A Nonintrusive Load Identification Model Based on Time-Frequency Features Fusion

Li, Kexin; Yin, Bo; Du, Zehua; Sun, Yufei

doi:10.1109/access.2020.3047147

Cited by 31 publications

(19 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors in [20] designed a capsule-network-based LRA, in which Convolutional Neural Network (CNN) extracted latent features from a set of non-overlapping energy measurement data segments. [21] proposed a dual-stream neural network to extract features from current signals. [22] proposed to extract features with Siamese neural networks and then used them in load recognition.…”

Section: Related Workmentioning

confidence: 99%

Learning-Based Non-Intrusive Electric Load Monitoring for Smart Energy Management

He,

Liu,

Zhang

et al. 2024

Preprint

View full text Add to dashboard Cite

The state-of-the-art smart city has been calling for an economic but efficient energy management over large-scale network, especially for the electric power system. It is a critical issue to monitor, analyze and control electric loads of all users in system. In this paper, we employ the popular computer vision techniques of AI to design a non-intrusive load monitoring method for smart electric energy management. First of all, we utilize both signal transforms (including wavelet transform and discrete Fourier transform) and Gramian Angular Field (GAF) methods to map one-dimensional current signals onto two-dimensional color feature images. Second, we propose to recognize all electric loads from color feature images using a deep neural network with multi-scale feature extraction and attention mechanism. Third, we design our method as a cloud-based, non-intrusive monitoring of all users, thereby saving energy cost during electric power system control. Experimental results on both public and our private datasets have demonstrated our method achieves superior performances than its peers, and thus supports efficient energy management over large-scale Internet of Things.

show abstract

Section: Related Workmentioning

confidence: 99%

Learning-Based Non-Intrusive Electric Load Monitoring for Smart Energy Management

He,

Liu,

Zhang

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…In PLAID and IDOUC dataset, the proposed method has excellent performance comparing with other two methods. [15] proposed a two-stream convolutional neural network based on current time-frequency feature fusion for nonintrusive load identification. First, a time series image coding method was proposed to extract the time domain and frequency domain features.…”

Section: Related Work a Non-intrusive Load Monitoring (Nilm)mentioning

confidence: 99%

Non-Intrusive Adaptive Load Identification Based on Siamese Network

Wang

et al. 2022

IEEE Access

View full text Add to dashboard Cite

The traditional non-intrusive load monitoring (NILM) algorithms are mostly based on classification models, which have several deficiencies. Firstly, a large amount of labeled data is required to train the classification model. Secondly, these algorithms cannot identify unknown devices that frequently encountered in practical application. Finally, these models have poor performance in versatility which means they only adapt to the trained data. These shortcomings greatly influence the practicality of these NILM algorithms. To tackle these problems, this paper has proposed a non-intrusive adaptive load identification model based on the Siamese network, which uses both the V-I trajectory and active power as the load signatures. The Siamese network is utilized to calculate the similarity of the V-I trajectory, and the load identification is realized by matching the signature with the feature library. Through adding new features to the feature library dynamically, the identification of unknown load can be realized. In addition, the Siamese network is a typical network for few-shot learning, thus the proposed model can be trained with a small number of samples to achieve ideal recognition effect. At last, the validity and versatility of the model are verified in PLAID dataset and COOLL dataset.

show abstract

“…When compared to the other two approaches on the PLAID and IDOUC datasets, the proposed approach performs extremely well. [14] suggested a non-intrusive load detection system based on a two-stream convolutional neural network with current timefrequency feature fusion. To extract the time domain and frequency domain characteristics, a time series image coding approach was devised first.…”

Section: Related Workmentioning

confidence: 99%

Non-Intrusive Load Monitoring (NILM) Using a LSTM With Socio-Economic Parameters

Ahmed¹,

Taimoor²,

Javed³

et al. 2022

Preprint

View full text Add to dashboard Cite

Nonintrusive load monitoring (NILM) deconstructs aggregated electrical usage data into individual appliances. The dissemination of disaggregated data to customers raises consumer awareness and encourages them to save power, lowering CO2 emissions to the environment. The performance of NILM systems has increased dramatically thanks to recent disaggregation methods. However, the capacity of these algorithms to generalize to various dwellings as well as the disaggregation of multi-state appliances remain significant obstacles. In this paper, we propose an energy disaggregation approach by using socio-economic parameters. The suggested approach helps in creating more accurate load profiles, which improves the accuracy and helps in better detection of the appliances. The proposed model outperforms state-of-the-art NILM techniques on the PRECON dataset. The mean absolute error reduces by 5% -10% on average across all appliances compared to the state-of-the-art. Thus, improving the detection of the target appliance in the aggregate measurement.

show abstract

A Nonintrusive Load Identification Model Based on Time-Frequency Features Fusion

Cited by 31 publications

References 29 publications

Learning-Based Non-Intrusive Electric Load Monitoring for Smart Energy Management

Learning-Based Non-Intrusive Electric Load Monitoring for Smart Energy Management

Non-Intrusive Adaptive Load Identification Based on Siamese Network

Non-Intrusive Load Monitoring (NILM) Using a LSTM With Socio-Economic Parameters

Contact Info

Product

Resources

About