An Analysis of Semi-Supervised Learning Approaches in Low-Rate Energy Disaggregation

Chang, Fang-Yi; Ho, Wingkei

doi:10.1109/icsgsc.2019.000-4

Cited by 3 publications

(8 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A second group of publications train on measured aggregate data but add synthetic data -also created by summing up sub-metered load curves -to increase the size of the training set. Four authors added individual activations from appliances to a measured aggregate [6,65,84,85]. Finally, some authors employed specialized strategies:…”

Section: Data Augmentationmentioning

confidence: 99%

“…The vast majority of approaches take as a continuous regularly sampled window from the time series of the aggregate measurement data input for the DNNs. The range of employed window lengths extends from 90 s [62] to around 9 h [40,88] or even 24 h [61,85]. It is important to note that the number of input samples to the neural networks, i.e.…”

Section: Shapementioning

confidence: 99%

“…These results might be caused by the relatively simple DNN. The authors of [85] trained an autoencoder on unlabeled data to subsequently use the learned embedding in a supervised training setting. This work was done on aggregate data with 15 min resolution that lead naturally to large estimation errors.…”

Section: Data Scarcitymentioning

confidence: 99%

See 2 more Smart Citations

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

Section: Data Augmentationmentioning

confidence: 99%

Section: Shapementioning

confidence: 99%

See 1 more Smart Citation

Review on Deep Neural Networks Applied to Low-Frequency NILM

Huber¹,

Calatroni²,

Rumsch³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The first part, estimation, is to estimate the portion of energy consumed owing to each appliance. The estimation strategy is inspired by our previous research "An Analysis of Semi-Supervised Learning Approaches in Low-Rate Energy Disaggregation" [5] and imitate a semi-supervised learning framework similar to it. As Figure 3, we perform sparse auto-encoder for the feature extraction on the daily time series of total power of both AMI and HEMS, and cluster these features with K-means clustering so that each HEMS feature is correspond to some ones of AMI nearby in the feature space.…”

Section: Nilm Estimationmentioning

confidence: 99%

“…Expensive meters with high sampling rate are needed for every appliance inside the house, and hence not applicable for a generalization to the whole city or the whole country. On the other hand, AMI, the cheap smart meters outside the house with low-sampling rate of 1mHz (sampling period of 15min) [4] [5], are quite suitable. And more and more countries regard AMI as fundamental infrastructure.…”

Section: Introductionmentioning

confidence: 99%

An Empirical Study with A Low-Cost Strategy for Improving the Energy Disaggregation via Questionnaire Survey

Chang¹,

Ho²,

Hung³

et al. 2020

Computer Science &Amp; Information Technology (CS &Amp; IT)

Self Cite

View full text Add to dashboard Cite

Based on neural network and machine learning, we apply the energy disaggregation for both classification (prediction on usage time) and estimation (prediction on usage amount) on 150 AMI (Advanced Metering Infrastructure) smart meters and a small amount of HEMS (Home Energy Management System) smart plugs in a community in New Taipei City, Taiwan. The aim of this paper is to clarify how we lower the cost, obtain the model of appliance usage from only a small portion of households, improve it with simple questionnaire, and generalize it for prediction on collective households. Our investigation demonstrates the benefits and various possibilities for power suppliers and the government, and won the Elite Award in the Presidential Hackathon 2020, Taiwan.

show abstract

Review on Deep Neural Networks Applied to Low-Frequency NILM

et al. 2021

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. The overall purpose of this review is, firstly, to gain an overview on the state of the research up to November 2020, and secondly, to identify worthwhile open research topics. Accordingly, we first review the many degrees of freedom of these approaches, what has already been done in the 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 mean absolute error (MAE) and F1-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 generative adversarial network (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

An Analysis of Semi-Supervised Learning Approaches in Low-Rate Energy Disaggregation

Cited by 3 publications

References 3 publications

Review on Deep Neural Networks Applied to Low-Frequency NILM

Review on Deep Neural Networks Applied to Low-Frequency NILM

An Empirical Study with A Low-Cost Strategy for Improving the Energy Disaggregation via Questionnaire Survey

Review on Deep Neural Networks Applied to Low-Frequency NILM

Contact Info

Product

Resources

About