scholarly journals Wind speed prediction with RBF neural network based on PCA and ICA

2018 ◽  
Vol 69 (2) ◽  
pp. 148-155 ◽  
Author(s):  
Yagang Zhang ◽  
Chenhong Zhang ◽  
Yuan Zhao ◽  
Shuang Gao

Abstract Thanks to non-pollution and sustainability of wind energy, it has become the main source of power generation in the new era worldwide. However, the inherent random fluctuation and intermittency of wind power have negative effects on the safe and stable operation of power system and the quality of power. The key solving this problem is to improve the accuracy of wind speed prediction. In the paper, considering the forecasting accuracy is affected by many factors, we propose that, Principal Component Analysis (PCA) is combined with Independent Component Analysis (ICA) to process the sample, which can weaken the mutual interference between the various factors, extract accurately independent component reflected the characteristics of wind farm and achieve the purpose of improving the accuracy of wind speed prediction. At the same time, the adaptive and self-learning ability of neural network is more suitable for wind speed sequence prediction. The prediction results demonstrate that compared with the traditional neural network predicting model (RBF, BP, Elman), this model makes full use of the information provided by varieties of relevant factors, weakens the volatility of wind speed sequence and significantly enhances the short-term wind speed forecasting accuracy. The research work in the paper can help wind farm reasonably arrange the power dispatching plan, reduce the power operation cost and effectively boost the large-scale development and utilization of renewable energy.

2019 ◽  
Vol 70 (3) ◽  
pp. 198-207 ◽  
Author(s):  
Yagang Zhang ◽  
Guifang Pan ◽  
Chenhong Zhang ◽  
Yuan Zhao

Abstract Wind power, as a new energy generation technology, has been applying widely and growing rapidly, which make it become the main force of renewable energy. However, wind speed sequence has its own character of the intermittent and uncertainty, which brings a great challenge to the safety and stability of the power grid, one of the valid ways solving the problem is improving the wind speed predicting accuracy. Therefore, given atmospheric disturbances, we firstly used empirical mode decomposition (EMD) to deal with the non-linear wind speed sequence, and combined with strong adaptive and self-learning ability of BP neural network, then, a wind speed prediction model, EMD-BP neural network based on Lorenz disturbance, was proposed. Finally, it was to made use of actual wind speed data to take a simulation experiment and explored the improvement effect of the preliminary forecasting sequence of wind speed influenced by Lorenz equation in the transient chaos and chaos. The results show that, the improved model weakened the random fluctuation of wind speed sequence, effectively corrected the wind speed sequences initial prediction values, and made a great improvement for the short-term wind speed prediction precision. This research work will help the power system dispatching department adjust the dispatching plan in time, formulate the wind farm control strategy reasonably, reduce the impact brought by wind power grid connection, increase the wind power penetration rate, and then promote the global energy power market innovation.


2014 ◽  
Vol 548-549 ◽  
pp. 1235-1240
Author(s):  
Bin Zeng ◽  
Jian Xiao Zou ◽  
Kai Li ◽  
Xiao Shuai Xin

Wind speed forecasting is an effective method to improve power stability of wind farm. Grey system theory have certain advantages in the study of poor information and uncertainty problems, it is suitable for the system with limited computing power and data storage capacity, such as wind turbine control system. In order to further improve the prediction accuracy of grey model, we combined GM (1, 1) model and BP neural network prediction model in this paper, and improved the combined model by background value optimizing and introducing genetic algorithm. Through analyzing the simulation results and comparing the forecasting results with the actual wind speed, it is clear that the improved combined prediction model is superior to pure grey forecasting model and it meets the needs of the wind power control.


2012 ◽  
Vol 608-609 ◽  
pp. 677-682 ◽  
Author(s):  
Rui Ma ◽  
Shu Ju Hu ◽  
Hong Hua Xu

Wind speed prediction is critical for wind energy conversion system since it not only can relieve or avoid the disadvantageous impact on power system, but also can enhance the competitive ability of wind power plants against others in electricity markets. The model presented in this paper was based on artificial neural network (ANN) and the selection of the model parameters was presented in detail. The autocorrelation function (ACF) of wind speed time series was used to determine the input variables of the neural network. The simulation was carried out with the proposed ANN model.The conclusion that the optimal network structure may be different corresponding to different error evaluation was drawn through a large number of simulation experiments. And the simulaiton results showed that the ANN model is less than 10.77% in terms of root mean square error and 5.86% in terms of mean absolute error compared with the persistence model.


2012 ◽  
Vol 450-451 ◽  
pp. 1593-1596 ◽  
Author(s):  
Cong Lin Zhang

The output of the wind turbine has high randomness due to natural wind velocity. Whether the output can be predicted accurately or not is directly related to the feasibility of dispatching wind power in the power network. The key of wind farm output prediction is to predict the wind speed of wind farm site. This paper uses AR model and BP neural network to predict 24-hour wind speed, and proves the feasibility of these two predicted methods according to comparison with measured wind speed data. This paper has certain reference significance for improving the precision of wind speed prediction.


2012 ◽  
Vol 236-237 ◽  
pp. 741-746 ◽  
Author(s):  
Feng Wang ◽  
Zhi Zhong Tan ◽  
De You Liu ◽  
Xiang Dong Qian

This paper analyzes the importance of the wind farm wind speed prediction, as well as the different forecasting methods in various fields. And established the RBF neural network forecasting model can forecast one hour ahead of the wind farm wind speed, and the results meet the actual forecast requirements. By reconstructing the wind speed time series, wind speed can be predicted one day in advance, the prediction accuracy and one hour ahead of forecast accuracy is similar. The method can predict a longer period of time the wind speed, and provide important reference for the wind farm power generation scheduling.


Sign in / Sign up

Export Citation Format

Share Document