Abstract

Precise estimation of flexible loads with different elasticity characteristics from the substation scale is crucial for demand-side management, especially considering the facility cost and privacy-preserving problem. However, owing to the non-independent and identical distribution resulting from randomness and variation in residential load profiles, as well as the load signature overlapping from power consumption aggregation, substation-level deferrable load exhibits non-periodicity with limited correlation with external factors, posing considerable challenges for disaggregation. To bridge the research gap, this paper proposes a hierarchical federated perception algorithm to disaggregate both deferrable and interruptible loads from the substation level following an edge-cloud collaborative framework. Firstly, residential load profiles are clustered with Affinity Propagation to exploit the hidden structural features from substation data. Secondly, the bottom-level residential load perception model is established based on FedPer to extract shared characteristics from representative residents through a lightweight federated sequence-to-point structure in a privacy-preserving manner. Subsequently, after the layerwise model transfer from the residential level, the top-level substation load disaggregation model is established, capable of precisely tracking transient fluctuations in complex deferrable loads. The proposed algorithm is verified on both the simulation platform and public datasets, demonstrating its accuracy, robustness, and efficiency for substation-level flexible load disaggregation.