On the Feasibility of Generic Deep Disaggregation for Single-Load Extraction

Barsim, Karim Said; Yang, Bin

doi:10.48550/arxiv.1802.02139

Cited by 4 publications

(7 citation statements)

References 18 publications

(31 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…which can be viewed as a non-linear regression problem. Deep neural networks is a natural approach to learn the function f , and recently, it has been successfully applied to NILM [31], [8], [32], [33], [34], [35], [36], [37], [38], [39], [40], [41], [42]. From the point of the view of statistical methods, it has been pointed out in [8] that given the pairs (X, Y ) we could train a model to represent a conditional distribution p(X|Y ).…”

Section: Introductionmentioning

confidence: 99%

Transfer Learning for Non-Intrusive Load Monitoring

D'Incecco

Squartini

Zhong

2020

IEEE Trans. Smart Grid

221

159

View full text Add to dashboard Cite

Non-intrusive load monitoring (NILM) is a technique to recover source appliances from only the recorded mains in a household. NILM is unidentifiable and thus a challenge problem because the inferred power value of an appliance given only the mains could not be unique. To mitigate the unidentifiable problem, various methods incorporating domain knowledge into NILM have been proposed and shown effective experimentally. Recently, among these methods, deep neural networks are shown performing best. Arguably, the recently proposed sequenceto-point (seq2point) learning is promising for NILM. However, the results were only carried out on the same data domain. It is not clear if the method could be generalised or transferred to different domains, e.g., the test data were drawn from a different country comparing to the training data. We address this issue in the paper, and two transfer learning schemes are proposed, i.e., appliance transfer learning (ATL) and crossdomain transfer learning (CTL). For ATL, our results show that the latent features learnt by a 'complex' appliance, e.g., washing machine, can be transferred to a 'simple' appliance, e.g., kettle. For CTL, our conclusion is that the seq2point learning is transferable. Precisely, when the training and test data are in a similar domain, seq2point learning can be directly applied to the test data without fine tuning; when the training and test data are in different domains, seq2point learning needs fine tuning before applying to the test data. Interestingly, we show that only the fully connected layers need fine tuning for transfer learning. Source code can be found at https://github.com/MingjunZhong/transferNILM.

show abstract

Section: Introductionmentioning

confidence: 99%

Transfer Learning for Non-Intrusive Load Monitoring

D'Incecco

Squartini

Zhong

2020

IEEE Trans. Smart Grid

221

159

View full text Add to dashboard Cite

show abstract

“…가전기기의 고도화, 주거 사용자 패턴의 다각화와 유효한 전력 소비 피드백을 제공하기 위해서는 가전기기와 사용 패턴에 의존성이 적은 딥러닝 기반 접근법이 적절하다고 판단된다. Convolutional Neural Networks(CNN) [12][13][14] , Recurrent Neural Networks (RNN) 15,16) 및 Long Short-Term Memory(LSTM) [16][17][18] , denoising autoencoder (dAE) 19)…”

Section: 기호 및 약어 설명unclassified

Deep Learning Based Active Power Disaggregation of Appliances for Personalized Energy Feedback System

Kim

Kim²,

Shin³

2022

J Korean Solar Energy

View full text Add to dashboard Cite

Energy consumption feedback with an appliance-level feedback system can reduce consumption by a maximum of 12%. In this study, we proposed a data acquisition and training framework for configuring deep learning based on Non-Intrusive Load Monitoring (NILM) for a personalized and appliance-level energy consumption feedback system. To construct a training dataset, an aggregation of active power data from four types of home appliances (refrigerator, induction, TV, washing machine) was performed for approximately three weeks. LSTNet was applied to extract and recognize the features of active power data and the state of each home appliance. With an accuracy metric of more than 90% of the disaggregation result, the applicability of the appliance-level active power feedback system was verified.

show abstract

“…The Neural NILM Rectangle model (Kelly and Knottenbelt 2015a) and Single Load Extraction model (Barsim and Yang 2018) two deep learning NILM models dealing with the time sequence of energy consumption for multiple appliances active power disaggregation. They are both build with UK-DALE dataset (Kelly and Knottenbelt 2015b) 1/6 Hz sampling active power time pattern.…”

Section: Time-series Based Operation Detection Modelsmentioning

confidence: 99%

PUMPNET: a deep learning approach to pump operation detection

Meng

Pan

et al. 2021

Energy Inform

View full text Add to dashboard Cite

Non-urgent high energy-consuming residential appliances, such as pool pumps, may significantly affect the peak to average ratio (PAR) of energy demand in smart grids. Effective load monitoring is an important step to provide efficient demand response (DR) to PAR. In this paper, we focus on pool pump analytics and present a deep learning framework, PUMPNET, to identify the pool pump operation patterns from power consumption data. Different from conventional time-series based Non-intrusive Load Monitoring (NILM) methods, our approach transfers the time-series data into image-like (date-time matrix) data. Then a U-shaped fully convolutional neural network is developed to detect and segment the image-like data in pixel level for operation detection. Our approach identify whether pool pumps operate given thirty-minute interval aggregated active power consumption data in kilowatt-hours only. Furthermore, the PUMPNET algorithm could identify pool pump operation status with high accuracy in the low-frequency sampling scenario for thousands of household, compared to traditional NILM algorithms which process high sampling rate data and can only apply to limited number of households. Experiments on real-world data validate the promising results of the proposed PUMPNET model.

show abstract

On the Feasibility of Generic Deep Disaggregation for Single-Load Extraction

Cited by 4 publications

References 18 publications

Transfer Learning for Non-Intrusive Load Monitoring

Transfer Learning for Non-Intrusive Load Monitoring

Deep Learning Based Active Power Disaggregation of Appliances for Personalized Energy Feedback System

PUMPNET: a deep learning approach to pump operation detection

Contact Info

Product

Resources

About