Sequence-To-Subsequence Learning With Conditional Gan For Power Disaggregation

Pan, Yungang; Liu, Ke; Shen, Zhaoyan; Cai, Xiaoyan; Jia, Zhiping

doi:10.1109/icassp40776.2020.9053947

Cited by 53 publications

(61 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…EnerGAN++ is a robust to noise model and achieves good performance, regardless of noise, in contrast to the SEQ2SUB model. SEQ2SUB model achieves good results in normal cases as shown in [31], however, given noise aggregate signal input, its performance is degraded (Fig. 9).…”

Section: Robustness To Noisementioning

confidence: 79%

“…9. Comparison between EnerGAN++ model results provided after applying Gaussian noise to the aggregate signal and the respective results of the disaggregation using the sequence to sub-sequence conditional GAN model of [31]. The small MAE error values provide better performance.…”

Section: Robustness To Noisementioning

confidence: 99%

“…Fig. 9 compares the results of EnerGAN++ model with the corresponding results provided by the sequence to subsequence conditional GAN model [31], given noisy aggregate signal values, for the REFIT dataset. EnerGAN++ is a robust to noise model and achieves good performance, regardless of noise, in contrast to the SEQ2SUB model.…”

Section: Robustness To Noisementioning

confidence: 99%

“…3) Generative Adversarial Networks in NILM Modelling: Bao et al [30] adopt a GAN-based framework for solving NILM in an early attempt. Then, Kaselimi et al [9] propose a generative adversarial network for sequence to sequence learning, whereas Pan et al [31] achieve sequence to sub-sequence learning with conditional GANs. Chen et al [32] propose a context aware convolutional network for NILM that has been trained adversarially.…”

mentioning

confidence: 99%

See 3 more Smart Citations

EnerGAN++: A Generative Adversarial Gated Recurrent Network for Robust Energy Disaggregation

Kaselimi

Doulamis

Voulodimos

et al. 2021

IEEE Open J. Signal Process.

View full text Add to dashboard Cite

Section: Robustness To Noisementioning

confidence: 79%

Section: Robustness To Noisementioning

confidence: 99%

Section: Robustness To Noisementioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

EnerGAN++: A Generative Adversarial Gated Recurrent Network for Robust Energy Disaggregation

Kaselimi

Doulamis

Voulodimos

et al. 2021

IEEE Open J. Signal Process.

View full text Add to dashboard Cite

“…Some authors also normalized the target values for the training of the DNNs. While some publications mention that different normalization strategies were tried out, only two studies report on the influence of normalization strategies on training efficiency and testing performance: [71] finds that instance normalization [72] performs better than batch normalization [73] and [69] concludes that L 2 -normalization works best.…”

Section: Preprocessingmentioning

confidence: 99%

Review on Deep Neural Networks Applied to Low-Frequency NILM

Huber¹,

Calatroni²,

Rumsch³

et al. 2021

Preprint

View full text Add to dashboard Cite

This paper reviews non-intrusive load monitoring (NILM) approaches that employ deep neural networks to disaggregate appliances from low frequency data, i.e. data with sampling rates lower than the AC base frequency. We first review the many degrees of freedom of these approaches, what has already been done in literature, and compile the main characteristics of the reviewed publications in an extensive overview table. The second part of the paper discusses selected aspects of the literature and corresponding research gaps. In particular, we do a performance comparison with respect to reported MAE and F$_1$-scores and observe different recurring elements in the best performing approaches, namely data sampling intervals below 10\,s, a large field of view, the usage of GAN losses, multi-task learning, and post-processing. Subsequently, multiple input features, multi-task learning and related research gaps are discussed, the need for comparative studies is highlighted, and finally, missing elements for a successful deployment of NILM approaches based on deep neural networks are pointed out. We conclude the review with an outlook on possible future scenarios.

show abstract

Recent trends of smart nonintrusive load monitoring in buildings: A review, open challenges, and future directions

Himeur

Alsalemi

Bensaali

et al. 2022

Int J of Intelligent Sys

View full text Add to dashboard Cite

Smart nonintrusive load monitoring (NILM) represents a cost-efficient technology for observing power usage in buildings. It tackles several challenges in transitioning into a more effective, sustainable, and digital energy efficiency environment. This paper presents a comprehensive review of recent trends in the NILM field, in which we propose a multiperspective classification of existing smart NILM techniques. More attention is devoted to describing the contributions of deep learning, feature extraction, computing platforms, and application scenarios for NILM development. Accordingly, NILM technical aspects are first Int J Intell Syst. 2022;37:7124-7179. wileyonlinelibrary.com/journal/int investigated, including data collection devices and public data sets. Next, event-based and non-eventbased NILM algorithms are overviewed. Furthermore, potential limitations of existing solutions are identified, highlighting their technical challenges, especially those related to security and privacy preservation, data scarcity, results reproduction, and implementation and business difficulties. Lastly, future directions are explored to overcome the identified limitations.

show abstract

Sequence-To-Subsequence Learning With Conditional Gan For Power Disaggregation

Cited by 53 publications

References 7 publications

EnerGAN++: A Generative Adversarial Gated Recurrent Network for Robust Energy Disaggregation

EnerGAN++: A Generative Adversarial Gated Recurrent Network for Robust Energy Disaggregation

Review on Deep Neural Networks Applied to Low-Frequency NILM

Recent trends of smart nonintrusive load monitoring in buildings: A review, open challenges, and future directions

Contact Info

Product

Resources

About