PB-NILM: Pinball Guided Deep Non-Intrusive Load Monitoring

Gomes, Eduardo Rodrigues; Pereira, Lucas

doi:10.1109/access.2020.2978513

Cited by 47 publications

(32 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The vast majority of works employ either the mean absolute error (MAE) or the mean squared error (MSE) in case of power disaggregation and the cross entropy loss for on/off classification. Recent works also investigate alternative loss functions: Quantile regression [123] was employed by [124,125].…”

Section: Training and Loss Functionsmentioning

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

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: Training and Loss Functionsmentioning

confidence: 99%

“…The authors of [124] found that their proposed loss increased the performance of two state-of-the-art models compared to the MSE loss. Some works [59,71,76,126] employ GAN loss functions -called 'adversarial loss' in [76] -that classify if the output of the regression DNN is a real or fake appliance load curve.…”

Section: Training and Loss Functionsmentioning

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

show abstract

“…These algorithms typically outperform unsupervised approaches in terms of accuracy, but require labelled data for training, which can be difficult or expensive to obtain. Numerous supervised learning algorithms have been applied for NILM, including support vector machines (SVMs) [38], [39], and both shallow [40], [41] and deep neural networks (NNs) [42], [43]. Researchers have also used pre-filtering techniques to generate input features for NNs across vastly different time-scales [37] and combined NN-based load identification with unsupervised learning optimization techniques to improve results [44].…”

Section: Nonintrusive Load Monitoring Reviewmentioning

confidence: 99%

Nonintrusive Load Monitoring of Variable Speed Drive Cooling Systems

et al. 2020

View full text Add to dashboard Cite

To improve the energy efficiencies of building cooling systems, manufacturers are increasingly utilizing variable speed drive (VSD) motors in system components, e.g. compressors and condensers. While these technologies can provide significant energy savings, these benefits are only realized if these components operate as intended and under proper control. Undetected faults can foil efficiency gains. As such, it's imperative to monitor cooling system performance to both identify faulty conditions and to properly inform building or multi-building models used for predictive control and energy management. This paper presents nonintrusive load monitoring (NILM) based "mapping" techniques for tracking the performance of a building's central air conditioning from smart electrical meter or energy monitor data. Using a multivariate linear model, a first mapping disaggregates the air conditioner's power draw from that of the total building by exploiting the correlations between the building's line-current harmonics and the power consumption of the air conditioner's VSD motors. A second mapping then estimates the air conditioner's heat rejection performance using as inputs the estimated power draw of the first mapping, the building's zonal temperature, and the outside environmental temperature. The usefulness of these mapping techniques are demonstrated using data collected from a research facility building on the Masdar City Campus of Khalifa University. The mapping techniques combine to provide accurate estimates of the building's air conditioning performance when operating under normal conditions. These estimates could thus be used as feedback in building energy management controllers and can provide a performance baseline for detection of air conditioner underperformance.

show abstract

“…NILM provides households with cost-effective monitoring of appliance-specific energy consumption, and it can be easily integrated into existing buildings without causing any inconvenience to inhabitants. Several machine learning techniques have been proposed to address the energy-disaggregation [7][8][9][10][11][12].…”

Section: Introductionmentioning

confidence: 99%

Multi-Label Learning for Appliance Recognition in NILM Using Fryze-Current Decomposition and Convolutional Neural Network

Faustine

Pereira²

2020

Energies

Self Cite

View full text Add to dashboard Cite

The advance in energy-sensing and smart-meter technologies have motivated the use of a Non-Intrusive Load Monitoring (NILM), a data-driven technique that recognizes active end-use appliances by analyzing the data streams coming from these devices. NILM offers an electricity consumption pattern of individual loads at consumer premises, which is crucial in the design of energy efficiency and energy demand management strategies in buildings. Appliance classification, also known as load identification is an essential sub-task for identifying the type and status of an unknown load from appliance features extracted from the aggregate power signal. Most of the existing work for appliance recognition in NILM uses a single-label learning strategy which, assumes only one appliance is active at a time. This assumption ignores the fact that multiple devices can be active simultaneously and requires a perfect event detector to recognize the appliance. In this paper proposes the Convolutional Neural Network (CNN)-based multi-label learning approach, which links multiple loads to an observed aggregate current signal. Our approach applies the Fryze power theory to decompose the current features into active and non-active components and use the Euclidean distance similarity function to transform the decomposed current into an image-like representation which, is used as input to the CNN. Experimental results suggest that the proposed approach is sufficient for recognizing multiple appliances from aggregated measurements.

show abstract

PB-NILM: Pinball Guided Deep Non-Intrusive Load Monitoring

Cited by 47 publications

References 36 publications

Review on Deep Neural Networks Applied to Low-Frequency NILM

Review on Deep Neural Networks Applied to Low-Frequency NILM

Nonintrusive Load Monitoring of Variable Speed Drive Cooling Systems

Multi-Label Learning for Appliance Recognition in NILM Using Fryze-Current Decomposition and Convolutional Neural Network

Contact Info

Product

Resources

About