A hybrid forecasting method for wind power ramp based on Orthogonal Test and Support Vector Machine (OT-SVM)

Yonqian Liu, Ying Sun, David Infield, Yu Zhao, Shuang Han, Jie Yan

Research output: Contribution to journalArticlepeer-review

75 Citations (Scopus)
112 Downloads (Pure)


In an electric power system with a high penetration of wind power, incoming power ramps pose a serious threat to the power system. To adopt suitable response strategies for wind power ramps, it is important to predict them accurately and in a timely manner. Since power ramps are caused by various factors, their occurrence have irregular characteristics and vary by location, bringing great difficulty in forecasting. To solve this problem, a hybrid forecasting model OT-SVM (Orthogonal Test and Support Vector Machine) was developed in this paper, which combines an orthogonal test with a support vector machine. A novel factor analysis method was established based on the theory of the orthogonal test (OT), and applied to determine the optimal
inputs of a support vector machine (SVM). The effectiveness of OT-SVM was tested with three wind farms in China, while comparing the results with other related methods. The results show that the proposed OT-SVM has the highest accuracy covering different input numbers and time resolutions. In addition, a novel evaluation index MAI (Mean Accuracy Index) was proposed, considering both the missed ramps and false ramps, which can be used as a supplementary index for CSI.
Original languageEnglish
Pages (from-to)451-457
Number of pages7
JournalIEEE Transactions on Sustainable Energy
Issue number2
Early online date31 Aug 2016
Publication statusPublished - Apr 2017


  • wind power ramp forecasting Orthogonal test
  • multi-factor analysis
  • large-scale integration of wind power
  • meteorological factors
  • statistical analysis
  • support vector machine


Dive into the research topics of 'A hybrid forecasting method for wind power ramp based on Orthogonal Test and Support Vector Machine (OT-SVM)'. Together they form a unique fingerprint.

Cite this