Wind Speed Prediction using Extra Tree Classifier

Abstract

A cluster of wind turbines in the same site that generates power. Using turbines perform effectively with severe winds and optimal wind speed. For a wind farm, the wind direction and speed can be projected that wind turbines would operate efficiently. So, the wind generators' output will be having increased effectiveness. Big data and machine learning are defined as a large collection of datasets that are advanced to process. Wind speed forecasting is one of the most critical responsibilities in a wind farm. Machine learning approaches are frequently used to forecast time series non-linear wind behavior. This research provides a wind dataset prediction model that relies on the Extra Tree classifier in this context. The proposed model has the benefit of being simple, quick, and well-suited to the short term. The accuracy of the project is then compared with bagging classifier and Ada boost Classifier algorithms in their regression mode, and then the project aims to illustrate how wind direction may affect power generation and why it is vital to anticipate it. A real-time series data collection contains past values of characteristics like speed of wind, temperature, and atmospheric pressure, they are used to forecast the speed of the wind. The suggested model Extra Tree classifier will be evaluated using Mean Absolute, Mean Square Error values, and its performance will be compared to that of bagging classifier and Ada boost Classifier algorithm models.