Please wait a minute...
购物车 申请加入邮件组 English
高级检索 图表检索
Frontiers in Energy

ISSN 2095-1701

ISSN 2095-1698(Online)

CN 11-6017/TK

邮发代号 80-972

2019 Impact Factor: 2.657

热点文章  |  下载排行  |  浏览排行
在线投稿 免费RSS订阅
Frontiers in Energy  2022, Vol. 16 Issue (1): 130-143   https://doi.org/10.1007/s11708-022-0822-z
  本期目录
State identification of home appliance with transient features in residential buildings
Lei YAN1, Runnan XU1, Mehrdad SHEIKHOLESLAMI1, Yang LI2, Zuyi LI1()
1. Electrical and Computer Engineering Department, Illinois Institute of Technology, Chicago, IL 60616, USA; School of Electrical Engineering, Northeast Electric Power University, Jilin 132012, China
2. School of Electrical Engineering, Northeast Electric Power University, Jilin 132012, China
 全文: PDF(2229 KB)   HTML
Abstract：

Nonintrusive load monitoring (NILM) is crucial for extracting patterns of electricity consumption of household appliance that can guide users’ behavior in using electricity while their privacy is respected. This study proposes an online method based on the transient behavior of individual appliances as well as system steady-state characteristics to estimate the operating states of the appliances. It determines the number of states for each appliance using the density-based spatial clustering of applications with noise (DBSCAN) method and models the transition relationship among different states. The states of the working appliances are identified from aggregated power signals using the Kalman filtering method in the factorial hidden Markov model (FHMM). Thereafter, the identified states are confirmed by the verification of system states, which are the combination of the working states of individual appliances. The verification step involves comparing the total measured power consumption with the total estimated power consumption. The use of transient features can achieve fast state inference and it is suitable for online load disaggregation. The proposed method was tested on a high-resolution data set such as Labeled hIgh-Frequency daTaset for Electricity Disaggregation (LIFTED) and it outperformed other related methods in the literature.
Key words： nonintrusive load monitoring (NILM)    load disaggregation    online load disaggregation    Kalman filtering    factorial hidden Markov model (FHMM)    Labeled hIgh-Frequency daTaset for Electricity Disaggregation (LIFTED)
收稿日期: 2021-01-28      出版日期: 2022-03-30
Corresponding Author(s): Zuyi LI   
 引用本文:   
. [J]. Frontiers in Energy, 2022, 16(1): 130-143.
Lei YAN, Runnan XU, Mehrdad SHEIKHOLESLAMI, Yang LI, Zuyi LI. State identification of home appliance with transient features in residential buildings. Front. Energy, 2022, 16(1): 130-143.
 链接本文:  
https://academic.hep.com.cn/fie/CN/10.1007/s11708-022-0822-z
https://academic.hep.com.cn/fie/CN/Y2022/V16/I1/130
Fig.1  
Fig.2  
Fig.3  
Fig.4  
Fig.5  
Fig.6  
Fig.7  
Appliance Kettle Vacuum Steamer Mixer Dryer
Index 1 2 3 4 5
Total state 2 2 4 2 3
Current state 1 0 1 1 2
Tab.1  
Fig.8  
Fig.9  
Fig.10  
Fig.11  
Fig.12  
Fig.13  
Appliance FHMM-KF FHMM-KFNT FHMM-KFNS SIQCP
Kettle 0.99 0.76 0.91 0.79
Vacuum 0.99 1.19 0.99 1.18
Steamer 0.99 0.99 1.16 1.02
Hair dryer 0.98 1.00 1.02 1.08
Refrigerator 0.97 1.00 1.21 1.00
Washing machine 1.01 1.00 1.06 1.02
Toaster 0.99 0.99 0.99 1.06
Hotpot 0.99 1.00 1.08 1.11
Mixer 0.96 0.83 0.96 0.76
Blender 0.99 0.92 0.87 0.88
Tab.2  
Fig.14  
Fig.15  
Fig.16  
Appliance FHMM-KF CO FHMM_EXACT
Kettle 90.4 367.9 478.8
Vacuum 8.6 0.2 0.2
Steamer 3.2 59.3 0.2
Hair dryer 7.4 323.1 0.2
Refrigerator 12.1 65.1 26.6
Washing machine 24.4 77.3 33.4
Toaster 4.2 0.2 60.9
Hotpot 6.1 103.8 475.3
Mixer 0.96 13.3 14.7
Blender 2.3 28.8 36.5
Average/W 15.9 103.9 112.7
Tab.3  
Appliance Accuracy f1-score
FHMM-KF FHMM-KFNT FHMM-KF FHMM-KFNT
Kettle 99.98% 64.01% 99.98% 63.24%
Vacuum 99.99% 61.71% 99.74% 59.08%
Steamer 99.97% 94.17% 99.98% 99.98%
Hair dryer 99.87% 94.85% 99.07% 89.57%
Refrigerator 99.51% 92.31% 99.57% 97.60%
Washing machine 99.56% 91.59% 99.41% 89.81%
Toaster 99.98% 94.79% 99.90% 99.90%
Hotpot 99.99% 93.48% 99.98% 90.16%
Mixer 99.92% 85.50% 99.35% 67.67%
Blender 99.97% 93.52% 99.73% 76.73%
  
Appliance Accuracy f1-score
FHMM-KF FHMM-KFNS FHMM-KF FHMM-KFNS
Kettle 99.98% 95.39% 99.98% 95.38%
Vacuum 99.99% 96.30% 99.74% 96.04%
Steamer 99.97% 97.11% 99.98% 97.08%
Hair dryer 99.87% 96.82% 99.07% 87.41%
Refrigerator 99.51% 70.52% 99.57% 72.79%
Washing machine 99.56% 96.51% 99.41% 94.64%
Toaster 99.98% 97.40% 99.90% 97.30%
Hotpot 99.99% 98.11% 99.98% 98.08%
Mixer 99.92% 95.16% 99.35% 94.45%
Blender 99.97% 97.87% 99.73% 96.63%
  
Appliance Accuracy f1-score
FHMM-KF SIQCP FHMM-KF SIQCP
Kettle 99.98% 59.41% 99.98% 61.17%
Vacuum 99.99% 58.00% 99.74% 58.46%
Steamer 99.97% 91.27% 99.98% 99.95%
Hair dryer 99.87% 93.05% 99.07% 88.41%
Refrigerator 99.51% 89.81% 99.57% 96.62%
Washing machine 99.56% 88.79% 99.41% 89.92%
Toaster 99.98% 92.19% 99.90% 99.55%
Hotpot 99.99% 91.58% 99.98% 90.21%
Mixer 99.92% 72.14% 99.35% 64.51%
Blender 99.97% 75.81% 99.73% 77.49%
  
1 S Ghosh, A Chatterjee, D Chatterjee. Improved non-intrusive identification technique of electrical appliances for a smart residential system. IET Generation, Transmission & Distribution, 2019, 13( 5): 695– 702
https://doi.org/10.1049/iet-gtd.2018.5475
2 F Luo, G Ranzi, W Kong. et al.. Nonintrusive energy saving appliance recommender system for smart grid residential users. IET Generation, Transmission & Distribution, 2017, 11( 7): 1786– 1793
https://doi.org/10.1049/iet-gtd.2016.1615
3 K Carrie Armel, A Gupta, G Shrimali. et al.. Is disaggregation the holy grail of energy efficiency? The case of electricity. Energy Policy, 2013, 52 : 213– 234
https://doi.org/10.1016/j.enpol.2012.08.062
4 G W Hart. Nonintrusive appliance load monitoring. Proceedings of the IEEE, 1992, 80( 12): 1870– 1891
https://doi.org/10.1109/5.192069
5 W Kong, Z Y Dong, J Ma. et al.. An extensible approach for non-intrusive load disaggregation with smart meter data. IEEE Transactions on Smart Grid, 2018, 9( 4): 3362– 3372
https://doi.org/10.1109/TSG.2016.2631238
6 Z Guo, Z J Wang, A Kashani. Home appliance load modeling from aggregated smart meter data. IEEE Transactions on Power Systems, 2015, 30( 1): 254– 262
https://doi.org/10.1109/TPWRS.2014.2327041
7 S Makonin, F Popowich, I V Bajić. et al.. Exploiting HMM sparsity to perform online real-time nonintrusive load monitoring. IEEE Transactions on Smart Grid, 2016, 7( 6): 2575– 2585
https://doi.org/10.1109/TSG.2015.2494592
8 N Sadeghianpourhamami, J Ruyssinck, D Deschrijver. et al.. Comprehensive feature selection for appliance classification in NILM. Energy and Building, 2017, 151 : 98– 106
https://doi.org/10.1016/j.enbuild.2017.06.042
9 S Pulipaka, A Ramesh, R Kumar. et al.. Non-intrusive real-time monitoring of PV generation at inverters using Internet of photovoltaics. Electronics Letters, 2017, 53( 16): 1137– 1138
https://doi.org/10.1049/el.2017.0694
10 R Brito, M C Wong, H C ZhangInstantaneous active and reactive load signature applied in non-intrusive load monitoring systems. IET Smart Grid, 2021, 4(1): 121–133
11 L Yan, J Han, Z LiAn online transient-based electrical appliance state tracking method via Markov chain Monte Carlo sampling. In: 2020 IEEE Power and Energy Society General Meeting (PESGM), Montreal, Canada, 2020
12 J Kelly, W. KnottenbeltNeural NILM: deep neural networks applied to energy disaggregation. In: Proceedings of the 2nd ACM International Conference on Embedded Systems for Energy-efficient Built Environments, Seoul, South Korea, 2015
13 M Kaselimi, N Doulamis, A DoulamisBayesian-optimized bidirectional LSTM regression model for non-intrusive load monitoring. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, UK, 2019
14 M Zeifman, K. Roth Viterbi algorithm with sparse transitions (VAST) for nonintrusive load monitoring. In: 2011 IEEE Symposium on Computational Intelligence Applications in Smart Grid (CIASG), Paris, France, 2011
15 F Gustafsson. Particle filter theory and practice with positioning applications. IEEE Aerospace and Electronic Systems Magazine, 2010, 25( 7): 53– 82
https://doi.org/10.1109/MAES.2010.5546308
16 V Breschi, D Piga, A Bemporad. Kalman filtering for energy disaggregation. IFAC-PapersOnLine, 2018, 51( 5): 108– 113
https://doi.org/10.1016/j.ifacol.2018.06.219
17 X Wu, X Han, K X Liang. Event-based non-intrusive load identification algorithm for residential loads combined with underdetermined decomposition and characteristic filtering. IET Generation, Transmission & Distribution, 2019, 13( 1): 99– 107
https://doi.org/10.1049/iet-gtd.2018.6125
18 M Lu, Z Li. A hybrid event detection approach for non-intrusive load monitoring. IEEE Transactions on Smart Grid, 2020, 11( 1): 528– 540
https://doi.org/10.1109/TSG.2019.2924862
19 Z Li, K Luo. Research on adaptive parameters determination in DBSCAN algorithm. Computer Engineering and Applications, 2016, 52( 3): 70– 73
20 K Krishna, Murty M. Genetic K-means algorithm Narasimha. IEEE Transactions on Systems, Man, and Cybernetics. Part B, Cybernetics, 1999, 29( 3): 433– 439
https://doi.org/10.1109/3477.764879
21 Y H Lin, M S Tsai, C S. ChenApplications of fuzzy classification with fuzzy c-means clustering and optimization strategies for load identification in NILM systems. In: 2011 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2011), Taipei, China, 2011
22 A Sharma, A. SharmaKNN-DBSCAN: Using k-nearest neighbor information for parameter-free density based clustering. In: 2017 International Conference on Intelligent Computing, Instrumentation and Control Technologies (ICICICT), Kerala, India, 2017
23 L Yan, J Han, Z LiLIFTED: household appliance-level load dataset and data compression with lossless coding considering precision. In: 2020 IEEE Power and Energy Society General Meeting (PESGM), Montreal, Canada, 2020
24 N Batra, J Kelly, O ParsonNILMTK: an open-source toolkit for non-intrusive load monitoring. In: Proceedings of the 5th International Conference on Future Energy Systems, Cambridge, UK, 2014
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed