Scholarlink

In this study, we assess the performance of various regression models for predicting the theoretical power generated by a wind turbine using supervisory control and data acquisition. The tested models include linear regression, fine tree, support vector machine, rational quadratic Gaussian process regression, and the boosted trees optimizable. We use cross- validation to select the best-performing model. Our findings indicate that the Boosted Trees Optimizable model exhibits superior accuracy, indicated by its low root mean squared error value of 3.69 compared to other models. This high accuracy demonstrates the potential of the Boosted Trees Optimizable model for effective application in wind turbines management.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Predictive Wind Turbine Power Analysis Based on SCADA Data and Machine Learning Algorithms

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Zouhir Iourzikene,
  • Fawzi Gougam,
  • Djamel Benazzouz

摘要

In this study, we assess the performance of various regression models for predicting the theoretical power generated by a wind turbine using supervisory control and data acquisition. The tested models include linear regression, fine tree, support vector machine, rational quadratic Gaussian process regression, and the boosted trees optimizable. We use cross- validation to select the best-performing model. Our findings indicate that the Boosted Trees Optimizable model exhibits superior accuracy, indicated by its low root mean squared error value of 3.69 compared to other models. This high accuracy demonstrates the potential of the Boosted Trees Optimizable model for effective application in wind turbines management.