Short-term Wind Speed Prediction Research Articles

Short-Term Wind Speed Forecasting Based on Optimizated Support Vector Machine

To avoid the impact which is caused by the characteristics of the random fluctuations of the wind speed to grid-connected wind power generation system, accurately prediction of short-term wind speed is needed. This paper designed a combination prediction model which used the theories of wavelet transformation and support vector machine (SVM). This improved the model’s prediction accuracy through the method of achiving change character in wind speed sequences in different scales by wavelet transform and optimizing the parameters of support vector machines through the improved particle swarm algorithm. The model showed great generalization ability and high prediction accuracy through the experiment. The lowest root-mean-square error of 200 samples was up to 0.0932 and the model’s effect was much stronger than the BP neural network prediction model. It provided an effective method for predicting wind speed.

Very Short-Term Wind Speed Prediction of a Wind Farm Based on Artificial Neural Network

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.

Short-Term Wind Power Forecasting Based on SVM with Backstepping Wind Speed of Power Curve

Accurate wind farm power prediction can relieve the disadvantageous impact of wind power plants on power systems and reduce the difficulty of the scheduling of power dispatching department. Improving accuracy of short-term wind speed prediction is the key of wind power prediction. The authors have studied the short-term wind power forecasting of power plants and proposed a model prediction method based on SVM with backstepping wind speed of power curve. In this method, the sequence of wind speed that is calculated according to the average power of the wind farm operating units and the scene of the power curve is the input of the SVM model. The results show that this method can meet the real-time needs of the prediction system, but also has better prediction accuracy, is a very valuable short-term wind power prediction method.

Design a Wind Speed Prediction Model Using Probabilistic Fuzzy System

Generation of wind is a very complicated process and influenced by large numbers of unknown factors. A probabilistic fuzzy system based prediction model is designed for the short-term wind speed prediction. By introducing the third probability dimension, the proposed prediction model can capture both stochastic and the deterministic uncertainties, and guarantee a better prediction in complex stochastic environment. The effectiveness of this intelligent wind speed prediction model is demonstrated by the simulations on a group of wind speed data. The robust modeling performance further discloses its potential in the practical prediction of wind speed under complex circumstance.

The effect of different state sizes on Mycielski approach for wind speed prediction

Short-term wind speed prediction is very useful for efficient utilization of wind power. Mycielski algorithm is a novel and effective approach alternative to statistical or artificial intelligence based models for wind speed prediction. In order to apply the Mycielski algorithm, the wind speed values are converted to wind states. This paper investigates the effect of different wind speed state sizes on the Mycielski approach for wind speed prediction. The data sets from three different wind farms are used to test the variation of different state sizes for the Mycielski approach. The comparison results and F-test statistics show that the moderate small state size has a significant benefit to predict the wind speed accurately.

A Short-Term Wind Speed Forecasting Through Support Vector Regression Regularized by Particle Swarm Optimization

A sustainability of electricity supply has emerged as a critical issue for low carbon green growth in South Korea. Wind power is the fastest growing source of renewable energy. However, due to its own intermittency and volatility, the power supply generated from wind energy has variability in nature. Hence, accurate forecasting of wind speed and power plays a key role in the effective harvesting of wind energy and the integration of wind power into the current electric power grid. This paper presents a short-term wind speed prediction method based on support vector regression. Moreover, particle swarm optimization is adopted to find an optimum setting of hyper-parameters in support vector regression. An illustration is given by real-world data and the effect of model regularization by particle swarm optimization is discussed as well.

Wind Speed Prediction Model Based on Radial Basis Functional Neural Network

Wind speed forecasting is important to operation of wind power plants and power systems. To solve short term wind speed prediction problem, a radial basis functional neural network prediction model for wind speed time series based on cross iterative fuzzy clustering algorithm and regularized orthogonal least squares algorithm is proposed. First, the optimal fuzzy clustering centers of samples are computed by cross iterative fuzzy clustering algorithm. Then radial basis functional centers are optimized by regularized orthogonal least squares algorithm, and the generalized cross-validation is regarded as criteria to halt center selection. The proposed model centralizes advantages of both algorithms, and it can decrease network scale, improve generalization performance, accelerate network training speed and avoid ill-conditioning of learning problems. A case of practical wind speed time series from wind power plants verifies validity of the proposed model.

An Innovative Hybrid Algorithm for Very Short-Term Wind Speed Prediction Using Linear Prediction and Markov Chain Approach

A new hybrid algorithm using linear prediction and Markov chain is proposed in order to facilitate very short-term wind speed prediction. First, the Markov chain transition probability matrix is calculated. Then, linear prediction method is applied to predict very short-term values. Finally, the results are modified according to the long-term pattern by a nonlinear filter. The results from proposed method are compared by linear prediction method, persistent method and actual values. It is shown that the prediction-modification processes improves very short-term predictions, by reducing the maximum percentage error and mean absolute percentage error, while it retains simplicity and low CPU time and improvement in uncertainty of prediction.

基于模糊信息粒化的风电场短期风速预测

风速的观测值往往存在大量冗余信息，导致计算量庞大并影响预测的有效性。本文提出一种基于模糊信息粒化的风电场短期风速预测方法，将原始风速观测时序数据进行模糊粒化处理，粒化后的数据既能反映风速变化特征，又能大量减少冗余，在此基础上运用支持向量机进行短期风速预测。利用武隆风电场提供的风速数据进行试验表明，该方法能够有效预测未来短期风速变化空间。 There is often a lot of redundant information in observed values of wind speed to result in large computation and affect the predictive validity. A short-term wind speed prediction method based on theory of fuzzy information granulation is proposed to granulate wind speed data of time series. Granulated data can not only reflect the characteristics of wind but also reduce redundant information. Support vector machine can be used to forecast short-term wind speed. A group of wind speed data is provided by Wulong wind farms in Chongqing. The test result shows that this method can predict the short-term wind speed space.

Short term wind speed prediction based on evolutionary support vector regression algorithms

Hyper-parameters estimation in regression Support Vector Machines (SVMr) is one of the main problems in the application of this type of algorithms to learning problems. This is a hot topic in which very recent approaches have shown very good results in different applications in fields such as bio-medicine, manufacturing, control, etc. Different evolutionary approaches have been tested to be hybridized with SVMr, though the most used are evolutionary approaches for continuous problems, such as evolutionary strategies or particle swarm optimization algorithms. In this paper we discuss the application of two different evolutionary computation techniques to tackle the hyper-parameters estimation problem in SVMrs. Specifically we test an Evolutionary Programming algorithm (EP) and a Particle Swarm Optimization approach (PSO). We focus the paper on the discussion of the application of the complete evolutionary-SVMr algorithm to a real problem of wind speed prediction in wind turbines of a Spanish wind farm.

Very short-term wind speed prediction: A new artificial neural network–Markov chain model

As the objective of this study, artificial neural network (ANN) and Markov chain (MC) are used to develop a new ANN–MC model for forecasting wind speed in very short-term time scale. For prediction of very short-term wind speed in a few seconds in the future, data patterns for short-term (about an hour) and very short-term (about minutes or seconds) recorded prior to current time are considered. In this study, the short-term patterns in wind speed data are captured by ANN and the long-term patterns are considered utilizing MC approach and four neighborhood indices. The results are validated and the effectiveness of the new ANN–MC model is demonstrated. It is found that the prediction errors can be decreased, while the uncertainty of the predictions and calculation time are reduced.

Hybridizing the fifth generation mesoscale model with artificial neural networks for short-term wind speed prediction

This paper presents the hybridization of the fifth generation mesoscale model (MM5) with neural networks in order to tackle a problem of short-term wind speed prediction. The mean hourly wind speed forecast at wind turbines in a wind park is an important parameter used to predict the total power production of the park. Our model for short-term wind speed forecast integrates a global numerical weather prediction model and observations at different heights (using atmospheric soundings) as initial and boundary conditions for the MM5 model. Then, the outputs of this model are processed using a neural network to obtain the wind speed forecast in specific points of the wind park. In the experiments carried out, we present some results of wind speed forecasting in a wind park located at the south-east of Spain. The results are encouraging, and show that our hybrid MM5-neural network approach is able to obtain good short-term predictions of wind speed at specific points.

Short term wind speed prediction using support vector machine model

Wind speed prediction in short term is required to asses the effect of wind on different objects in action in free space, like rockets, navigating ships and planes, guided missiles satellites in launch etc. Forecasting also helps in usage of wind energy as an alternative source of energy in Electrical power generation plants. The wind speed depends on the values of other atmospheric variables, such as pressure, moisture content, humidity, rainfall etc. This paper reports a Support Vector Machine model for short term wind speed prediction. The model uses the values of these parameters, obtained from a nearest weather station, as input data. The trained model is validated using a part of data. The model is then used to predict the wind speed, using the same meteorological information.

Accurate short-term wind speed prediction by exploiting diversity in input data using banks of artificial neural networks

Wind speed prediction is a very important part of wind parks management. Currently, hybrid physical-statistical wind speed forecasting models are used to this end, some of them using neural networks as the final step to obtain accurate wind speed predictions. In this paper we propose a method to improve the performance of one of these hybrid systems, by exploiting diversity in the input data of the neural network part of the system. The diversity in the data is produced by the physical models of the system, applied with different parameterizations. Two structures of neural network banks are used to exploit the input data diversity. We will show that our method is able to improve the performance of the system, obtaining accurate wind speed predictions better than the one obtained by the system using single neural networks.

Neural Networks for Short Term Wind Speed Prediction

Predicting short term wind speed is essential in order to prevent systems in-action from the effects of strong winds. It also helps in using wind energy as an alternative source of energy, mainly for Electrical power generation. Wind speed prediction has applications in Military and civilian fields for air traffic control, rocket launch, ship navigation etc. The wind speed in near future depends on the values of other meteorological variables, such as atmospheric pressure, moisture content, humidity, rainfall etc. The values of these parameters are obtained from a nearest weather station and are used to train various forms of neural networks. The trained model of neural networks is validated using a similar set of data. The model is then used to predict the wind speed, using the same meteorological information. This paper reports an Artificial Neural Network model for short term wind speed prediction, which uses back propagation algorithm. Keywords—Short term wind speed prediction, Neural networks, Back propagation.

A short-term strong wind prediction model for railway application: design and verification

Deutsche Bahn AG (German Rail) developed a wind warning system to protect high-speed trains against strong crosswinds. Within this so-called Nowcasting System a short-term prediction of the maximum wind speed is made on the basis of continuous wind measurements at distinct locations of a high-speed railway line. The development of the prediction model was based on high-resolution wind data gathered from a meteorological test site which had been especially built for this purpose. The model has been independently verified by Deutscher Wetterdienst (German Weather Service) using wind data collected from various meteorological stations.