Study on Wind Speed Forecasting Based on STC and BP Neural Network

2013 ◽  
Vol 724-725 ◽  
pp. 623-629
Author(s):  
Xing Jie Liu ◽  
Wen Shu Zheng ◽  
Tian Yun Cen
Keyword(s):  
Neural Network ◽  
Wind Speed ◽  
Bp Neural Network ◽  
Prediction Accuracy ◽  
Wind Farm ◽  
Target Prediction ◽  
Temporal Correlation ◽  
Economic Security ◽  
Wind Speed Forecasting ◽  
Spatio Temporal

Accurate wind speed forecasting of wind farm is of great significance in economic security and stability of the grid. In order to improve the prediction accuracy, the paper first proposed a spatio-temporal correlation predictor method. Based on physical characteristics of wind speed evolution, the method looked for the wind speed and direction information at sites close to the target prediction site, and established STCP model to forecast. And then we established the BP neural network to finish multi-step forecast with wind speed time series of target forecast site .Last, two methods were combined to form STCP-BP method. Simulation tests are conducted with operation data from certain wind farm group in China and results show that STCP-BP method can effectively improve the prediction accuracy compared with BP model.

Wind Speed Forecasting in Wind Farm

2014 ◽  
Vol 672-674 ◽  
pp. 306-309
Author(s):  
Hong Peng Liu ◽  
Xiao Di Zhang ◽  
Hong Sheng Li ◽  
Qing Wang
Keyword(s):  
Neural Network ◽  
Wind Speed ◽  
Prediction Accuracy ◽  
Wind Farm ◽  
Rbf Neural Network ◽  
Forecasting Model ◽  
Training Time ◽  
Wind Speed Forecasting ◽  
Forecasting Models ◽  
Artificial Neural Network Method

Artificial neural network method was used to forecast the wind speed, and two wind speed forecasting models were built based on BP and RBF neural network methods. 24 hours continuous wind speed forecast was conducted for a single wind turbine in wind farm. The results show that the models built are reasonable and have high prediction accuracy. By comparing the two kinds of wind speed forecasting models, BP neural network forecasting model has higher prediction accuracy than RBF neural network forecasting model in wind speed, but it demands much more training time.

Wind Power Short-Term Forcasting of BP Neural Network Based on the Small-World Optimization

2014 ◽  
Vol 933 ◽  
pp. 384-389
Author(s):  
Xin Zhao ◽  
Shuang Xin Wang
Keyword(s):  
Neural Network ◽  
Wind Speed ◽  
Wind Power ◽  
Bp Neural Network ◽  
Wind Direction ◽  
Wind Farm ◽  
Prediction Method ◽  
Small World ◽  
Power Method ◽  
Short Term

Wind power short-term forcasting of BP neural network based on the small-world optimization is proposed. First, the initial data collected from wind farm are revised, and the unreasonable data are found out and revised. Second, the small-world optimization BP neural network model is proposed, and the model is used on the prediction method of wind speed and wind direction, and the prediction method of power. Finally, by simulation analysis, the NMAE and NRMSE of the power method are smaller than those of the wind speed and wind direction method when the wind power data of one hour later are predicted. When the power method are used to forecast the data one hour later, NMAE is 5.39% and NRMSE is 6.98%.

A case study on a hybrid wind speed forecasting method using BP neural network

2011 ◽  
Vol 24 (7) ◽  
pp. 1048-1056 ◽  
Author(s):  
Zhen-hai Guo ◽  
Jie Wu ◽  
Hai-yan Lu ◽  
Jian-zhou Wang
Keyword(s):  
Neural Network ◽  
Wind Speed ◽  
Bp Neural Network ◽  
Wind Speed Forecasting ◽  
Forecasting Method

scholarly journals A Comparative Study of Activation Functions of NAR and NARX Neural Network for Long-Term Wind Speed Forecasting in Malaysia

2019 ◽  
Vol 2019 ◽  
pp. 1-14 ◽  
Author(s):  
Rasel Sarkar ◽  
Sabariah Julai ◽  
Sazzad Hossain ◽  
Wen Tong Chong ◽  
Mahmudur Rahman
Keyword(s):  
Neural Network ◽  
Wind Speed ◽  
Wind Power ◽  
Wind Farm ◽  
Wind Power Generation ◽  
Activation Functions ◽  
Wind Speed Forecasting ◽  
Nonlinear Autoregressive ◽  
Narx Neural Network

Since wind power is directly influenced by wind speed, long-term wind speed forecasting (WSF) plays an important role for wind farm installation. WSF is essential for controlling, energy management and scheduled wind power generation in wind farm. The proposed investigation in this paper provides 30-days-ahead WSF. Nonlinear Autoregressive (NAR) and Nonlinear Autoregressive Exogenous (NARX) Neural Network (NN) with different network settings have been used to facilitate the wind power generation. The essence of this study is that it compares the effect of activation functions (namely, tansig and logsig) in the performance of time series forecasting since activation function is the core element of any artificial neural network model. A set of wind speed data was collected from different meteorological stations in Malaysia, situated in Kuala Lumpur, Kuantan, and Melaka. The proposed activation functions tansig of NARNN and NARXNN resulted in promising outcomes in terms of very small error between actual and predicted wind speed as well as the comparison for the logsig transfer function results.

scholarly journals Multistep Wind Speed Forecasting Based on a Hybrid Model of VMD and Nonlinear Autoregressive Neural Network

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Yuqiao Zheng ◽  
Bo Dong ◽  
Yuhan Liu ◽  
Xiaolei Tong ◽  
Lei Wang
Keyword(s):  
Neural Network ◽  
Wind Speed ◽  
Wind Power ◽  
Wind Farm ◽  
Maintenance Strategies ◽  
Wind Speed Forecasting ◽  
Operation And Maintenance ◽  
Comparison Results ◽  
Nonlinear Autoregressive ◽  
Autoregressive Neural Network

Reducing the costs of wind power requires reasonable wind farm operation and maintenance strategies, and then to develop these strategies, the 24-hour ahead forecasting of wind speed is necessary. However, existing prediction work is mostly limited to 5 hours. This work developed a diurnal forecasting methodology for the regional wind farm according to real-life data of the supervisory control and data acquisition (SCADA) system of a wind farm from Jiangxi Province. The methodology used the variational mode decomposition (VMD) to extract wind characteristics, and then, the characteristics were put in the nonlinear autoregressive neural network (Narnet) and long short-term memory network (LSTM) for prediction; the forecast results of VMD-Narnet and VMD-LSTM are compared with the actual wind speed. The comparison results indicate that compared with the LSTM, the Narnet improves the accuracy by 61.90% in 24 hours on wind speed forecasting, and the predicted time horizon was improved by 6.8 hours. This work strongly supports the development of wind farm operation and maintenance strategies and provides a foundation for the reduction of wind power costs.

Sign in / Sign up

Export Citation Format

Share Document