Demonstrates autonomous energy disaggregation in homes, highlighting federated learning for managing smart grid demands.
Effective demand‐side management (DSM) can alleviate ever‐increasing electricity demand required by, for instance, residential customers in downstream sectors of a smart grid. Different from traditional intrusive load monitoring conducted and used in a home energy management system (HEMS), energy disaggregation (i.e., nonintrusive load monitoring) can monitor relevant major electrical appliances in a nonintrusive and cost‐effective fashion so as to ultimately achieve effective residential DSM. In this research, a live smart autonomous distributed energy disaggregation approach that is implemented in active edge‐cloud collaborative computing is developed for live smart residential mains energy disaggregation at the edge, and its practical evaluation is showcased. The proposed approach is an autonomous edge‐cloud collaborative two‐phase energy disaggregation scheme that can achieve complex open‐set load identification of single or multiple targeted unknown/new latent electrical appliances, whose implementation is horizontal federated learning‐accommodated. The autonomous edge‐cloud collaborative scheme implemented for live smart distributed energy disaggregation at the edge is a promising achievement, instead of transmitting raw private real‐time load data to a central cloud server for traditional AI model training. In the two‐phase energy disaggregation scheme, nonstationary/time‐varying/unexpected nontargeted unknown loads as noisy loads including small loads can be combated during the offline load modeling and online live load monitoring phases for an enhanced achievement of smart distributed energy disaggregation at the edge. Practical evaluations are conducted and used to demonstrate the feasibility and effectiveness of the developed approach applied to a public electrical‐end‐use data (EEUD) dataset for live smart distributed residential mains energy disaggregation at the edge.
No takes yet. Share an insight, caveat, or question.
Lin et al. (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: