Non-Intrusive Load Identification Based on Multivariate Features and Information Entropy-Weighted Ensemble

In non-intrusive load monitoring (NILM), single-dimensional features exhibit limited representational capacity, while feature fusion at the feature layer often leads to information loss due to dimensional transformation, as well as the risk of dimensional explosion caused by the newly added features...

Full description

Saved in:
Bibliographic Details
Main Authors: Yue Liu, Wenxia You, Miao Yang
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Energies
Subjects:
Online Access:https://www.mdpi.com/1996-1073/18/9/2369
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850275382901604352
author Yue Liu
Wenxia You
Miao Yang
author_facet Yue Liu
Wenxia You
Miao Yang
author_sort Yue Liu
collection DOAJ
description In non-intrusive load monitoring (NILM), single-dimensional features exhibit limited representational capacity, while feature fusion at the feature layer often leads to information loss due to dimensional transformation, as well as the risk of dimensional explosion caused by the newly added features. To address these challenges, this paper proposes a non-intrusive load identification method based on multivariate features and information entropy-weighted ensemble. Specifically, one-dimensional numerical features related to power and current are input into traditional machine learning models, and two-dimensional image features of binary V-I trajectory are processed by the deep neural network model Swin Transformer. Information entropy is employed to adaptively determine the weight of each classification model, and a weighted voting strategy is utilized to combine the decisions of multiple models to obtain the final identification result. This approach achieves feature fusion at the decision layer, effectively avoiding dimensional transformations and fully leveraging the complementary advantages of features from different dimensions. Experimental results show that the proposed method achieves identification accuracies of 99.48% and 99.54% on the public datasets PLAID and WHITED, respectively.
format Article
id doaj-art-14608e2f582143e9a38fa5b3a4eaf1fb
institution OA Journals
issn 1996-1073
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Energies
spelling doaj-art-14608e2f582143e9a38fa5b3a4eaf1fb2025-08-20T01:50:45ZengMDPI AGEnergies1996-10732025-05-01189236910.3390/en18092369Non-Intrusive Load Identification Based on Multivariate Features and Information Entropy-Weighted EnsembleYue Liu0Wenxia You1Miao Yang2College of Electrical Engineering and New Energy, China Three Gorges University, Yichang 443002, ChinaCollege of Electrical Engineering and New Energy, China Three Gorges University, Yichang 443002, ChinaHubei Qingjiang Hydropower Dev Co., Ltd., Yichang 443000, ChinaIn non-intrusive load monitoring (NILM), single-dimensional features exhibit limited representational capacity, while feature fusion at the feature layer often leads to information loss due to dimensional transformation, as well as the risk of dimensional explosion caused by the newly added features. To address these challenges, this paper proposes a non-intrusive load identification method based on multivariate features and information entropy-weighted ensemble. Specifically, one-dimensional numerical features related to power and current are input into traditional machine learning models, and two-dimensional image features of binary V-I trajectory are processed by the deep neural network model Swin Transformer. Information entropy is employed to adaptively determine the weight of each classification model, and a weighted voting strategy is utilized to combine the decisions of multiple models to obtain the final identification result. This approach achieves feature fusion at the decision layer, effectively avoiding dimensional transformations and fully leveraging the complementary advantages of features from different dimensions. Experimental results show that the proposed method achieves identification accuracies of 99.48% and 99.54% on the public datasets PLAID and WHITED, respectively.https://www.mdpi.com/1996-1073/18/9/2369NILMmultivariate featuresinformation entropy-weighted votingV-I trajectory
spellingShingle Yue Liu
Wenxia You
Miao Yang
Non-Intrusive Load Identification Based on Multivariate Features and Information Entropy-Weighted Ensemble
Energies
NILM
multivariate features
information entropy-weighted voting
V-I trajectory
title Non-Intrusive Load Identification Based on Multivariate Features and Information Entropy-Weighted Ensemble
title_full Non-Intrusive Load Identification Based on Multivariate Features and Information Entropy-Weighted Ensemble
title_fullStr Non-Intrusive Load Identification Based on Multivariate Features and Information Entropy-Weighted Ensemble
title_full_unstemmed Non-Intrusive Load Identification Based on Multivariate Features and Information Entropy-Weighted Ensemble
title_short Non-Intrusive Load Identification Based on Multivariate Features and Information Entropy-Weighted Ensemble
title_sort non intrusive load identification based on multivariate features and information entropy weighted ensemble
topic NILM
multivariate features
information entropy-weighted voting
V-I trajectory
url https://www.mdpi.com/1996-1073/18/9/2369
work_keys_str_mv AT yueliu nonintrusiveloadidentificationbasedonmultivariatefeaturesandinformationentropyweightedensemble
AT wenxiayou nonintrusiveloadidentificationbasedonmultivariatefeaturesandinformationentropyweightedensemble
AT miaoyang nonintrusiveloadidentificationbasedonmultivariatefeaturesandinformationentropyweightedensemble