Home Journal of Xinjiang University(Natural Science Edition in Chinese and English) Article
PDF (35.6 MB)
Cite
EndNote(RIS) BibTeX
Collect
Submit Manuscript
Show Outline
Outline
Abstract
Keywords
References
Show full outline
Hide outline

Research on Feature Model and Mining Method for Current Transition Sequence

Hui ZHANG1,2, Shuai LIU1,2, Zecheng YANG1,2, Ping WANG1,2, Hongmei CHENG1,3, Zhenya ZHANG1,2()
Anhui Province Key Laboratory of Intelligent Building & Building Energy Saving, Anhui Jianzhu University, Hefei Anhui 230022, China
School of Electronic and Information Engineering, Anhui Jianzhu University, Hefei Anhui 230022, China
School of Economics and Management, Anhui Jianzhu University, Hefei Anhui 230022, China
Show Author Information

Abstract

In this paper, based on the high-frequency monitoring of current in the circuit via smart sockets and electrical situation data of the customer obtained, the current transition sequence and the univariate regression model for the feature of the current transition sequence are proposed. Based on the ε-fragment for the current steady sequence and fragment for the current stable sequence, a mining method for current transition sequence discovery is designed. And further, a univariate regression model is proposed to describe each current transition sequence. And with the univariate regression model, each current transition sequence in variable length is mapped into the feature space for the current transition sequence with fixed dimension. Furthermore, a microenvironment-based particle swarm optimization (MPSO) algorithm is given to optimize the univariate regression features for the current transition sequences. The experimental results show that using the current transition sequence features proposed in this paper for electrical device state recognition can achieve an average accuracy of 97.93%. Compared with the PSO algorithm and CAPSO algorithm, the MPSO algorithm used in this paper achieves the same accuracy with fewer particles and significantly reduces usage time.

Keywords

current transition sequenceparticle swarm optimization algorithmunivariate regression modelmicroenvironment
Article ID: 2096-7675(2024)01-0037-015

References

[1]
WANG P, LIN J Y, GUO S, et al. Distribution system data analytics and applications[J]. Power System Technology, 2017, 41(10): 3333-3340. (in Chinese)
Google Scholar
[2]
ZHOU Y J, WU Y X, DONG Z H, et al. Non-intrusive load monitoring based on motif mining and harmonic function based semi-supervised learning[J]. Electric Power Automation Equipment, 2022, 42(7): 3-10. (in Chinese)
Google Scholar
[3]
ZHU T Y, AI Q, HE X, et al. An overview of data-driven electricity consumption behavior analysis method and application[J]. Power System Technology, 2020, 44(9): 3497-3507. (in Chinese)
Google Scholar
[4]
LIN Y H, TSAI M S. Development of an improved time-frequency analysis-based nonintrusive load monitor for load demand identification[J]. IEEE Transactions on Instrumentation and Measurement, 2014, 63(6): 1470-1483.
Crossref Google Scholar
[5]
SAITOH T, OSAKI T, KONISHI R, et al. Current sensor based home appliance and state of appliance recognition[J]. SICE Journal of Control, Measurement, and System Integration, 2010, 3(2): 86-93.
Crossref Google Scholar
[6]
YAN D, JIN Y, SUN H S, et al. Household appliance recognition through a Bayes classification model[J]. Sustainable Cities and Society, 2019, 46: 101393.
Crossref Google Scholar
[7]
MULINARI B M, DE CAMPOS D P, DA COSTA C H, et al. A new set of steady-state and transient features for power signature analysis based on V-I trajectory[C]//2019 IEEE PES Innovative Smart Grid Technologies Conference-Latin America (ISGT Latin America). Gramado, Brazil. IEEE, 2019: 1-6.
Crossref
[8]
CHEN J F, WANG X, ZHANG X T, et al. Temporal and spectral feature learning with two-stream convolutional neural networks for appliance recognition in NILM[J]. IEEE Transactions on Smart Grid, 2022, 13(1): 762-772.
Crossref Google Scholar
[9]
NORFORD L K, LEEB S B. Non-intrusive electrical load monitoring in commercial buildings based on steady-state and transient load-detection algorithms[J]. Energy and Buildings, 1996, 24(1): 51-64.
Crossref Google Scholar
[10]
CHANG H H. Non-intrusive demand monitoring and load identification for energy management systems based on transient feature analyses[J]. Energies, 2012, 5(11): 4569-4589.
Crossref Google Scholar
[11]
LE T T H, KANG H, KIM H. Household appliance classification using lower odd-numbered harmonics and the bagging decision tree[J]. IEEE Access, 2020, 8: 55937-55952.
Crossref Google Scholar
[12]
BOUHOURAS A S, GKAIDATZIS P A, PANAGIOTOU E, et al. A NILM algorithm with enhanced disaggregation scheme under harmonic current vectors[J]. Energy and Buildings, 2019, 183: 392-407.
Crossref Google Scholar
[13]
HIMEUR Y, ALSALEMI A, BENSAALI F, et al. Robust event-based non-intrusive appliance recognition using multi-scale wavelet packet tree and ensemble bagging tree[J]. Applied Energy, 2020, 267: 114877.
Crossref Google Scholar
[14]
GUO L Y, WANG S X, CHEN H W, et al. A load identification method based on active deep learning and discrete wavelet transform[J]. IEEE Access, 2020, 8: 113932-113942.
Crossref Google Scholar
[15]
JIMENEZ Y, DUARTE C, PETIT J, et al. Feature extraction for nonintrusive load monitoring based on S-Transform[C]//2014 Clemson University Power Systems Conference. Clemson, SC, USA. IEEE, 2014: 1-5.
Crossref
[16]
ZHANG G J. Design and implementation of smart socket system for electricity equipment management[D]. Hefei: Anhui Jianzhu University, 2017. (in Chinese)
[17]
FANG Q S, ZHANG G J, ZHANG Z Y, et al. An intelligent socket: CN205039355U[P]. 2016-02-17. (in Chinese)
[18]
DUAN Y X, CHEN N, CHANG L J, et al. CAPSO: Chaos adaptive particle swarm optimization algorithm[J]. IEEE Access, 2022, 10: 29393-29405.
Crossref Google Scholar
[19]
ZHANG Z Y, FANG B, WANG P, et al. A local area network-based insect intelligent building platform[J]. International Journal of Pattern Recognition and Artificial Intelligence, 2023, 37(2): 2359004.
Crossref Google Scholar
Journal of Xinjiang University(Natural Science Edition in Chinese and English)
Volume 41 Issue 1,
January 2024
Pages 37-51
DOI: 10.13568/j.cnki.651094.651316.2023.06.29.0001
Cite this article:
ZHANG H, LIU S, YANG Z, et al. Research on Feature Model and Mining Method for Current Transition Sequence. Journal of Xinjiang University(Natural Science Edition in Chinese and English), 2024, 41(1): 37-51. https://doi.org/10.13568/j.cnki.651094.651316.2023.06.29.0001
Metrics & Citations  
Article History
Copyright
Return