Energy disaggregation using variational autoencoders

Langevin, Antoine; Carbonneau, Marc‐André; Cheriet, Mohamed; Gagnon, Ghyslain

doi:10.1016/j.enbuild.2021.111623

Cited by 41 publications

(31 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The attention mechanism is incorporated using the self-attention method [11,20,21] or the transformer architecture [22]. Recently, generative models have been proposed for the problem of NILM by using GANs [23] or variational approaches [24][25][26]. For the reader's reference, Huber et al [27] present an extensive review of several deep learning solutions for NILM.…”

Section: Related Workmentioning

confidence: 99%

Neural Fourier Energy Disaggregation

Nalmpantis

Gkalinikis

Vrakas

2022

Sensors

View full text Add to dashboard Cite

Deploying energy disaggregation models in the real-world is a challenging task. These models are usually deep neural networks and can be costly when running on a server or prohibitive when the target device has limited resources. Deep learning models are usually computationally expensive and they have large storage requirements. Reducing the computational cost and the size of a neural network, without trading off any performance is not a trivial task. This paper suggests a novel neural architecture that has less learning parameters, smaller size and fast inference time without trading off performance. The proposed architecture performs on par with two popular strong baseline models. The key characteristic is the Fourier transformation which has no learning parameters and it can be computed efficiently.

show abstract

Section: Related Workmentioning

confidence: 99%

Neural Fourier Energy Disaggregation

Nalmpantis

Gkalinikis

Vrakas

2022

Sensors

View full text Add to dashboard Cite

show abstract

“…The latter presents good robustness during the feature extraction phase against the noise generated from multiple appliances operating together. Moving forward, the authors in Reference [110] employ VAE to overcome the challenges of generalization over distinct households and the disaggregation of multistate devices for DL‐based NILM solutions. Typically, the probabilistic encoder encodes information pertinent for reconstructing the target device consumption, and the VAE‐based NILM scheme (i) accurately produces complex energy consumption profiles, (ii) improves the reconstruction of energy signals of multistate devices, and (iii) improves the generalization capability of overall architecture across separate households.…”

Section: Overview Of Recent Smart Nilm Algorithmsmentioning

confidence: 99%

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

“…Customer information can be derived from load profiles [21], which is the important information for utilities to provide personalized service or assist utilities in determining efficient rate structures and demand response [25]. Smart meter data disaggregation is another analysis approach, which helps customers understand the load profile of each appliance, e.g., [26,27]. This helps organize and optimize appliance usage schedules [28], as well as identify and eliminate low-efficient appliances [29].…”

Section: Related Workmentioning

confidence: 99%