Skip to content
2000
Volume 18, Issue 4
  • ISSN: 2212-7976
  • E-ISSN: 1874-477X

Abstract

Background

The electricity demand is continuously increasing. However, various institutions, enterprises, and individuals exhibit many irregularities in their electricity usage, leading to significant wastage of electricity. To achieve effective energy management, researchers are attempting to analyze and regulate users' electricity demands by monitoring their load usage through Non-Intrusive Load Monitoring (NILM) technology. The accuracy of load identification in this technology will greatly impact the results of load monitoring. Although there are currently many articles and patents related to NILM, they utilize a large amount of computational resources and require high sampling rates from devices, yet the results are still unsatisfactory. Therefore, it is necessary to improve the accuracy of load identification in data with relatively low sampling frequencies.

Objective

To improve the accuracy of load identification with low sampling frequency data, this paper proposes a typical scenario load identification method based on feature fusion and transfer learning.

Methods

This method adopts the fusion of current and power factor angles to provide abundant identification information for NILM, effectively reducing the situation of single-feature overlap of different loads. By inputting the fused feature data into GoogLeNet and utilizing transfer learning for training, not only is the accuracy improved, but also the training time and the requirement for the sampling rate of training data are greatly reduced. In addition, selecting typical scenario loads can monitor loads in a targeted manner, reduce the waste of computing resources caused by irrelevant loads, and more effectively guide electricity usage strategies.

Results

The proposed load identification method was tested on the low sampling frequency dataset used in this paper. It achieved an overall load identification accuracy of 94.61% across three scenarios, improving accuracy by 3% to 7% compared to other models.

Conclusion

The simulation results indicate that this method achieves high load identification accuracy at low sampling frequencies. It also exhibits good generalization ability. This method not only reduces the performance requirements for monitoring equipment but also enhances monitoring efficiency.

© 2025 Bentham Science Publishers
Loading

Article metrics loading...

/content/journals/meng/10.2174/0122127976325514241001045948
2024-10-22
2025-12-15

  • From This Site

    /content/journals/meng/10.2174/0122127976325514241001045948
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. QuM. ZhangX. LuoX. YanX. LiZ. WangL. Energy consumption optimization for the cold source system of a hospital in shanghai - Part II: Operation control strategy using energyPlus.Recent Pat. Mech. Eng.202417429030310.2174/0122127976290446240228055313
     [Google Scholar]
  2. GyubaekK. SanghyunP. Pre-trained non-intrusive load monitoring model for recognizing activity of daily living.Appl. Intell.2022539109371095510.1007/s10489‑022‑04053‑7
     [Google Scholar]
  3. BuddhahaiB. WongsereeW. RakkwamsukP. An energy prediction approach for a nonintrusive load monitoring in home appliances.IEEE Trans. Consum. Electron.20206619610510.1109/TCE.2019.2956638
     [Google Scholar]
  4. FengR. YuanW. GeL. JiS. Nonintrusive load disaggregation for residential users based on alternating optimization and downsampling.IEEE Trans. Instrum. Meas.20217011210.1109/TIM.2021.3117068
     [Google Scholar]
  5. GopinathR. KumarM. DeepEdge-NILM: A case study of non-intrusive load monitoring edge device in commercial building.Energy Build.202329411322610.1016/j.enbuild.2023.113226
     [Google Scholar]
  6. LiuY. LiuW. ShenY. ZhaoX. GaoS. Toward smart energy user: Real time non-intrusive load monitoring with simultaneous switching operations.Appl. Energy202128711661610.1016/j.apenergy.2021.116616
     [Google Scholar]
  7. HartG.W. Nonintrusive appliance load monitoring.Proc. IEEE199280121870189110.1109/5.192069
     [Google Scholar]
  8. AngelisG.F. TimplalexisC. KrinidisS. IoannidisD. TzovarasD. NILM applications: Literature review of learning approaches, recent developments and challenges.Energy Build.202226111195110.1016/j.enbuild.2022.111951
     [Google Scholar]
  9. LinY.H. Trainingless multi-objective evolutionary computing-based nonintrusive load monitoring: Part of smart-home energy management for demand-side management.J. Build. Eng.20213310160110.1016/j.jobe.2020.101601
     [Google Scholar]
  10. BouhourasA.S. GkaidatzisP.A. PanagiotouE. PoulakisN. ChristoforidisG.C. A NILM algorithm with enhanced disaggregation scheme under harmonic current vectors.Energy Build.201918339240710.1016/j.enbuild.2018.11.013
     [Google Scholar]
  11. GhoshS. ChatterjeeA. ChatterjeeD. An improved load feature extraction technique for smart Homes using fuzzy-based NILM.IEEE Trans. Instrum. Meas.2021701910.1109/TIM.2021.3095093
     [Google Scholar]
  12. AlcaláJ. UreñaJ. HernándezA. GualdaD. Event-based energy disaggregation algorithm for activity monitoring from a single-point sensor.IEEE Trans. Instrum. Meas.201766102615262610.1109/TIM.2017.2700987
     [Google Scholar]
  13. RafiqH. ManandharP. Rodriguez-UbinasE. AhmedQ.O. PalpanasT. A review of current methods and challenges of advanced deep learning-based non-intrusive load monitoring (NILM) in residential context.Energy Build.202430511389010.1016/j.enbuild.2024.113890
     [Google Scholar]
  14. XiaoZ. GangW. YuanJ. ZhangY. FanC. Cooling load disaggregation using a NILM method based on random forest for smart buildings.Sustain Cities Soc.20217410320210.1016/j.scs.2021.103202
     [Google Scholar]
  15. NolascoL.S. LazzarettiA.E. MulinariB.M. DeepDFML-NILM: A new CNN-based architecture for detection, feature extraction and multi-label classification in NILM signals.IEEE Sens. J.202222150150910.1109/JSEN.2021.3127322
     [Google Scholar]
  16. ZhouZ. XiangY. XuH. YiZ. ShiD. WangZ. A novel transfer learning-based intelligent nonintrusive load-monitoring with limited measurements.IEEE Trans. Instrum. Meas.2021701810.1109/TIM.2020.3011335
     [Google Scholar]
  17. CiancettaF. BucciG. FiorucciE. MariS. FioravantiA. A new convolutional neural network-based system for NILM applications.IEEE Trans. Instrum. Meas.20217011210.1109/TIM.2020.3035193
     [Google Scholar]
  18. ChenH. YangX. ZhaoL. A non-intrusive load identification system based on deep neural networks and transfer learning.CN Patent 2023104987202023
  19. VermaS. SinghS. MajumdarA. Multi-label LSTM autoencoder for non-intrusive appliance load monitoring.Electr. Power Syst. Res.202119910741410.1016/j.epsr.2021.107414
     [Google Scholar]
  20. HwangH. KangS. Nonintrusive load monitoring using an LSTM with feedback structure.IEEE Trans. Instrum. Meas.20227111110.1109/TIM.2022.3169536
     [Google Scholar]
  21. KellyJ. KnottenbeltW. Neural NILM: Deep neural networks applied to energy disaggregation.2nd ACM International Conference on Embedded Systems for Energy-Efficient Built EnvironmentsSeoul, South Korea2015556410.1145/2821650.2821672
     [Google Scholar]
  22. KaselimiM. DoulamisN. VoulodimosA. ProtopapadakisE. DoulamisA. Context aware energy disaggregation using adaptive bidirectional LSTM models.IEEE Trans. Smart Grid20201143054306710.1109/TSG.2020.2974347
     [Google Scholar]
  23. LeCunY. BoserB. DenkerJ.S. Backpropagation applied to handwritten zip code recognition.Neural Comput.19891454155110.1162/neco.1989.1.4.541
     [Google Scholar]
  24. RafiqH. ShiX. ZhangH. LiH. OchaniM.K. A deep recurrent neural network for non-intrusive load monitoring based on multi-feature input space and post-processing.Energies2020139219510.3390/en13092195
     [Google Scholar]
  25. ChenT. QinH. LiX. WanW. YanW. A Non-intrusive load monitoring method based on feature fusion and SE-ResNet.Electronics (Basel)2023128190910.3390/electronics12081909
     [Google Scholar]
  26. ZhouX LiS LiuC ZhuH DongN XiaoT Non-intrusive load monitoring using a CNN-LSTM-RF model considering label correlation and class-imbalance.IEEE Access20219843061510.1109/ACCESS.2021.3087696
     [Google Scholar]
  27. LiK YinB DuZ SunY. A nonintrusive load identification model based on time-frequency features fusion.IEEE Access2021913768710.1109/ACCESS.2020.3047147
     [Google Scholar]
  28. WangA.L. ChenB.X. WangC.G. HuaD. Non-intrusive load monitoring algorithm based on features of V–I trajectory.Electr. Power Syst. Res.201815713414410.1016/j.epsr.2017.12.012
     [Google Scholar]
  29. LiuJ. LiuN. SongH. LiuX. SunX. ZhangD. Non-intrusive load identification model based on 3D spatial feature and convolutional neural network.Energy Power Eng.2021134304010.4236/epe.2021.134B004
     [Google Scholar]
  30. LiuY. WangX. YouW. Non-intrusive load monitoring by voltage-current trajectory enabled transfer learning.IEEE Trans. Smart Grid20191055609561910.1109/TSG.2018.2888581
     [Google Scholar]
  31. KyrkouL. NalmpantisC. VrakasD. Imaging time-series for NILM.Commun. Comput. Inf. Sci.2019100018819610.1007/978‑3‑030‑20257‑6_16
     [Google Scholar]
  32. TitoS.R. Image segmentation-based event detection for non-intrusive load monitoring using gramian angular summation field.IEEE Industrial Electronics and Applications ConferencePenang, Malaysia20211859010.1109/IEACon51066.2021.9654789
     [Google Scholar]
  33. SenarathnaM. HerathM. ThilakanayakeT.D. LiyanageM.H. AngammanaC.J. An image based approach of energy signal disaggregation using artificial intelligence.IEEE 16th International Conference on Industrial and Information Systems (ICIIS)Kandy, Sri Lanka. 2021; pp. 98-10310.1109/ICIIS53135.2021.9660638
     [Google Scholar]
  34. YinH. ZhouK. YangS. Non-intrusive load monitoring by load trajectory and multi-feature based on DCNN.IEEE Trans. Industr. Inform.20231910103881040010.1109/TII.2023.3240924
     [Google Scholar]
  35. BatraN. GulatiM. SinghA. SrivastavaM.B. It’s different: Insights into home energy consumption in India. In: Proceedings of the 5th ACM Workshop on Embedded Systems for Energy-Efficient Buildings (BuildSys ’13); 2013 Nov 11; New York: ACM; 2013p. 1–810.1145/2528282.2528293
     [Google Scholar]
  36. AMPds2: The Almanac of Minutely Power dataset (Version 2).Available from: https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/FIE0S4 2016
  37. KimJ.G. LeeB. Appliance classification by power signal analysis based on multi-feature combination multi-layer LSTM.Energies20191214280410.3390/en12142804
     [Google Scholar]
/content/journals/meng/10.2174/0122127976325514241001045948
Loading
Typical Scenario Load Identification Based on Feature Fusion and Transfer Learning
Recent Patents on Mechanical Engineering 18, 491 (2025); https://doi.org/10.2174/0122127976325514241001045948
/content/journals/meng/10.2174/0122127976325514241001045948
/content/journals/meng/10.2174/0122127976325514241001045948
Loading

Data & Media loading...


  • Article Type:     Research Article
Keyword(s): feature fusion; GoogLeNet; non-intrusive load monitoring (NILM); sampling frequencies; transfer learning; typical scenario

Most Cited Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error
Please enter a valid_number test