Improving the Generalisability of Deep Learning NILM Algorithms using One-Shot Transfer Learning

Can one-shot transfer learning be leveraged to enhance the performance of a CNN-based NILM algorithm on unseen data?

Bachelor Thesis (2023)
Author(s)

W.J.M. Verschuren (TU Delft - Electrical Engineering, Mathematics and Computer Science)

Contributor(s)

Luciano Siebert – Mentor (TU Delft - Interactive Intelligence)

Sietze Kai Kuilman – Mentor (TU Delft - Interactive Intelligence)

MM De Weerdt – Graduation committee member (TU Delft - Algorithmics)

Faculty
Electrical Engineering, Mathematics and Computer Science
Copyright
© 2023 Wim Verschuren
More Info
expand_more
Publication Year
2023
Language
English
Copyright
© 2023 Wim Verschuren
Graduation Date
28-06-2023
Awarding Institution
Delft University of Technology
Project
['CSE3000 Research Project']
Programme
['Computer Science and Engineering']
Faculty
Electrical Engineering, Mathematics and Computer Science
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Non-Intrusive Load Monitoring (NILM) is a technique used to disaggregate household power consumption data into individual appliance components without the need for dedicated meters for each appliance. This paper focuses on improving the generalizability of NILM algorithms to unseen households using Convolutional Neural Networks (CNNs) and one-shot transfer learning. The research investigates the effectiveness of one-shot transfer learning in fine-tuning a CNN model to accurately detect the ON/OFF state of appliances in households not seen during the training phase of the CNN. The study utilizes the Pecan Street dataset for training and evaluation, which includes detailed energy consumption records from various locations in the United States. The results suggest that one-shot transfer learning could enhance the performance of the NILM algorithm, particularly when multiple data samples are used for fine-tuning. However, the effectiveness of one-shot transfer learning varies strongly depending on the number of samples and the characteristics of the target household.

Files

Wim_Verschuren_FINAL_3_.pdf
(pdf | 0.175 Mb)
License info not available