A novel application of artificial neural network for wind speed estimation

Providing accurate multi-steps wind speed estimation models has increasing significance, because of the important technical and economic impacts of wind speed on power grid security and environment benefits. In this study, the combined strategies for wind speed forecasting are proposed based on an intelligent data processing system using artificial neural network (ANN). Generalized regression neural network and Elman neural network are employed to form two hybrid models. The approach employs one of ANN to model the samples achieving data denoising and assimilation and apply the other to predict wind speed using the pre-processed samples. The proposed method is demonstrated in terms of the predicting improvements of the hybrid models compared with single ANN and the typical forecasting method. To give sufficient cases for the study, four observation sites with monthly average wind speed of four given years in Western China were used to test the models. Multiple evaluation methods demonstrated that the proposed method provides a promising alternative technique in monthly average wind speed estimation.     

Effect of direction on wind speed estimation in complex terrain using neural networks

A method of estimating the annual average wind speed at a selected site using neural networks is presented. The method proposed uses only a few measurements taken at the selected site in a short time period and data collected at nearby fixed stations.The neural network used in this study is a multilayer perceptron with one hidden layer of 15 neurons, trained by the Bayesian regularization algorithm. The number of inputs that must be used in the neural network was analyzed in detail, and results suggest that only wind speed and direction data for a single station are required. In sites of complex terrain, direction is a very important input that can cause a decrease of 23% in root mean square (RMS).The results obtained by simulating the annual average wind speed at the selected site based on data from nearby stations are satisfactory, with errors below 2%.     

基于MMAS BP算法的短期风速非线性组合预测模型

为提高风电场短期风速的预测精度,引入一种基于改进蚁群算法优化神经网络的非线性组合预测方法,按误差平方和最小原则对所建灰色GM(1,1)模型、BP网络和RBF网络三种单一预测数据进行非线性组合,并将其结果作为最终预测值。仿真结果表明,该方法的平均绝对误差及均方误差分别为17.76%和3.68%,均小于单一模型、线性组合模型及神经网络组合模型的预测结果,提高了网络的泛化能力,降低了预测风险,为风电场风速预测提供了一种新途径。     

基于小波变换与Elman神经网络的短期风速组合预测

风速的准确预测对风电场发电系统的经济和安全运行有着重要的作用。为了克服风速随机性强的缺点,提高短期风速预测的精度,提出了一种将小波变换与Elman神经网络相结合的短期风速组合预测模型。该模型由小波预处理模块和神经网络预测模块组成。首先利用小波预处理模块将风速序列作多尺度分解,重构得到不同频段的子序列,然后利用Elman神经网络模块分别对其训练和预测。实际风速预测结果表明,与单一的Elman和ARMA法相比,该组合预测模型的预测精度有较大的改善,可以用于风电场短期风速的预测。     

On comparing three artificial neural networks for wind speed forecasting

Wind speed forecasting is critical for wind energy conversion systems since it greatly influences the issues such as the scheduling of a power system, and the dynamic control of the wind turbine. In this paper, we present a comprehensive comparison study on the application of different artificial neural networks in 1-h-ahead wind speed forecasting. Three types of typical neural networks, namely, adaptive linear element, back propagation, and radial basis function, are investigated. The wind data used are the hourly mean wind speed collected at two observation sites in North Dakota. The performance is evaluated based on three metrics, namely, mean absolute error, root mean square error, and mean absolute percentage error. The results show that even for the same wind dataset, no single neural network model outperforms others universally in terms of all evaluation metrics. Moreover, the selection of the type of neural networks for best performance is also dependent upon the data sources. Among the optimal models obtained, the relative difference in terms of one particular evaluation metric can be as much as 20%. This indicates the need of generating a single robust and reliable forecast by applying a post-processing method.     

基于Elman神经网络的短期风电功率预测

为提高风电场输出功率预测精度,提出一种动态基于神经网络的功率预测方法。根据实际运行的风电场相关风速、相关风向和风电功率的历史数据,建立了基于Elman神经元网络的短期风电功率预测模型。运用多层Elman神经网络模型对西北某风电场实际1h和24h的风电输出功率预测,与BP神经网络模型对比,经仿真分析证明前者具有预测精度高的特点,三隐含层Elman神经网络模型预测效果最佳。这表明利用Elman回归神经网络建模对风电功率进行预测是可行的,能有效提高功率预测精度。     

Wind speed forecasting based on the hybrid ensemble empirical mode decomposition and GA-BP neural network method

Wind speed is the major factor that affects the wind generation, and in turn the forecasting accuracy of wind speed is the key to wind power prediction. In this paper, a wind speed forecasting method based on improved empirical mode decomposition (EMD) and GA-BP neural network is proposed. EMD has been applied extensively for analyzing nonlinear stochastic signals. Ensemble empirical mode decomposition (EEMD) is an improved method of EMD, which can effectively handle the mode-mixing problem and decompose the original data into more stationary signals with different frequencies. Each signal is taken as an input data to the GA-BP neural network model. The final forecasted wind speed data is obtained by aggregating the predicted data of individual signals. Cases study of a wind farm in Inner Mongolia, China, shows that the proposed hybrid method is much more accurate than the traditional GA-BP forecasting approach and GA-BP with EMD and wavelet neural network method. By the sensitivity analysis of parameters, it can be seen that appropriate settings on parameters can improve the forecasting result. The simulation with MATLAB shows that the proposed method can improve the forecasting accuracy and computational efficiency, which make it suitable for on-line ultra-short term (10 min) and short term (1 h) wind speed forecasting.     

Application of Bayesian model averaging in modeling long-term wind speed distributions

Accurate estimation of wind speed distribution is critical to the assessment of wind energy potential, the site selection of wind farms, and the operations management of wind power conversion systems. This paper proposes a new approach for deriving more reliable and robust wind speed distributions than conventional statistical modeling approach. This approach combines Bayesian model averaging (BMA) and Markov Chain Monte Carlo (MCMC) sampling methods. The derived BMA probability density function (PDF) of the wind speed is an average of the model PDFs included in the model space weighted by their posterior probabilities over the sample data. MCMC method provides an effective way for numerically computing marginal likelihoods, which are essential for obtaining the posterior model probabilities. The approach is applied to multiple sites with high wind power potential in North Dakota. The wind speed data at these sites are the mean hourly wind speeds collected over two years. It is demonstrated that indeed none of the conventional statistical models such as Weibull distribution are universally plausible for all the sites. However, the BMA approach can provide comparative reliability and robustness in describing the long-term wind speed distributions for all sites, while making the traditional model comparison based on goodness-of-fit statistics unnecessary.     

Wind resource assessment of an area using short term data correlated to a long term data set

A method of estimating the annual wind energy potential of a selected site using short term measurements related to one year’s recorded wind data at another reference site is presented. The proposed method utilizes the 1-year measured wind speed of one site to extrapolate the annual wind speed at a new site, using an artificial neural network (ANN). In this study, concurrent measurements from target and reference sites over periods of 1-month and 2-month were used to “train” the ANN. Topographical details or other meteorological data are not required for this approach. After derivation of the simulated wind speed time series for the target site, its mean value and its corresponding Weibull distribution parameters are calculated. The derived Weibull distribution of the simulated wind speed is used to make an assessment of the annual wind energy resource in the new area with respect to a particular wind turbine model. Three pairs of measuring stations in the southwest of Ireland were examined, where the wind potential is high and technically exploitable. Analysis of the measurements showed a reasonable cross-correlation coefficient of the wind speed between the sites. Results indicate that with this method, only a short time period of wind data acquisition in a new area might provide the information required for a satisfactory assessment of the annual wind energy resource. To evaluate the accuracy of the method, simulation results of the 1-month and 2-month training periods are compared to the corresponding actual values recorded at the sites. Also, a comparison with the results of a commercial wind energy assessment software package is presented showing similar results.     

风速时间序列非线性短期预测

针对风速时间序列复杂的非线性特征,根据C-C算法确定重构参数(嵌入维数及延迟时间)并对风速重构相空间,建立径向基函数神经网络(RBF网络)及Volterra自适应预测模型对风速时间序列进行预测,以Lorenz方程数值解为例验证了两种预测方法的可行性。结果表明:RBF神经网络模型和Volterra自适应预测模型都能对实测风速时间序列进行较为准确的预测,预测误差分别在0.3和0.1 m/s内;Volterra自适应预测模型预测结果总体较RBF神经网络模型预测精度更高,且随着预测时间的增大,预测误差呈增大趋势,这与混沌存在初值敏感性的特征相符。     

A novel approach for the forecasting of mean hourly wind speed time series

This paper presents a novel method for the forecasting of mean hourly wind speed data using time series analysis. The initial point for this approach is mainly the fact that none of the forecasting approaches for hourly data, that can be found in the literature, based on time series analysis or meteorological models, gives significantly lower prediction error than the elementary persistent approach. This was combined with the characteristics of the wind speed data, which are determined by the power spectrum values, distinguished by the spectral gap in intervals between 20 minutes and 2 hours. The finally proposed methodology is based on the multi-step forecasting of 10 minutes averaged data and the subsequent averaging to generate mean hourly predictions. When applied to two independent data sets, this approach outperformed by a factor of four, the conventional one which utilizes past mean hourly wind speed values as inputs to the forecasting models.     

Very short-term wind speed forecasting with Bayesian structural break model

This paper examines a new time series method for very short-term wind speed forecasting. The time series forecasting model is based on Bayesian theory and structural break modeling, which could incorporate domain knowledge about wind speed as a prior. Besides this Bayesian structural break model predicts wind speed as a set of possible values, which is different from classical time series model's single-value prediction This set of predicted values could be used for various applications, such as wind turbine predictive control, wind power scheduling. The proposed model is tested with actual wind speed data collected from utility-scale wind turbines.     

基于熵权时序模型的超短期风电功率预测

针对风电具有较强的随机性和波动性,传统的单一预测方法难以准确描述其规律且预测精度较低的问题,提出风速熵和功率熵的概念,在时间序列法的基础上分别采用基于风速和基于功率的预测方法,并根据风速熵和功率熵的计算结果动态设置预测点的权值,建立风电功率的熵权时序模型。算例分析结果表明,所提方法能有效提取风速及功率历史数据中的有用信息,提高超短期风电功率预测精度,预测结果的准确率和合格率均优于神经网络法、时间序列法和基于风速法。     

测风数据间隔对风速预测精度影响的研究

风速预测对风电场控制和电网调度具有十分重要的意义。文章以不同时间间隔的测风数据为基础,采用时间序列法和人工神经网络法对风速进行预测,通过比较风速预测绝对平均误差,说明时间间隔较短时,采用BP神经网络预测精度较高;当时间间隔增大时,采用时间序列法预测精度较高;时间间隔过大,即风速数据太少时,两种预测方法误差都较大,须谨慎使用。该研究结果对风电机组控制系统的设计以及电网调度计划的制定具有参考价值。     

风电场风速预测模型研究

介绍了两种风电场风速预测模型,分别是BP神经网络模型和小波-BP神经网络组合模型。BP神经网络模型是风速预测中常用的模型之一,小波技术和BP神经网络结合,即为组合模型。小波技术将风速时间序列按时间和频率两个方向展开,体现了各成分对预测值贡献率的不同。将BP神经网络模型和小波-BP神经网络组合模型分别应用到我国朱日和风电场的逐时风速预测中,从预测结果对比得出组合模型更适合该风电场的逐时风速预测。     

A new strategy for predicting short-term wind speed using soft computing models

Wind power prediction is a widely used tool for the large-scale integration of intermittent wind-powered generators into power systems. Given the cubic relationship between wind speed and wind power, accurate forecasting of wind speed is imperative for the estimation of future wind power generation output. This paper presents a performance analysis of short-term wind speed prediction techniques based on soft computing models (SCMs) formulated on a backpropagation neural network (BPNN), a radial basis function neural network (RBFNN), and an adaptive neuro-fuzzy inference system (ANFIS). The forecasting performance of the SCMs is augmented by a similar days (SD) method, which considers similar historical weather information corresponding to the forecasting day in order to determine similar wind speed days for processing. The test results demonstrate that all evaluated SCMs incur some level of performance improvement with the addition of SD pre-processing. As an example, the SD+ANFIS model can provide up to 48% improvement in forecasting accuracy when compared to the individual ANFIS model alone.     

A neural network approach to local downscaling of GCM output for assessing wind power implications of climate change

A methodology is presented for downscaling General Circulation Model (GCM) output to predict surface wind speeds at scales of interest in the wind power industry under expected future climatic conditions. The approach involves a combination of Neural Network tools and traditional weather forecasting techniques. A Neural Network transfer function is developed to relate local wind speed observations to large scale GCM predictions of atmospheric properties under current climatic conditions. By assuming the invariability of this transfer function under conditions of doubled atmospheric carbon dioxide, the resulting transfer function is then applied to GCM output for a transient run of the National Center for Atmospheric Research coupled ocean-atmosphere GCM. This methodology is applied to three test sites in regions relevant to the wind power industry—one in Texas and two in California. Changes in daily mean wind speeds at each location are presented and discussed with respect to potential implications for wind power generation.     

Complex-valued forecasting of wind profile

This paper presents a novel approach for the simultaneous modelling and forecasting of wind signal components. This is achieved in the complex domain by using novel neural network algorithms and architectures. We first perform a signal nonlinearity and component-dependent analyses, which suggest the use of modular complex-valued recurrent neural networks (RNNs). This RNN-based modelling rests upon a combination of nonlinearity, complexity and internal memory and allows for the multiple step ahead forecasting of the wind signal in its complex form (speed and direction). The approach is first verified on benchmark Data Set A (NH₃ laser data) of the Santa Fe Time Series Prediction Competition together with artificial data generated by chaotic Mackey–Glass equations, and then applied to the real-world wind measurements. Simulations support the proposed architecture and algorithms.     

基于混沌分析和神经网络的风速直接多步预测

针对风速序列的混沌特性,提出了一种将混沌分析和神经网络相结合的短期风速直接多步预测新方法,以提高其预测精度。首先,对风速序列进行混沌特性分析和相空间重构;然后,根据重构相空间的特征参数,结合预测需求,确定Elman网络结构;最后,利用空间欧式距离选取的样本对Elman网络进行训练,建立风速直接多步预测模型。以华北地区某风电场实测风速为例进行仿真测试,结果表明与单步迭代法和直接神经网络法相比,该文方法在进行风速直接多步预测时具有更好的整体误差指标。     

Short term wind speed forecasting in La Venta,Oaxaca, México,using artificial neural networks

In this paper the short term wind speed forecasting in the region of La Venta, Oaxaca, Mexico, applying the technique of artificial neural network (ANN) to the hourly time series representative of the site is presented. The data were collected by the Comisión Federal de Electricidad (CFE) during 7 years through a network of measurement stations located in the place of interest. Diverse configurations of ANN were generated and compared through error measures, guaranteeing the performance and accuracy of the chosen models. First a model with three layers and seven neurons was chosen, according to the recommendations of diverse authors, nevertheless, the results were not sufficiently satisfactory so other three models were developed, consisting of three layers and six neurons, two layers and four neurons and two layers and three neurons. The simplest model of two layers, with two input neurons and one output neuron, was the best for the short term wind speed forecasting, with mean squared error and mean absolute error values of 0.0016 and 0.0399, respectively. The developed model for short term wind speed forecasting showed a very good accuracy to be used by the Electric Utility Control Centre in Oaxaca for the energy supply.