Research PaperNo Access

An Improved TCN Considering Data Augmentation in Enabling Load Classification

Ding Han

Economic Research Institute, State Grid Henan Electric Power Company, Zhengzhou 450052, P. R. China

Search for more papers by this author

Hongkun Bai

Economic Research Institute, State Grid Henan Electric Power Company, Zhengzhou 450052, P. R. China

Search for more papers by this author

Yuanyuan Wang

Economic Research Institute, State Grid Henan Electric Power Company, Zhengzhou 450052, P. R. China

Search for more papers by this author

Shiqian Wang

Economic Research Institute, State Grid Henan Electric Power Company, Zhengzhou 450052, P. R. China

Search for more papers by this author

Jie Zhang

College of Electrical Engineering, Sichuan University, Chengdu 610065, P. R. China

Search for more papers by this author

, and

Yang Liu

https://orcid.org/0000-0002-7935-7146

College of Electrical Engineering, Sichuan University, Chengdu 610065, P. R. China

E-mail Address: yang.liu@scu.edu.cn

Corresponding author.

Search for more papers by this author

https://doi.org/10.1142/S021812662250284XCited by:4 (Source: Crossref)

Abstract

In modern power system, along with the developments of the data collecting technologies, the intensive and high-dimensional load data collection can be achieved. Therefore, to deeply reveal the patterns and behaviors hidden in the load dataset using load classification is of great significance for improving the service quality and the user experience of the power system. However, inevitable issues, for example the data missing and class imbalance are frequently reported in the present load dataset, which deteriorates the performance of the classification algorithms. Also, due to the special features, for example the time series, periodicity, and fluctuation of the load data, the traditional data classification algorithms also encounter performance defects. Therefore, this paper presents a data augmentation based enhanced temporal convolutional network (TCN) algorithm in enabling load classification. In the data augmentation phase, first an LRTC-TSVD algorithm is presented to implement the missing data completion. Second, a WGAN based class balancing approach is further presented to solve the class imbalance issue. Then, in the enhanced TCN phase, a WeightNorm, exponential linear unit (ELU) activation function, residual connection, and bidirectional feature fusion techniques based improved TCN (ITCN) algorithm is presented to carry out the accurate load data classification. Combining the data augmentation and the enhanced TCN phases, the ITCN algorithm is finally conducted. Based on the benchmark load datasets, the performances of the presented ITCN are evaluated. The experimental results report that the presented data augmentations can improve the quality of the dataset, moreover the classification algorithm is able to achieve the satisfied classification accuracy.

This paper was recommended by Regional Editor Tongquan Wei.

Keywords:

References

1. K. Zhou, S. Yang and Z. Shao , Energy internet: The business perspective, Appl. Energy 178 (2016) 212–222. Crossref, Web of Science, Google Scholar
2. T. Zhu, Q. Ai and X. He , An overview of data-driven electricity consumption behavior analysis method and application, Power Syst. Technol. 44 (2020) 3497–3507. Google Scholar
3. F. Fahiman, S. M. Erfani, S. Rajasegarar, M. Palaniswami and C. Leckie , Improving load forecasting based on deep learning and K-shape clustering, 2017 Int. Joint Conf. Neural Networks (IJCNN), Anchorage, USA, 14–19 May 2017, pp. 4134–4141. Google Scholar
4. L. Sun, K. Zhou and S. Yang , An ensemble clustering based framework for household load profiling and driven factors identification, Sust. Cities Soc. 53 (2020) 101958. Crossref, Web of Science, Google Scholar
5. Z. Zheng, Y. Yang, X. Niu, H. Dai and Y. Zhou , Wide and deep convolutional neural networks for electricity-theft detection to secure smart grids, IEEE Trans. Ind. Inf. 14 (2017) 1606–1615. Crossref, Web of Science, Google Scholar
6. Y. Liu, Y. Liu and L. Xu , A high performance extraction method for massive user load typical characteristics considering data class imbalance, Proc. CSEE 19 (2019) 4093–4104. Google Scholar
7. Y. Liu, X. Li and X. Chen , High-performance machine learning for large-scale data classification considering class imbalance, Sci. Program. 2020 (2020) 1953461. Web of Science, Google Scholar
8. T. Xu, H. Chiang, G. Liu and C. Tan , Hierarchical K-means method for clustering large-scale advanced metering infrastructure data, IEEE Trans. Power Deliv. 32 (2017) 609–616. Crossref, Web of Science, Google Scholar
9. R. Sun, X. Xiao, F. Zhou and Y. Zhou , Research of power user load classification method based on k-means and FSVM, 2019 IEEE 3rd Information Technology, Networking, Electronic and Automation Control Conf. (ITNEC), Chengdu, China, 15–17 March 2019, pp. 2138–2142. Google Scholar
10. M. Modenesi, A. Evsukoff and M. Costa , A load balancing knapsack algorithm for parallel fuzzy c-means cluster analysis, in High Performance Computing for Computational Science-VECPAR 2008 (Springer, Berlin, 2008). Crossref, Google Scholar
11. S. Lin, X. Gu and J. Tang , Power load profile classification method based on neural network of sparse automatic encoder, Power Syst. Technol. 44 (2020) 3508–3515. Google Scholar
12. J. Kim and B. Lee , Appliance classification by power signal analysis based on multi-feature combination multi-layer LSTM, Energies 12 (2019) 1–24. Crossref, Web of Science, Google Scholar
13. Y. Liu, L. Gao and L. Liu , Parallel load type identification algorithm considering sample class imbalance, Power Syst. Technol. 44 (2020) 4310–4317. Google Scholar
14. W. Peng, J. Wang and S. Yin , Short-term load forecasting model based on attention-LSTM in electricity market, Power Syst. Technol. 43 (2019) 1745–1751. Google Scholar
15. D. Yang, X. Gao, L. Kong, Y. Pang and B. Zhou , An event-driven convolutional neural architecture for non-intrusive load monitoring of residential appliance, IEEE Trans. Consum. Electron. 66 (2020) 173–182. Crossref, Web of Science, Google Scholar
16. Z. Deng, B. Wang, Y. Xu, T. Xu, C. Liu and Z. Zhu , Multi-scale convolutional neural network with time-cognition for multi-step short-term load forecasting, IEEE Access 7 (2019) 88058–88071. Crossref, Web of Science, Google Scholar
17. C. Lea, M. D. Flynn, R. Vidal, A. Reiter and G. D. Hager , Temporal convolutional networks for action segmentation and detection, 2017 IEEE Conf. Computer Vision and Pattern Recognition (CVPR), Honolulu, USA, 21–26 July 2017, pp. 1003–1012. Google Scholar
18. G. Tutz and S. Ramzan , Improved methods for the imputation of missing data by nearest neighbor methods, Comput. Stat. Data Anal. 90 (2015) 87–99. Crossref, Web of Science, Google Scholar
19. S. Wang, H. Chen and Z. Pan , A reconstruction method for missing data in power system measurement using an improved generative adversarial network, Proc. CSEE 39 (2019) 56–64. Google Scholar
20. X. Zhou, C. Yang, H. Zhao and W. Yu , Low-rank modeling and its applications in image analysis, ACM Comput. Surv. 47 (2014) 1–33. Crossref, Web of Science, Google Scholar
21. L. Cai, J. Gu and Z. Jin , Low rank matrix completion for recovering missing load data in power system, 2018 IEEE Power & Energy Society General Meeting (PESGM), Portland, USA, 5–10 August 2018, pp. 1–5. Google Scholar
22. A. Ghasemkhani, I. Niazazari, Y. Liu, H. Livani, V. A. Centeno and L. Yang , A regularized tensor completion approach for PMU data recovery, IEEE Trans. Smart Grid 12 (2021) 1519–1528. Crossref, Web of Science, Google Scholar
23. Y. Deng, L. Wang, H. Jia, X. Tong and F. Li , A sequence-to-sequence deep learning architecture based on bidirectional GRU for type recognition and time location of combined power quality disturbance, IEEE Trans. Ind. Inf. 15 (2019) 4481–4493. Crossref, Web of Science, Google Scholar
24. Z. Wang, H. Li, Z. Tang and Y. Liu , User-level ultra-short-term load forecasting model based on optimal feature selection and Bahdanau attention mechanism, J. Circuits, Syst. Comput. 30 (2021) 2150279. Link, Web of Science, Google Scholar
25. S. Luo, Y. Rao, J. Chen, H. Wang and Z. Wang , Short-term load forecasting model of distribution transformer based on CNN and LSTM, 2020 IEEE Int. Conf. High Voltage Engineering and Application (ICHVE), Beijing, China, 6–10 September 2020, pp. 1–4. Google Scholar
26. H. Rafiq, X. Shi, H. Zhang, H. Li, M. K. Ochani and A. A. Shah , Generalizability improvement of deep learning-based non-intrusive load monitoring system using data augmentation, IEEE Trans. Smart Grid 12 (2021) 3265–3277. Crossref, Web of Science, Google Scholar
27. L. Oudre, J. Jakubowicz, P. Bianchi and C. Simon , Classification of periodic activities using the Wasserstein distance, IEEE Trans. Biomed. Eng. 59 (2012) 1610–1619. Crossref, Web of Science, Google Scholar
28. PowerCons dataset and ItalyPowerDemand dataset: https://www.cs.ucr.edu/ $\sim$ eamonn/time_series_data_2018/. Google Scholar
29. ElectricityLoadDiagrams dataset: http://archive.ics.uci.edu/ml/datasets/ElectricityLoadDiagrams20112014. Google Scholar
30. Y. Yu, J. J. Q. Yu, V. O. K. Li and J. C. K. Lam , A novel interpolation-SVT approach for recovering missing low-rank air quality data, IEEE Access 8 (2020) 74291–74305. Crossref, Web of Science, Google Scholar
31. V. López et al., An insight into classification with imbalanced data: Empirical results and current trends on using data intrinsic characteristics, Inf. Sci. 250 (2013) 113–141. Crossref, Web of Science, Google Scholar
32. L. Wu, X. Chen, Y. Yang and Y. Liu , Feature-driven economic improvement for network-constrained unit commitment: A closed-loop predict-and-optimize framework, IEEE Trans. Power Syst. (2021). https://doi.org/10.1109/TPWRS.2021.3128485. Web of Science, Google Scholar
33. W. Jiang et al., Energy-aware design of stochastic applications with statistical deadline and reliability guarantees, IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst. 38 (2019) 1413–1426. Crossref, Web of Science, Google Scholar
34. H. Qin, H. Zhou and J. Cao , Imbalanced learning algorithm based intelligent abnormal electricity consumption detection, Neurocomputing 402 (2020) 112–123. Crossref, Web of Science, Google Scholar
35. W. Jiang, Z. Song, J. Zhan, D. Liu and J. Wan , Layer-wise security protection for deep neural networks in industrial cyber physical systems, IEEE Transactions on Industrial Informatics, Early Access, https://doi.org/10.1109/TII.2022.3155112. Google Scholar