An adaptive identification method of abnormal data in wind and solar power stations. (May 2023)

• Record Type: Journal Article
• Authors: Wang, Han; Zhang, Ning; Du, Ershun; Yan, Jie; Han, Shuang; Li, Nan; Li, Hongxia; Liu, Yongqian
• Is Part Of: Renewable energy. Volume 208(2023)
• Page Start: 76
• Page End: 93
• Publication Date: 2023-05
• Subjects: Wind farm -- Solar plant -- Abnormal data -- Adaptive identification -- Power reconstruction; Renewable energy sources -- Periodicals; Power resources -- Periodicals; Énergies renouvelables -- Périodiques; Ressources énergétiques -- Périodiques; 333.794
• DOI: 10.1016/j.renene.2023.03.081
• Languages: English
• ISSNs: 0960-1481

Abstract

Abstract: Accurate and credible operation data sets of wind and solar power stations are the basis of many research works. However, such data sets often contain abnormal data due to failure, maintenance, energy curtailment, etc. The existing identification methods fail to consider the operating characteristics of power stations and the forms of abnormal data, resulting in low identification ability. Therefore, an adaptive identification method of abnormal data (AIMAD) in the wind and solar power stations is proposed in this paper, including the bidirectional one-sided quartile method and double DBSCAN method to deal with unevenly distributed abnormal data; the improved K-means clustering method based on the distance between the cluster center and benchmark power curve to process the abnormal data that are densely accumulated and closely connected with normal data in the power scatter diagram. The proposed method can adjust adaptively according to the forms of abnormal data to realize accurate identification and has strong robustness for power stations. The operation data of 30 wind farms and 8 solar plants in China are taken as examples to verify the effectiveness and superiority of the proposed method. Highlights: BOQ and d-DBSCAN are proposed to deal with unevenly distributed abnormal data. Improved K-means method is proposed for identifying stacked abnormal data. AIMAD is proposed to realize accurate identification of abnormal data. Operation data in 38 stations are used to verify the effectiveness of AIMAD.