Application Prospect of Compressed Sensing in Non-intrusive Load Monitoring

被引：0
作者：
Yuan, Bo [1 ]
Ge, Shaoyun [1 ]
Liu, Hong [1 ]
机构：
[1] College of Electrical Automation and Information Engineering, Key Laboratory of Smart Grid of Ministration of Education, Tianjin University, Nankai District, Tianjin
来源：
Zhongguo Dianji Gongcheng Xuebao/Proceedings of the Chinese Society of Electrical Engineering | 2024年 / 44卷 / 16期
关键词：
application modes; compressed sensing; event detection; improvement compressed sensing (CS) elements; load analysis method; load decomposition; load identification; non-intrusive load monitoring;
D O I：
10.13334/j.0258-8013.pcsee.230255
中图分类号：
学科分类号：
摘要：
With further application of compressed sensing (CS) in smart grid, research on CS application in non-invasive load monitoring (NILM) is lagging behind. For this reason, after analyzing application necessity of CS in NILM, this paper provides an outlook and exploration into the untapped application research of CS in NILM. First, three application modes of CS in NILM are proposed by comparing the principle of CS and the process of NILM. Then, based on the specific processes of those three application modes, the research directions in theory and suitable scenarios in engineering for each application mode are prospected. On this basis, the key technologies that need to be addressed in the application of CS in NILM are mainly discussed from two aspects which are CS elements and load analysis. The research ideas for improving CS elements such as measurement matrix, sparse basis and reconstruction algorithm adapted to NILM are deeply discussed, while the implementation idea of load analysis methods under CS framework such as event detection, load decomposition, load identification and feature extraction are proposed. The work done in this paper aims to realize the preliminary exploration of the application of CS in NILM, which provides guidance for follow-up research. © 2024 Chinese Society for Electrical Engineering. All rights reserved.
引用
收藏
页码：6416 / 6431
页数：15
相关论文
共 113 条
  • [51] DONG Weiguang, ZHANG Xiaodong, TANG Min'an, Voltage signal reconstruction method of wind power converter based on ITD and improved inner product compressed sensing[J], High Voltage Engineering, 44, 7, pp. 2338-2345, (2018)
  • [52] SHI Guangming, LIU Danhua, GAO Dahua, Advances in theory and application of compressed sensing[J], Acta Electronica Sinica, 37, 5, pp. 1070-1081, (2009)
  • [53] GLEICHMAN S, ELDAR Y C．, Blind compressed sensing [J], IEEE Transactions on Information Theory, 57, 10, pp. 6958-6975, (2011)
  • [54] RAVISHANKAR S, BRESLER Y．, Data-driven learning of a union of sparsifying transforms model for blind compressed sensing[J], IEEE Transactions on Computational Imaging, 2, 3, pp. 294-309, (2016)
  • [55] SINGHAL V, MAJUMDAR A, WARD R K, Semi-supervised deep blind compressed sensing for analysis and reconstruction of biomedical signals from compressive measurements[J], IEEE Access, 6, pp. 545-553, (2018)
  • [56] LINGALA S G, JACOB M．, Blind compressive sensing dynamic MRI[J], IEEE Transactions on Medical Imaging, 32, 6, pp. 1132-1145, (2013)
  • [57] TSAIG Y, DONOHO D L．, Extensions of compressed sensing[J], Signal Processing, 86, 3, pp. 549-571, (2006)
  • [58] CANDES E J，, ROMBERG J, TAO T．, Robust uncertainty principles ： exact signal reconstruction from highly incomplete frequency information[J], IEEE Transactions on Information Theory, 52, 2, pp. 489-509, (2006)
  • [59] CANDES E J, TAO T, Decoding by linear programming[J], IEEE Transactions on Information Theory, 51, 12, pp. 4203-4215, (2005)
  • [60] RAUHUT H．, Compressive sensing and structured random matrices[J], Theoretical Foundations and Numerical Methods for Sparse Recovery, 9, 1, pp. 1-92, (2010)
12345678910