Nontechnical Loss Detection using Neural Architecture Search and Outlier Detection

Ke Fei; Qi Li; Can Cui; Xue chen; Xinxin Xu; Benshan Xue; Weifeng Cai

doi:10.1051/e3sconf/202125601025

All issues

Volume 256 (2021)

E3S Web Conf., 256 (2021) 01025

References

Open Access

Issue		E3S Web Conf. Volume 256, 2021 2021 International Conference on Power System and Energy Internet (PoSEI2021)


Article Number		01025
Number of page(s)		5
Section		Smart Grid Technology and Power System Regulation Modeling
DOI		https://doi.org/10.1051/e3sconf/202125601025
Published online		10 May 2021

96 Billion is Lost Every Year to Electricity Theft. Accessed: May 8, 2017. [Online]. Available at: https://www.prnewswire.com/newsreleases/96-billion-is-lost-every-year to-electricity-theft-300453411.html [Google Scholar]
Chen Z, Meng D, Zhang Y, et al. Electricity Theft Detection Using Deep Bidirectional Recurrent Neural Network[C]//2020 22nd International Conference on Advanced Communication Technology (ICACT). IEEE, 2020: 401-406. [Google Scholar]
Salman Saeed M, Mustafa M W, Sheikh U U, et al. An efficient boosted C5. 0 Decision-Tree-Based classification approach for detecting non-technical losses in power utilities[J]. Energies, 2020, 13(12): 3242. [Google Scholar]
Nizar A H, Dong Z Y, Wang Y. Power utility nontechnical loss analysis with extreme learning machine method[J]. IEEE Transactions on Power Systems, 2008, 23(3): 946–955. [Google Scholar]
Tacón J, Melgarejo D, Rodríguez F, et al. Semisupervised approach to non technical losses detection[C]//Iberoamerican Congress on Pattern Recognition. Springer, Cham, 2014: 698-705. [Google Scholar]
Punmiya, R., & Choe, S. (2019). Energy theft detection using gradient boosting theft detector with feature engineering-based preprocessing. IEEE Transactions on Smart Grid [PubMed] [Google Scholar]
Spirić J V, Stanković S S, Dočić M B. Identification of suspicious electricity customers[J]. International Journal of Electrical Power & Energy Systems, 2018, 95: 635-643. [Google Scholar]
Viegas J L, Esteves P R, Vieira S M. Clustering-based novelty detection for identification of non-technical losses[J]. International Journal of Electrical Power & Energy Systems, 2018, 101: 301-310. [Google Scholar]
Krishna V B, Weaver G A, Sanders W H. PCA-based method for detecting integrity attacks on advanced metering infrastructure[C]//International Conference on Quantitative Evaluation of Systems. Springer, Cham, 2015: 70-85. [Google Scholar]
Ramos C C O, de Sousa A N, Papa J P, et al. A new approach for nontechnical losses detection based on optimum-path forest[J]. IEEE Transactions on Power Systems, 2010, 26(1): 181–189. [Google Scholar]
ISSDA. Data from the Commission for Energy Regulation – <http://www.ucd.ie/issda>. [Google Scholar]
Jin, H., Song, Q., & Hu, X. (2019). Auto-Keras: An Efficient Neural Architecture Search System. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. [Google Scholar]
Vincent P, Larochelle H, Bengio Y, et al. Extracting and composing robust features with denoising autoencoders[C]//Proceedings of the 25th international conference on Machine learning. 2008: 1096-1103. [Google Scholar]
Hoffmann H. Kernel PCA for novelty detection[J]. Pattern recognition, 2007, 40(3): 863–874. [Google Scholar]
He, Z., Xu, X. and Deng, S., 2003. Discovering cluster-based local outliers. Pattern Recognition Letters, 24(9-10), pp.1641-1650. [CrossRef] [Google Scholar]
Goldstein, M. and Dengel, A., 2012. Histogram-based outlier score (hbos): A fast unsupervised anomaly detection algorithm. In KI-2012: Poster and Demo Track, pp.59-63. [Google Scholar]
Kriegel, H.P. and Zimek, A., 2008, August. Angle-based outlier detection in high-dimensional data. In KDD ‘08, pp. 444-452. ACM. [Google Scholar]
Liu, F.T., Ting, K.M. and Zhou, Z.H., 2008, December. Isolation forest. In International Conference on Data Mining, pp. 413-422. IEEE. [Google Scholar]

Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.

Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.

Initial download of the metrics may take a while.

[1] 96 Billion is Lost Every Year to Electricity Theft. Accessed: May 8, 2017. [Online]. Available at: https://www.prnewswire.com/newsreleases/96-billion-is-lost-every-year to-electricity-theft-300453411.html [Google Scholar]

[2] Chen Z, Meng D, Zhang Y, et al. Electricity Theft Detection Using Deep Bidirectional Recurrent Neural Network[C]//2020 22nd International Conference on Advanced Communication Technology (ICACT). IEEE, 2020: 401-406. [Google Scholar]

[3] Salman Saeed M, Mustafa M W, Sheikh U U, et al. An efficient boosted C5. 0 Decision-Tree-Based classification approach for detecting non-technical losses in power utilities[J]. Energies, 2020, 13(12): 3242. [Google Scholar]

[4] Nizar A H, Dong Z Y, Wang Y. Power utility nontechnical loss analysis with extreme learning machine method[J]. IEEE Transactions on Power Systems, 2008, 23(3): 946–955. [Google Scholar]

[5] Tacón J, Melgarejo D, Rodríguez F, et al. Semisupervised approach to non technical losses detection[C]//Iberoamerican Congress on Pattern Recognition. Springer, Cham, 2014: 698-705. [Google Scholar]

[6] Punmiya, R., & Choe, S. (2019). Energy theft detection using gradient boosting theft detector with feature engineering-based preprocessing. IEEE Transactions on Smart Grid [PubMed] [Google Scholar]

[7] Spirić J V, Stanković S S, Dočić M B. Identification of suspicious electricity customers[J]. International Journal of Electrical Power & Energy Systems, 2018, 95: 635-643. [Google Scholar]

[8] Viegas J L, Esteves P R, Vieira S M. Clustering-based novelty detection for identification of non-technical losses[J]. International Journal of Electrical Power & Energy Systems, 2018, 101: 301-310. [Google Scholar]

[9] Krishna V B, Weaver G A, Sanders W H. PCA-based method for detecting integrity attacks on advanced metering infrastructure[C]//International Conference on Quantitative Evaluation of Systems. Springer, Cham, 2015: 70-85. [Google Scholar]

[10] Ramos C C O, de Sousa A N, Papa J P, et al. A new approach for nontechnical losses detection based on optimum-path forest[J]. IEEE Transactions on Power Systems, 2010, 26(1): 181–189. [Google Scholar]

[11] ISSDA. Data from the Commission for Energy Regulation – <http://www.ucd.ie/issda>. [Google Scholar]

[12] Jin, H., Song, Q., & Hu, X. (2019). Auto-Keras: An Efficient Neural Architecture Search System. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. [Google Scholar]

[13] Vincent P, Larochelle H, Bengio Y, et al. Extracting and composing robust features with denoising autoencoders[C]//Proceedings of the 25th international conference on Machine learning. 2008: 1096-1103. [Google Scholar]

[14] Hoffmann H. Kernel PCA for novelty detection[J]. Pattern recognition, 2007, 40(3): 863–874. [Google Scholar]

[15] He, Z., Xu, X. and Deng, S., 2003. Discovering cluster-based local outliers. Pattern Recognition Letters, 24(9-10), pp.1641-1650. [CrossRef] [Google Scholar]

[16] Goldstein, M. and Dengel, A., 2012. Histogram-based outlier score (hbos): A fast unsupervised anomaly detection algorithm. In KI-2012: Poster and Demo Track, pp.59-63. [Google Scholar]

[17] Kriegel, H.P. and Zimek, A., 2008, August. Angle-based outlier detection in high-dimensional data. In KDD ‘08, pp. 444-452. ACM. [Google Scholar]

[18] Liu, F.T., Ting, K.M. and Zhou, Z.H., 2008, December. Isolation forest. In International Conference on Data Mining, pp. 413-422. IEEE. [Google Scholar]