Loading [MathJax]/extensions/MathZoom.js
Load Recognition With Few-Shot Transfer Learning Based on Meta-Learning and Relational Network in Non-Intrusive Load Monitoring | IEEE Journals & Magazine | IEEE Xplore

Load Recognition With Few-Shot Transfer Learning Based on Meta-Learning and Relational Network in Non-Intrusive Load Monitoring


Abstract:

Non-intrusive load monitoring (NILM) monitors the operating status and power consumption of residential appliances with only one main meter, providing a new measure for e...Show More

Abstract:

Non-intrusive load monitoring (NILM) monitors the operating status and power consumption of residential appliances with only one main meter, providing a new measure for energy management. Deep learning (DL) shows outperformance in NILM. However, the lack of appliance data caused by rapid growth appliance types and high-cost data sampling reduces the DL-based load recognition accuracy. Transfer learning (TL) enables DL-based model generalization. However, the generalization would be limited when data in the target domain are insufficient. Therefore, a non-intrusive load recognizing (NILR) few-shot TL based on meta-learning and relational network is proposed to improve the load recognition generalization performance, named MRNILR-TL. First, the method constructs an episode task dataset by task sampling to provide diverse learnable tasks for few-shot load recognition training. Afterward, a multi-classification load recognition model based on meta-learning and relational network is constructed, and a meta-learning based relational network enhances the ability to learn the laws of similarity among appliance features from few-shot data. Finally, achieving the few-shot multi-classification load recognition generalization by directly transferring the source task knowledge and strategies to the target task. Experimental results in four transfer scenes demonstrate the proposed method achieves generalization and outperforms most existing NILM TL methods.
Published in: IEEE Transactions on Smart Grid ( Volume: 15, Issue: 5, September 2024)
Page(s): 4861 - 4876
Date of Publication: 18 April 2024

ISSN Information:

Funding Agency:


I. Introduction

Carbon emissions caused by energy consumption are seriously affecting climate change. Scientific control of carbon emissions could balance economic development and environmental protection. With the level of electrification in society, more terminal energy consumption has shifted from other energy sources to electricity, gradually forming a new energy pattern dominated by electricity. Therefore, the carbon emission reduction pressure in the power industry continues to increase. As an essential part of the new energy industry, the demand side of power grid realizes refined and intelligent energy management through “Internet + energy,” improving energy efficiency and reducing carbon emissions. Energy management needs to know the detailed appliance electrical quantity data. Although the smart appliances produced in recent years could directly provide usage information through embedded sensor hardware, many non-smart appliances are still without sensors today.

References

References is not available for this document.