Education, Science, Technology, Innovation and Life
Open Access
Sign In

Outlier Detection of Power Supplier Quotation Based on Characteristic Index

Download as PDF

DOI: 10.23977/ieim.2022.051205 | Downloads: 8 | Views: 620

Author(s)

Bo Gao 1, Jiawei Pan 2, Xuwen Liu 1, Changyu Qian 2, Linjie Wang 1

Affiliation(s)

1 Jiangsu Power Exchange Center Co., Ltd., No. 62, Yunnan Road, Gulou District, Nanjing, China
2 School of Electrical Engineering, Southeast University, No. 2, Sipailou, Xuanwu District, Nanjing, China

Corresponding Author

Changyu Qian

ABSTRACT

In order to detect the abnormal behavior of unit quotation in power market, an outlier detection method based on characteristic index is proposed. According to the characteristics of abnormal behavior of unit quotation, the corresponding characteristic indexes are extracted, and the dimension is reduced by principal component analysis method. The local outlier factor algorithm is used to detect outliers, and the evaluation indexes are compared when different number of features are extracted. The experimental results show that the proposed method can detect abnormal quotation units to a certain extent, and the evaluation index is improved with the number of features extracted.

KEYWORDS

Outlier detection, Feature extraction, Principal component analysis, Local outlier factor

CITE THIS PAPER

Bo Gao, Jiawei Pan, Xuwen Liu, Changyu Qian, Linjie Wang, Outlier Detection of Power Supplier Quotation Based on Characteristic Index. Industrial Engineering and Innovation Management (2022) Vol. 5: 34-43. DOI: http://dx.doi.org/10.23977/ieim.2022.051205.

REFERENCES

[1] Han Jiawei, Kamber M.Data Mining: Concepts and techniques. Fan Ming, Meng Xiaofeng, Trans. 3rd Ed. Beijing: China Machine Press, 2012:186-188.
[2] Barnett V, Lewis T, Abeles F. utliers in statistical data. 3rd ed. Hoboken: Wiley, 1994.
[3] Eskin E.A nomaly detection over noisy data using learnt probability distributions//Proc of the 17th International Conference on Machine Learning. San Francisco, CA: Morgan Kaufmann Publishers, 2000: 255-262.
[4] Fawcett T, Provost F. The Adaptive fraud detection. Data Mining & Issue 12 Merlin, et al.: A survey of outlier detection techniques •3525• Knowledge Discovery, 1997, 1(3): 291-316.
[5] Ni Wei-Wei, Lu Jie-ping, Chen Geng, Sun Zhi-hui. Data displacement outgroup detection algorithm based on K-means partitioning. Computer Research and Development, 2006 (09): 1639-1643.
[6] Gu Ping, Liu Haibo, Luo Zhiheng. An outlier detection algorithm Based on Multiple reunion classes. Application Research of Computers, 2013, 30 (03): 751-753+756.
[7] Tao Qing, Cao Jinde, Sun Demin. Regression method based on Support Vector Machine classification. Journal of Software, 2002 (05): 1024-1028.
[8] Zhang Yi, Liu Xumin, Sui Ying, Guan Yong. Research and Improvement of Denoising Algorithm Based on K-Nearest Neighbor Point Cloud. Journal of Computer Applications, 2009, 29 (04): 1011-1014.
[9] Wang Zhen. Analysis and Research of distance-based Outlier detection algorithm. Chongqing University, 2011.
[10] Wang Jinghua, Zhao Xinxiang, Zhang Guoyan, Liu Jianyin. NLOF: A novel density-based local outlier detection algorithm. Computer Science, 2013, 40 (08): 181-185.
[11] Thakur S, Gasperis G D. Cartel formation in charging network for electric vehicles// IEEE 16th International Conference on Environment and Electrical Engineering. Florence: Institute of Electrical and Electronics Engineers, 2016:1-6.

Downloads: 16424
Visits: 380152

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.