Non-Intrusive Load Disaggregation Based on a Multi-Scale Attention Residual Network
Source abstract
Abstract
Non-intrusive load disaggregation (NILD) is of great significance to the development of smart grids. Current energy disaggregation methods extract features from sequences, and this process easily leads to a loss of load features and difficulties in detecting, resulting in a low recognition rate of low-use electrical appliances. To solve this problem, a non-intrusive sequential energy disaggregation method based on a multi-scale attention residual network is proposed. Multi-scale convolutions are used to learn features, and the attention mechanism is used to enhance the learning ability of load features. The residual learning further improves the performance of the algorithm, avoids network degradation, and improves the precision of load decomposition. The experimental results on two benchmark datasets show that the proposed algorithm has more advantages than the existing algorithms in terms of load disaggregation accuracy and judgments of the on/off state, and the attention mechanism can further improve the disaggregation accuracy of low-frequency electrical appliances.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Smart Grid Energy Management · Smart Grid Security and Resilience · Microgrid Control and Optimization
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Jiangsu Collaborative Innovation Center on Atmospheric Environment and Equipment Technology, Nanjing University of Information Science and Technology, Nanjing 210044, China
College of Information Science and Technology, Nanjing Forestry University, Nanjing 210037, China
China Electric Power Research Institute, Nanjing 210003, China
Funding
State Grid Corporation of China Project
References (41)
Show source-provided references
1. Wong, Y.F., Şekercioğlu, Y.A., Drummond, T., and Wong, V.S. (2013, January 16–19). Recent approaches to non-intrusive load monitoring techniques in residential settings. Proceedings of the 2013 IEEE Computational Intelligence Applications in Smart Grid, Singapore.10.1109/CIASG.2013.6611501 ↗
2. General noise support vector regression with non-constant uncertainty intervals for solar radiation prediction10.1007/s40565-018-0397-1 ↗
3. An optimization strategy of controlled electric vehicle charging considering demand side response and regional wind and photovoltaic10.1007/s40565-015-0117-z ↗
4. A Comprehensive Electrical-Gas-Hydrogen Microgrid Model for Energy Management Applications
5. Nonintrusive appliance load monitoring10.1109/5.192069 ↗
6. Non-intrusive energy disaggregation using non-negative matrix factorization with sum-to-k constraint10.1109/TPWRS.2017.2660246 ↗
7. Non-intrusive load monitoring approaches for disaggregated energy sensing: A survey10.3390/s121216838 ↗
8. Particle-swarm-optimization-based nonintrusive demand monitoring and load identification in smart meters10.1109/TIA.2013.2258875 ↗
9. Development of an improved time–frequency analysis-based nonintrusive load monitor for load demand identification10.1109/TIM.2013.2289700 ↗
10. Sparse optimization for automated energy end use disaggregation10.1109/TCST.2015.2476777 ↗
11. Batra, N., Singh, A., and Whitehouse, K. (2015). Neighbourhood nilm: A big-data approach to household energy disaggregation. arXiv.
12. Modern development of an adaptive non-intrusive appliance load monitoring system in electricity energy conservation10.1016/j.apenergy.2011.11.027 ↗
13. Energy disaggregation via discriminative sparse coding
14. Bayesian nonparametric hidden semi-Markov models
15. Kim, H., Marwah, M., Arlitt, M., Lyon, G., and Han, J. (2011, January 28–30). Unsupervised disaggregation of low frequency power measurements. Proceedings of the 2011 SIAM International Conference on Data Mining, Society for Industrial and Applied Mathematics, Mesa, AZ, USA.10.1137/1.9781611972818.64 ↗
16. Current sensor based home appliance and state of appliance recognition10.9746/jcmsi.3.86 ↗
17. An empirical investigation of VI trajectory based load signatures for non-intrusive load monitoring10.1109/TSG.2013.2271282 ↗
18. Non-intrusive load disaggregation based on deep dilated residual network10.1016/j.epsr.2019.01.034 ↗
19. Multi-Stage Feature Constraints Learning for Age Estimation10.1109/TIFS.2020.2969552 ↗
20. Kuo, P.H., and Huang, C.J. (2018). A high precision artificial neural networks model for short-term energy load forecasting. Energies, 11.10.3390/en11010213 ↗
21. Kelly, J., and Knottenbelt, W. (2015, January 4–5). Neural nilm: Deep neural networks applied to energy disaggregation. Proceedings of the 2nd ACM International Conference on Embedded Systems for Energy-Efficient Built Environments, Seoul, Korea.10.1145/2821650.2821672 ↗
22. Zhang, C., Zhong, M., Wang, Z., Goddard, N., and Sutton, C. (2016). Sequence-to-point learning with neural networks for nonintrusive load monitoring. arXiv.
23. High-performance predictor for critical unstable generators based on scalable parallelized neural networks10.1007/s40565-016-0209-4 ↗
24. Semi-Supervised Multi-Label Deep Learning based Non-intrusive Load Monitoring in Smart Grids10.1109/TII.2019.2955470 ↗
25. Yadav, A., Sinha, A., Saidi, A., Trinkl, C., and Zörner, W. (2020, January 18). NILM based Energy Disaggregation Algorithm for Dairy Farms. Proceedings of the 5th International Workshop on Non-Intrusive Load Monitoring, Yokohama, Japan.10.1145/3427771.3427846 ↗
26. Faustine, A., Pereira, L., Bousbiat, H., and Kulkarni, S. (2020, January 18). UNet-NILM: A Deep Neural Network for Multi-tasks Appliances State Detection and Power Estimation in NILM. Proceedings of the 5th International Workshop on Non-Intrusive Load Monitoring, Yokohama, Japan.10.1145/3427771.3427859 ↗
27. Jin, Y., Guo, H., Wang, J., and Song, A. (2020). A Hybrid System Based on LSTM for Short-Term Power Load Forecasting. Energies, 13.10.3390/en13236241 ↗
28. Home appliance identification for NILM systems based on deep neural networks
29. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
30. Wang, F., Jiang, M., Qian, C., Yang, S., Li, C., Zhang, H., Wang, X., and Tang, X. (2017, January 21–26). Residual attention network for image classification. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.683 ↗
31. Hu, J., Shen, L., and Sun, G. (2018, January 18–22). Squeeze-and-excitation networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00745 ↗
32. Attention is all you need
33. Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. (2015, January 7–12). Going deeper with convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.10.1109/CVPR.2015.7298594 ↗
34. Lin, M., Chen, Q., and Yan, S. (2013). Network in network. arXiv.
35. Wang, B., Li, T., Huang, Y., Luo, H., Guo, D., and Horng, S.J. (2017, January 24–26). Diverse activation functions in deep learning. Proceedings of the 2017 12th International Conference on Intelligent Systems and Knowledge Engineering (ISKE), Nanjing, China.10.1109/ISKE.2017.8258768 ↗
36. Machine learning approaches for non-intrusive load monitoring: From qualitative to quantitative comparation10.1007/s10462-018-9613-7 ↗
37. Kelly, J., Batra, N., Parson, O., Dutta, H., Knottenbelt, W., Rogers, A., Singh, A., and Srivastava, M. (2014, January 4–6). Nilmtk v0.2: A non-intrusive load monitoring toolkit for large scale data sets: Demo abstract. Proceedings of the 1st ACM Conference on Embedded Systems for Energy-Efficient Buildings, Memphis, TN, USA.10.1145/2674061.2675024 ↗
38. Non-intrusive appliances load monitoring (nilm) for energy conservation in household with low sampling rate10.1016/j.procs.2016.05.049 ↗
39. Non-intrusive load disaggregation based on composite deep long short-term memory network10.1016/j.eswa.2020.113669 ↗
40. Krystalakos, O., Nalmpantis, C., and Vrakas, D. (2018, January 9–12). Sliding window approach for online energy disaggregation using artificial neural networks. Proceedings of the 10th Hellenic Conference on Artificial Intelligence, Patras, Greece.10.1145/3200947.3201011 ↗
41. Dilated multi-scale cascade forest for satellite image classification10.1080/01431161.2020.1763511 ↗