Short-Term Wind Power Prediction With Particle Swarm Optimization
Yongqian Liu · Power System Technology · 2011
According to the wind speed and wind direction data from numerical weather prediction,a short-term wind power forecasting is performed by BP neural network model with particle swarm optimization(PSO).The influences of data dependency on forecasting results are analyzed and the performances of BP neural network model with and without PSO are compared.Research results show that the BP neural network model with PSO possesses better performance that that without PSO,and based on the testing samplings with better data dependency a better forecasting result can be achieved.The higher the correlation coefficient between the numerically predicted wind data and output power,the higher the forecasting accuracy by BP neural network model with PSO will be than that without PSO.