Wind Power Forecasting Using Wavelet Decomposition and Elman Neural Network

Xiao Lu Gong; Zhi Jian Hu; Meng Lin Zhang; He Wang

doi:10.4028/www.scientific.net/AMR.608-609.628

Paper Titles

Dynamic Evaluation of Wind Turbine Health Condition Based on Multi-Source Information Fusion
p.607

Analysis Model of Wind Power Cost Based on Two-Factor Learning Curve
p.611

Control Strategy of Wind Power Converter under Unbalanced Grid Voltage Condition
p.615

The Crucial Issues in Low-Level Wind Predicton that Used for Wind Energy Forecasting
p.622

Wind Power Forecasting Using Wavelet Decomposition and Elman Neural Network
p.628

High Voltage Ride through of PMSG-Based Wind Turbines
p.633

Predictive Condition Monitoring and Fault Diagnosis Techniques for Offshore Wind Turbines
p.638

Study on the Influence of Wind Power to the Power Supply Side with Consideration of CO₂ Emission Reduction
p.644

Influence of Wind Turbine Aero-Elastic Load on Dynamic Response of Floating Platform
p.649

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 608-609Wind Power Forecasting Using Wavelet Decomposition...

Wind Power Forecasting Using Wavelet Decomposition and Elman Neural Network

Abstract:

The relevant data sequences provided by numerical weather prediction are decomposed into different frequency bands by using the wavelet decomposition for wind power forecasting. The Elman neural network models are established at different frequency bands respectively, then the output of different networks are combined to get the eventual prediction result. For comparison, Elman neutral network and BP neutral network are used to predict wind power directly. Several error indicators are given to evaluate prediction results of the three methods. The simulation results show that the Elman neural network can achieve good results and that prediction accuracy can be further improved by using the wavelet decomposition simultaneously.