Wind Speed Forecasting Based on Variable Weight Combination Model of Neural Network and Grey Model

2012 ◽  
Vol 217-219 ◽  
pp. 2654-2657
Author(s):  
Jian Zhang ◽  
Lun Nong Tan
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Wind Speed ◽  
Wind Farms ◽  
Grey Model ◽  
Weighting Coefficient ◽  
Forecasting Accuracy ◽  
Wind Speed Forecasting ◽  
Variable Weight ◽  
Artificial Neural Network Ann

The wind speed forecasting accuracy of artificial neural network(ANN) and grey model(GM) is poorly satisfied. Thus, we proposed a new variable weight combined (VWC) model, which was based on the ANN and GM, to improve the wind speed forecasting accuracy. VWC used weighting coefficient of different time to fit the two single models. The forecasting accuracy of VWC is higher than either of the two single models, and is also higher than the unchanged weight combination(UWC) model. Our data show a new method for wind speed forecasting and the reduction of auxiliary service costs of wind farms.

scholarly journals A Combined Model Based on Society Cognitive Optimization Algorithm for Wind Speed Forecasting

2021 ◽  
Author(s):  
Zhaoshuang He ◽  
Yanhua Chen ◽  
Min Li
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Wind Speed ◽  
Optimization Algorithm ◽  
Wind Farms ◽  
Combined Model ◽  
Wind Speed Forecasting ◽  
Forecasting Performance ◽  
Artificial Neural ◽  
Cognitive Optimization

Abstract Wind energy, as renewable energy, has drawn the attention of society. The use of wind power generation can reduce the pollution to the environment and solve the problem of power shortage in offshore islands, grassland, pastoral areas, mountain areas, and highlands. Wind speed forecasting plays a significant role in wind farms. It can improve economic and social benefits and make an operation schedule for wind turbines in large wind farms. At present, researchers have proposed a variety of methods for wind speed forecasting; artificial neural network (ANN) is one of the most commonly used methods. This paper proposes a combined model based on the existing artificial neural network algorithms for wind speed forecasting at different heights. We first use the wavelet threshold method to the original wind speed data set for noise reduction. After that, the three artificial neural networks, extreme learning machine (ELM), Elman neural network, and Long Short-Term Memory neural network (LSTM), are applied for wind speed forecasting. In addition, variance reciprocal method and society cognitive optimization algorithm (SCO) are used to optimize the weight coefficients of the combined model. In order to evaluate the forecasting performance of the combined model, we select wind speed data at three heights (20m, 50m, and 80m) in National Wind Technology Center M2 Tower. The experimental results show that the forecasting performance of the combined model is better than the single model, and it has a good forecasting performance for the wind speed at different heights.

24-hours wind speed forecasting and wind power generation in La Serena (Chile)

2018 ◽  
Vol 42 (6) ◽  
pp. 607-623 ◽  
Author(s):  
Ignacio Salfate ◽  
Carlos H López-Caraballo ◽  
Carolina Sabín-Sanjulián ◽  
Juan A Lazzús ◽  
Pedro Vega ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Wind Speed ◽  
Wind Power ◽  
Meteorological Data ◽  
Wind Farms ◽  
Vital Role ◽  
Wind Speed Forecasting ◽  
Wind Potential ◽  
Artificial Neural

This article presents 24-h wind speed forecasting for the city of La Serena in Chile and a methodology to explore forecasting effects on the production of wind turbine power. To that end, we used meteorological data from a weather station located in the southern zone of the hyper-arid Atacama Desert. In this area, energy resources are economically and environmentally important, and wind speed forecasting plays a vital role in the management and marketing processes of wind potential via wind farms. To contribute to the development of this energy, we propose carrying out the short-term prediction of 12 and 24 h ahead (identified as Ws( t + 12) and Ws( t + 24), respectively) using an artificial neural network with backpropagation approach. Hourly time series of wind speed, temperature, and relative humidity (from 2003 to 2006) were considered to characterize the artificial neural network in the training phase, while we used data from the year 2007 to check the efficiency of our prediction. For artificial neural network Ws( t + 12) and Ws( t + 24) models, we obtained similar performance of wind speed prediction with root mean square error of around 0.7 m s−1 and with maximum and minimum residuals of +4 and ‒4 m s−1, respectively. Based on the results, we gain a reliable tool to characterize wind speed properties in the range of 1 day within 20% of uncertainty. Moreover, this tool becomes useful to study the effects of our artificial neural network Ws( t + 12) and Ws( t + 24) models on the generation of wind energy from a wind power turbine parametrization.

scholarly journals Analysis of Random Forest Modeling Strategies for Multi-Step Wind Speed Forecasting

Energies ◽  
2020 ◽  
Vol 13 (20) ◽  
pp. 5488
Author(s):  
Daniel Vassallo ◽  
Raghavendra Krishnamurthy ◽  
Thomas Sherman ◽  
Harindra J. S. Fernando
Keyword(s):  
Wind Speed ◽  
Random Forest ◽  
Great Plains ◽  
Wind Farms ◽  
Data Availability ◽  
Training Data ◽  
Forecasting Accuracy ◽  
Wind Speed Forecasting ◽  
Atmospheric Radiation Measurement ◽  
Model Versus

Although the random forest (RF) model is a powerful machine learning tool that has been utilized in many wind speed/power forecasting studies, there has been no consensus on optimal RF modeling strategies. This study investigates three basic questions which aim to assist in the discernment and quantification of the effects of individual model properties, namely: (1) using a standalone RF model versus using RF as a correction mechanism for the persistence approach, (2) utilizing a recursive versus direct multi-step forecasting strategy, and (3) training data availability on model forecasting accuracy from one to six hours ahead. These questions are investigated utilizing data from the FINO1 offshore platform and Atmospheric Radiation Measurement (ARM) Southern Great Plains (SGP) C1 site, and testing results are compared to the persistence method. At FINO1, due to the presence of multiple wind farms and high inter-annual variability, RF is more effective as an error-correction mechanism for the persistence approach. The direct forecasting strategy is seen to slightly outperform the recursive strategy, specifically for forecasts three or more steps ahead. Finally, increased data availability (up to ∼8 equivalent years of hourly training data) appears to continually improve forecasting accuracy, although changing environmental flow patterns have the potential to negate such improvement. We hope that the findings of this study will assist future researchers and industry professionals to construct accurate, reliable RF models for wind speed forecasting.

scholarly journals Wind energy location prediction between meteorological stations using ANN

2015 ◽  
Vol 16 (6) ◽  
pp. 1135-1144
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Wind Speed ◽  
Wind Energy ◽  
Tamil Nadu ◽  
Energy Potential ◽  
Soft Computing Techniques ◽  
Wind Energy Potential ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

<div> <p>Wind Energy is one of the important sources of renewable energy. There is a need to prepare the availability of wind energy in the area where there is no measured wind speed data. For this type of situation, it seems to be necessary to predict the wind energy potential using such as wind speed using artificial neural network (ANN) method. Soft computing techniques are widely used now days in the study of wind energy potential estimation. In this study the wind energy potential between neighborhood meteorological tower stations is predicted using Artificial Neural Network technique. One of the most suitable areas of Tamil Nadu for wind power generation is some locations in the districts of Tirunelveli, Thoothukudi, Kanyakumari, Theni, Coimbatore, and Dindigul. Along the southeast coastline of Tamil Nadu there are no valleys and mountains besides the mountains are situated away from the sea coast in many regions. Therefore, these regions are exposed to northerly winds that are not as strong as the southerly winds.</p> </div> <p>&nbsp;</p>

scholarly journals Forecast of Wind Speed with a Backpropagation Artificial Neural Network in the Isthmus of Tehuantepec Region in the State of Oaxaca, Mexico

2012 ◽  
Vol 22 ◽  
pp. 7-14 ◽  
Author(s):  
Ernesto Cortés Pérez ◽  
Airel Nuñez Rodríguez ◽  
Rosa Edith Moreno De La Torre ◽  
Orlando Lastres Danguillecourt ◽  
José Rafael Dorrego Portela
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Wind Speed ◽  
Training Method ◽  
University Campus ◽  
Coefficient Corrélation ◽  
Isthmus Of Tehuantepec ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Backpropagation Artificial Neural Network

This paper presents the preliminary results of setting up an artificial neural network (ANN) of the feed forward type with the backpropagation training method for forecast wind speed in the region in the Isthmus of Tehuantepec, Oaxaca, Mexico. The database used covers the years from June 2008 - November 2011, and was supplied by a meteorological station located at the Isthmus University campus Tehuantepec. The experiments were done using the following variables: wind speed, pressure, temperature and date. At the same time were done seven tests combining these variables, comparing their mean square error (MSE) and coefficient correlation r, with data the predicting and experimental. In this research, is proposed a ANN of two hidden layers, for a forecast of 48 hours.

scholarly journals Development of Artificial Neural Network Model for Estimation of Salt Fields Productivity

2019 ◽  
Vol 20 (2) ◽  
pp. 152
Author(s):  
Indra Cahyadi ◽  
Heri Awalul Ilhamsah ◽  
Ika Deefi Anna
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Wind Speed ◽  
Prediction Model ◽  
Factorial Design ◽  
Neural Network Model ◽  
Artificial Neural Network Model ◽  
Model Performance ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

In recent years, Indonesia needs import million tons of salt to satisfy domestic industries demand. The production of salt in Indonesia is highly dependent on the weather. Therefore, this article aims to develop a prediction model by examining rainfall, humidity and wind speed data to estimate salt production. In this research, Artificial Neural Network (ANN) method is used to develop a model based on data collected from Kaliumenet Sumenep Madura.  The model analysis uses the full experimental factorial design to determine the effect of the ANN parameter differences. Then, the selected model performance compared with the estimate predictor of Holt-Winters. The results present that ANN-based models are more accurate and efficient for predicting salt field productivity.

Sign in / Sign up

Export Citation Format

Share Document