scholarly journals LONG TERM WIND SPEED PREDICTION USING WAVELET COEFFICIENTS AND SOFT COMPUTING

2016 ◽  
Vol 07 (01) ◽  
pp. 1338-1343
Author(s):  
Manju Khanna ◽  
◽  
Srinath N.K. ◽  
Mendiratta K. ◽  
◽  
...  
2012 ◽  
Vol 512-515 ◽  
pp. 803-808
Author(s):  
Ji Long Tong ◽  
Zeng Bao Zhao ◽  
Wen Yu Zhang

This paper presents a new strategy in wind speed prediction based on AR model and wavelet transform.The model uses the adjacent data for short-term wind speed forecasting and the data of the same moment in earlier days for long-term wind speed prediction at that moment,taking the similarity of wind speed at the same moment every day into account.Using the new model to analyze the wind speed of An-xi,China in April,2010,this paper concludes that the model is effective for that the correlation coefficient between the predicted value and the original data is larger than 0.8 when the prediction is less than 48 hours;while the prediction time is long ahead (48-120h),the error is acceptable (within 40%),which demonstrates that the new method is a novel and good idea for prediction on wind speed.


2019 ◽  
Vol 24 (15) ◽  
pp. 11441-11458 ◽  
Author(s):  
Yogambal Jayalakshmi Natarajan ◽  
Deepa Subramaniam Nachimuthu

2021 ◽  
Vol 7 (4) ◽  
pp. 542-552
Author(s):  
Manogaran Madhiarasan ◽  

<abstract> <p>In the current scenario, worldwide renewable energy systems receive renewed interest because of the global reduction of greenhouse gas emissions. This paper proposes a long-term wind speed prediction model based on various artificial neural network approaches such as Improved Back-Propagation Network (IBPN), Multilayer Perceptron Network (MLPN), Recursive Radial Basis Function Network (RBFN), and Elman Network with five inputs such as wind direction, temperature, relative humidity, precipitation of water content and wind speed. The proposed ANN-based wind speed forecasting models help plan, integrate, and control power systems and wind farms. The simulation result confirms that the proposed Recursive Radial Basis Function Network (RRBFN) model improves the wind speed prediction accuracy and minimizes the error to a minimum compared to other proposed IBPN, MLPN, and Elman Network-based wind speed prediction models.</p> </abstract>


2019 ◽  
Vol 136 ◽  
pp. 1082-1090 ◽  
Author(s):  
Haoshu Cai ◽  
Xiaodong Jia ◽  
Jianshe Feng ◽  
Qibo Yang ◽  
Yuan-Ming Hsu ◽  
...  

2017 ◽  
Vol 21 (1) ◽  
pp. 29
Author(s):  
Juan A Lazzús ◽  
Ignacio Salfate

An artificial neural network was used for forecasting of long-term wind speed data (24 and 48 hours ahead) in La Serena City (Chile). In order to obtain a more effective correlation and prediction, a particle swarm algorithm was implemented to update the weights of the network. 43800 data points of wind speed were used (years 2003- 2007), and the past values of wind speed, relative humidity, and air temperature were used as input parameters, considering that these meteorogical parameters are more readily available around the globe. Several neural network architectures were studied, and the optimum architecture was determined by adding neurons in systematic form and evaluating the root mean square error (RMSE) during the learning process. The results show that the meteorological variables used as input parameters, have influential effects on the good training and predicting capabilities of the chosen network, and that the hybrid neural network can forecast the hourly wind speed with acceptable accuracy, such as: RMSE=0.81 [m·s−1], MSE=0.65 [m·s−1] 2 and R2 =0.97 for 24-hours-ahead wind speed prediction, and RMSE=0.78, MSE=0.634 [m·s−1] 2 and R2 =0.97 for 48-hours-ahead wind speed prediction. Predicción a largo plazo de la velocidad de viento en la ciudad de La Serena (Chile) utilizando un algoritmo híbrido de red neuronal-enjambre de partículasResumenUna red neuronal artificial fue utilizada para la predicción de datos de la velocidad de viento a largo plazo (24 y 48 horas en adelanto) en la Ciudad de La Serena (Chile). Para obtener una efectiva correlación y predición, se implementó una optimización de enjambre de particulas para actualizar los pesos de la red. Se emplearon 43800 datos de velocidad de viento (años 2003-2007), y los valores pasados de velocidad del viento, humedad relativa y temperatura del aire fueron utilizados como parámetros de entrada, considerando que estos parámetros meteorológicos se encuentran fácilmente disponibles en todo el mundo. Se estudiaron varias arquitecturas de redes neuronales y la arquitectura optima se determine añadiendo neuronas de forma sistemática y evaluando la raíz del error cuadrático medio (RMSE) durante el proceso de aprendizaje. Los resultados muestran que las variables meteorológicas utilizadas como parámetros de entrada, tienen un efecto positivo sobre el correcto entrenamiento y capacidades predictivas de la red, y que la red neural híbrida puede pronosticar la velocidad del viento horaria con una precisión aceptable, como un RMSE=0.81 [m·s−1], MSE=0.65 [m·s−1] 2 y R2 =0.97 para la predicción de la velocidad del viento de 24 horas en adelanto, y un RMSE=0.78, MSE=0.634 [m·s−1] 2 and R2 =0.97 para la predicción de la velocidad del viento de 48 horas en adelanto


Sign in / Sign up

Export Citation Format

Share Document