A Self-training Multi-task Attention Method for NILM

Li, Keqin; Xing, Yitong; Wang, Bowen

doi:10.1109/ddcls55054.2022.9858445

Cited by 3 publications

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, both HMM-based methods and machine learning methods, such as SVM and KNN-based methods, require manual feature extraction. In contrast, deep neural network methods can automatically extract features without human involvement [17].…”

Section: Introductionmentioning

confidence: 99%

Non-Intrusive Load Decomposition Based on Instance-Batch Normalization Networks

Wang

Liu

2023

Energies

View full text Add to dashboard Cite

At present, the non-intrusive load decomposition method for low-frequency sampling data is as yet insufficient within the context of generalization performance, failing to meet the decomposition accuracy requirements when applied to novel scenarios. To address this issue, a non-intrusive load decomposition method based on instance-batch normalization network is proposed. This method uses an encoder-decoder structure with attention mechanism, in which skip connections are introduced at the corresponding layers of the encoder and decoder. In this way, the decoder can reconstruct a more accurate power sequence of the target. The proposed model was tested on two public datasets, REDD and UKDALE, and the performance was compared with mainstream algorithms. The results show that the F1 score was higher by an average of 18.4 when compared with mainstream algorithms. Additionally, the mean absolute error reduced by an average of 25%, and the root mean square error was reduced by an average of 22%.

show abstract

Section: Introductionmentioning

confidence: 99%

Non-Intrusive Load Decomposition Based on Instance-Batch Normalization Networks

Wang

Liu

2023

Energies

View full text Add to dashboard Cite

show abstract

“…Other than the multi-task learning, some researchers have explored the effectiveness of different learning strategies for NILM. For example, Li et al proposed a self-training multi-task attention method [28], which employs a dual-branch network structure like SGN but with single-task training considering the discrepancy between the network's disaggregation results and the labels. In 2023, Chen et al incorporate self-supervised learning into NILM [29], where the network is pre-trained on an unlabeled dataset using a self-supervised pretext task and then fine-tuned using a labeled dataset in the downstream task.…”

mentioning

confidence: 99%