Knowledge distillation for scalable non-intrusive load monitoring

Giulia Tanoni, Lina Stankovic, Vladimir Stankovic, Stefano Squartini, Emanuele Principi

Research output: Contribution to journalArticlepeer-review

58 Downloads (Pure)

Abstract

Smart meters allow the grid to interface with individual buildings and extract detailed consumption information using nonintrusive load monitoring (NILM) algorithms applied to the acquired data. Deep neural networks, which represent the state of the art for NILM, are affected by scalability issues since they require high computational and memory resources, and by reduced performance when training and target domains mismatched. This article proposes a knowledge distillation approach for NILM, in particular for multilabel appliance classification, to reduce model complexity and improve generalization on unseen data domains. The approach uses weak supervision to reduce labeling effort, which is useful in practical scenarios. Experiments, conducted on U.K.-DALE and REFIT datasets, demonstrated that a low-complexity network can be obtained for deployment on edge devices while maintaining high performance on unseen data domains. The proposed approach outperformed benchmark methods in unseen target domains achieving a F1 -score 0.14 higher than a benchmark model 78 times more complex.
Original languageEnglish
Pages (from-to)4710-4721
Number of pages12
JournalIEEE Transactions on Industrial Informatics
Volume20
Issue number3
Early online date9 Nov 2023
DOIs
Publication statusPublished - 1 Mar 2024

Keywords

  • deep learning
  • knowledge distillation
  • weak supervision
  • multi-label appliance classification
  • non-intrusive load monitoring

Fingerprint

Dive into the research topics of 'Knowledge distillation for scalable non-intrusive load monitoring'. Together they form a unique fingerprint.

Cite this