Abstract
Wind energy is one of the most widely used renewable energy sources. Wind power generation is uncertain because of the intermittent of wind power. To reduce the influence of wind power generation on the power system, it is necessary to forecast wind speed. This paper presents a hybrid wind speed prediction method based on Autoregressive Integrated Moving Average (ARIMA) model and Artificial Neural Network (ANN) model. In three wind speed prediction tests, the hybrid, ARIMA and ANN models are applied respectively. By analyzing the predicted results, it can be concluded that the hybrid method has better forecasting result. By analyzing the results, we can conclude that the hybrid method has better prediction effect.
Highlights
Wind energy is one of the most widely used renewable energy sources in the world
The prediction results of Autoregressive Integrated Moving Average (ARIMA) and Artificial Neural Network (ANN) models are delayed in time compared with real data
There is a slight delay in the data obtained from the ARIMA model, while there is a significant delay between the data predicted by the ANN model and the real data
Summary
Wind energy is one of the most widely used renewable energy sources in the world. In 2017, global wind power generation increased by more than 17 percent to 1,120 TWh, accounting for 4.4 percent of global total power generation. Statistical models implement the estimation by analyzing historical data and the relationship between variables These variables generally include wind speed data, and may have the output of the NWP model. Scholars have conducted extensive studies on wind speed prediction, including autoregressive moving average (ARMA) model, ARIMA model and other linear models, as well as nonlinear prediction models including support vector machine (SVM) and ANN. All of these prediction models have been widely used, but the single prediction model has its own limitations. Simulate the linear characteristics of wind speed time series, and ANN to simulate the nonlinear characteristics of wind speed time series, so as to increase the prediction accuracy
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.