energy efficiency is a crucial aspect of building a sustainable smart city and, more broadly, relevant for improving environmental, economic, and social well-being. Non-intrusive load monitoring (NILM) is a computing technique that estimates energy consumption in real-time and helps raise energy awareness among users to facilitate energy management. Most NILM solutions are still a single machine approach and do not fit well in smart cities. This work proposes a model-agnostic hybrid federated learning framework to collaboratively train NILM models for city-wide energy-saving applications. The framework supports both centralised and decentralised training modes to provide a cluster-based, customisable and optimal learning solution for users. The proposed framework is evaluated on a real-world energy disaggregation dataset. The results show that all NILM models trained in our proposed framework outperform the locally trained ones in accuracy. The results also suggest that the NILM models trained in our framework are resistant to privacy leakage.