Intelligent multiperiod wind power forecast model using statistical and machine learning model

Manisha Galphade, Valmik Nikam, Biplab Banerjee, Arvind Kiwelekar


With the rapidly increasing integration of wind energy into the modern energy grid system, wind energy prediction (WPP) is playing an important role in the planning and operation of an electrical distribution system. However, the time series data of wind energy always has nonlinear and non-stationary characteristics, which is still a great challenge to be accurately predicted. This paper proposes the intelligent wind power forecast model and evaluates to forecast long term, short term and medium term wind power. It uses statistical and machine learning approach for finding the best model for multiperiod forecasting. The model has been tested on Sotavento wind farm historical data, located in Galicia, Spain. The experimental results show that random forest has better accuracy than other models for long term, short term and medium term forecasting. The power prediction accuracy of the proposed model has been evaluated on RMSE, and MAE metrics. The proposed model has shown better accuracy for medium term and long term forecast. The accuracy is improved by 72.12% in case of medium term and 50.49% in case of long term.


Correlation matrix; Machine learning; MAE; Regression models; Renewable energy; RMSE; Statistical approach; Wind power forecasting

Full Text:




  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Bulletin of EEI Stats