Anomaly detection in smart grid based on encoder-decoder framework with recurrent neural network

doi:10.1016/S1005-8885(17)60243-7

中国邮电高校学报(英文) ›› 2017, Vol. 24 ›› Issue (6): 67-73.doi: 10.1016/S1005-8885(17)60243-7

• Artificial Intelligence • 上一篇下一篇

Anomaly detection in smart grid based on encoder-decoder framework with recurrent neural network

Zheng Fengming, Li Shufang, Guo Zhimin, Wu Bo, Tian Shiming, Pan Mi

1. 北京邮电大学信息与通信工程学院
2. 北京邮电大学
3. 国网河南省电力公司电力科学研究院
4. 中国电力科学研究院

收稿日期:2017-04-28 修回日期:2017-09-28 出版日期:2017-12-30 发布日期:2017-12-01
通讯作者: 郑凤鸣 E-mail:zfm@bupt.edu.cn
基金资助:
Business Integration and Data Sharing Service Technology Based on Through Information of Operation and Distribution (2016 state Grid Technology Project).

Anomaly detection in smart grid based on encoder-decoder framework with recurrent neural network

Zheng Fengming, Li Shufang, Guo Zhimin, Wu Bo, Tian Shiming, Pan Mi

1. 北京邮电大学信息与通信工程学院 2. 北京邮电大学 3. 国网河南省电力公司电力科学研究院 4. 中国电力科学研究院

Received:2017-04-28 Revised:2017-09-28 Online:2017-12-30 Published:2017-12-01
Contact: Feng-Ming ZHENG E-mail:zfm@bupt.edu.cn
Supported by:
Business Integration and Data Sharing Service Technology Based on Through Information of Operation and Distribution (2016 state Grid Technology Project).

摘要/Abstract

摘要： Anomaly detection in smart grid is critical to enhance the reliability of power systems. Excessive manpower has to be involved in analyzing the measurement data collected from intelligent motoring devices while performance of anomaly detection is still not satisfactory. This is mainly because the inherent spatio-temporality and multi-dimensionality of the measurement data cannot be easily captured. In this paper, we propose an anomaly detection model based on encoder-decoder framework with recurrent neural network (RNN). In the model, an input time series is reconstructed and an anomaly can be detected by an unexpected high reconstruction error. Both Manhattan distance and the edit distance are used to evaluate the difference between an input time series and its reconstructed one. Finally, we validate the proposed model by using power demand data from University of California, Riverside (UCR) time series classification archive and IEEE 39 bus system simulation data. Results from the analysis demonstrate that the proposed encoder-decoder framework is able to successfully capture anomalies with a precision higher than 95%.

关键词: smart grid, encoder-decoder framework, anomaly detection, time series mining

Abstract: Anomaly detection in smart grid is critical to enhance the reliability of power systems. Excessive manpower has to be involved in analyzing the measurement data collected from intelligent motoring devices while performance of anomaly detection is still not satisfactory. This is mainly because the inherent spatio-temporality and multi-dimensionality of the measurement data cannot be easily captured. In this paper, we propose an anomaly detection model based on encoder-decoder framework with recurrent neural network (RNN). In the model, an input time series is reconstructed and an anomaly can be detected by an unexpected high reconstruction error. Both Manhattan distance and the edit distance are used to evaluate the difference between an input time series and its reconstructed one. Finally, we validate the proposed model by using power demand data from University of California, Riverside (UCR) time series classification archive and IEEE 39 bus system simulation data. Results from the analysis demonstrate that the proposed encoder-decoder framework is able to successfully capture anomalies with a precision higher than 95%.

Key words: smart grid, encoder-decoder framework, anomaly detection, time series mining

Zheng Fengming, Li Shufang, Guo Zhimin, Wu Bo, Tian Shiming, Pan Mi. Anomaly detection in smart grid based on encoder-decoder framework with recurrent neural network[J]. JOURNAL OF CHINA UNIVERSITIES OF POSTS AND TELECOM, 2017, 24(6): 67-73.

参考文献

1. Wu J, Xiong J J, Shil P, et al. Real time anomaly detection in wide area monitoring of smart grids. Proceedings of the 2014 IEEE/ACM International Conference on Computer-Aided Design (ICCAD’14), Nov 2-6, 2014, San Jose, CA, USA. Piscataway, NJ, USA: IEEE, 2014: 197-204

2. Answar A, Mahmood A N. Anomaly detection in electric network database of smart grid: graph matching approach. Electric Power Systems Research, 2016, 133: 51-62

3. Levorato M, Mitra U. Fast anomaly detection in smart grids via sparse approximation theory. Proceedings of the IEEE 7th Sensor Array and Multichannel Signal Processing Workshop (SAM’16), Jun 17-20, 2016, Hoboken, NJ, USA. Piscataway, NJ, USA: IEEE, 2016: 5-8

4. Ford V, Siraj A, Eberle W. Smart grid energy fraud detection using artificial neural networks. Proceedings of the 2014 IEEE Symposium on Computational Intelligence Applications in Smart Grid (CIASG’14), Dec 9-12, 2014, Orlando, FL, USA. Piscataway, NJ, USA: IEEE, 2014: 6p

5. Laptev N, Amizadeh S, Flint I. Generic and scalable framework for automated time-series anomaly detection. Proceedings of the 21st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD’15), Aug 10-13, 2015, Sydney, Australia. New York, NY, USA: ACM, 2015: 1939-1947

6. Manzoor E A, Milajerdi S M, Akoglu L. Fast memory-efficient anomaly detection in streaming heterogeneous graphs. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD’16), Aug 24-27, 2016, San Francisco, CA, USA. New York, NY, USA: ACM, 2016: 1035-1044

7. Golmohammadi K, Zaiane O R. Time series contextual anomaly detection for detecting market manipulation in stock market. Proceedings of the 2015 IEEE International Conference on Data Science and Advanced Analytics (DSAA’15), Oct 19-21, 2015, Paris, France. Piscataway, NJ, USA: IEEE, 2015: 10p

8. Hu W, Zhang W L, Min Y, et al. Real-time emergency control decision in power system based on support vector machines. Proceedings of the CSEE, 2017, 37(16): 4567-4576 (in Chinese)

9. Cho K, van Merriënboer B, Gulcehre C, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP’14), Oct 25-29, 2014, Doha, Qatar. 2014: 14p

10. Johnson R, Zhang T. Supervised and semi-supervised text categorization using LSTM for region embeddings. Proceedings of the 33rd International Conference on International Conference on Machine Learning (ICML’16), Jun 19-24, 2016, New York, NY, USA. New York, NY, USA: ACM, 2016: 526-534

11. Li J W, Luong M T, Jurafsky D. A hierarchical neural autoencoder for paragraphs and documents. Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing (ACL-IJCNLP’15), Jul 26-31, 2015, Beijing, China. 2015: 1106-1115

12. Yang Y H, Xia Y J, Ge F J, et al. A trend based similarity calculation approach for mining time series data. Proceedings of the International MultiConference of Engineers and Computer Scientists (IMECS’12): Vol 1, Mar 14-16, 2012, Hong Kong, China. 2012: 4p

13. Malhotra P, Ramakrishnan A, Anand G, et al. LSTM-based encoder-decoder for multi-sensor anomaly detection. Proceedings of the 33rd International Conference on Machine Learning (ICML’16) Workshop on Anomaly Detection, Jun 19-24, 2016, New York, NY, USA. 2016

14. Chen Y P, Keogh E, Hu B, et al. The UCR time series classification archive. Riverside, CA, USA: University of California, Riverside (UCR), 2015

15. Grainger J J, Stevenson W D. Power system analysis. New York, NY, USA: McGraw-Hill, 2003

16. Chauhan S, Vig L. Anomaly detection in ECG time signals via deep long short-term memory networks. Proceedings of the 2015 IEEE International Conference on Data Science and Advanced Analytics (DSAA’15), Oct 19-21, 2015, Paris, France. Piscataway, NJ, USA: IEEE, 2015: 7p

Anomaly detection in smart grid based on encoder-decoder framework with recurrent neural network

Anomaly detection in smart grid based on encoder-decoder framework with recurrent neural network

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

编辑推荐

Metrics

本文评价