A Novel Cooperative Fuzzy Classifier for Predicting the Permissible Wind Speed Range in Wind Farms

Mohammadali Alipour, Jamshid Aghaei*, Mohammadali Norouzi, Sattar Hashemi, Matti Lehtonen

*Corresponding author for this work

Research output: Contribution to journalArticleScientificpeer-review

Abstract

It is important to forecast the wind speed range for managing the operation of wind turbines (WTs). Since the electrical power generated by WTs is highly dependent on the uncertain inherent of atmosphere meteorology, improving the accuracy of wind speed range forecasting models leads to the improvement of wind generation prediction. For the sake of uncertainties, it is very challenging to develop an effective and practical model to achieve accurate wind speed range forecasting in large forecasting horizons. This paper presents a novel hybrid classifier based on extended-classifier system with real input (XCSR) and an adaptive neuro-fuzzy inference system (ANFIS), for classification of the wind speed range. It should be mentioned that by employing a cooperative fuzzy classifier system (XCSR-ANFIS), the accuracy and number of the rules that XCSR system must be learned during the training process in the proposed model will be higher and fewer than the XCSR model, respectively. Finally, the comparison of obtained results by implementing the proposed model with other methods for long and short horizons confirms the desirable performance of the proposed model.

Original languageEnglish
Number of pages17
JournalIRANIAN JOURNAL OF SCIENCE AND TECHNOLOGY-TRANSACTIONS OF ELECTRICAL ENGINEERING
DOIs
Publication statusPublished - 14 May 2020
MoE publication typeA1 Journal article-refereed

Keywords

  • Wind speed range forecasting
  • Extended-classifier system (XCS)
  • Adaptive neuro-fuzzy inference system (ANFIS)
  • Accuracy and computational burden

Cite this