Title :
Application of improved fuzzy c-means algorithm on bad-data identification and adjustment in short-term load forecasting
Author :
Sun Qian ; Yao JianGang ; Jiang WenQian ; Yang Shengjie ; Xu ZhenChao
Author_Institution :
Coll. of Electr. & Inf. Eng., Hunan Univ., Changsha, China
Abstract :
Bad data identification and adjustment in Short-term load forecasting should fully consider the similarity and smoothness of the daily load curve. First, completing the missing data use the Neville algorithm. Then the daily load curves are clustered by improved fuzzy c-means algorithm, and a typical load curve is thus obtained for each cluster. Use the horizontal and vertical similarity of the daily load curve to identify the bad data. At last,the bad data are adjusted with typical curves. Test results using actual data demonstrate the validity and feasibility of the proposed method.
Keywords :
fuzzy set theory; load forecasting; pattern clustering; Neville algorithm; bad-data identification; daily load curve; improved fuzzy C-means algorithm; short-term load forecasting; Automation; Classification algorithms; Clustering algorithms; Indexes; Interpolation; Load forecasting; Neville algorithm; bad data; improved FCM algorithm; typical curve;
Conference_Titel :
Advanced Power System Automation and Protection (APAP), 2011 International Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4244-9622-8
DOI :
10.1109/APAP.2011.6180464