The application of artificial neural networks to mapping of wind speed profile for energy application in Nigeria

Modelling and prediction of wind speed are essential prerequisites in the sitting and sizing of wind power applications. The profile of wind speed in Nigeria is modelled using artificial neural network (ANN). The ANN model consists of 3-layered, feed-forward, back-propagation network with different configurations, designed using the Neural Toolbox for MATLAB. The monthly mean daily wind speed data monitored at 10 m above ground level for a period of 20 years (1983–2003) for 28 ground stations operated by the Nigeria Meteorological Services (NIMET) were used as training (18 stations) and testing (10 stations) dataset. The geographical parameters (latitude, longitude and altitude) and the month of the year were used as input data, while the monthly mean wind speed was used as the output of the network. The optimum network architecture with minimum Mean Absolute Percentage Error (MAPE) of 8.9% and correlation coefficient (r) between the predicted and the measured wind speed values of 0.9380 was obtained. The predicted monthly wind speed ranged from 0.9–13.1 m/s with an annual mean of 4.7 m/s. The model predicted wind speed values are given in the form of monthly maps, which can be easily used for assessment of wind energy potential for different locations within Nigeria.     

基于神经网络和改进相似日的光伏电站功率预测

为提高光伏电站功率预测的准确率,提出了一种基于SOM神经网络与熵权法优化关联系数的相似日预测模型,利用麻城市某100MW光伏电站的气温、相对湿度、风速及国家气象站日照时数、总云量、低云量等气象要素,采用SOM神经网络推算出预测日的三个相似日,再利用熵权法优化关联系数确定三个相似日的系数求出相似日分辨率为15min的瞬时功率,作为BP神经网络输入对光伏电站进行短期功率预测,并通过与其他四种预测模型的对比分析评估其性能。结果表明,模型的月相对均方根误差、月平均绝对百分比误差分别为5.88%、3.03%,与效果最佳的原理法模型误差接近;基于熵权法优化的关联系数和云量数据的加入对预测准确率有较大提高;模型预测准确率较高,抗扰动能力较强,可集合至本部门开发的预测系统运用到实际中。     

基于功率预测的风力机健康状态监测

随着风力发电的广泛应用,对风力机健康状态进行准确监测的重要性日益凸显,为此提出了一种基于风力机功率预测的健康状态监测方法,即结合多项式模型和自回归模型特点,考虑风速与风力机输出功率之间的相关性和滞后性,利用改进非线性自回归模型对某风场风力机输出功率进行预测,并将预测结果与传统灰色模型、BP神经网络模型预测结果进行对比,计算与实测数据之间的误差。最后,选取功率预测系数中变化较为稳定的系数项作为观测系数,通过标准残差法确定异常观测系数反推风力机健康状态。分析结果表明,改进非线性自回归模型预测值与实测数据较为接近,趋势较为吻合。相比于传统灰色模型、BP神经网络模型,改进非线性自回归模型预测误差较小,精度较高。可见通过分析功率预测系数变化能够及时发现风力机健康状态变化,为故障发现提供参考。     

基于多任务学习的风速实时预测方法

准确的秒级风速实时预测能够提高风电机组的运行状况和控制品质,为电网做出最优调度决策提供辅助信息.目前风速实时预测时间分辨率通常为分钟级,且在小数据集的情况下模型泛化能力弱.文章以时间分辨率为5s的风速序列为研究对象,提出了基于多任务学习的风速实时预测方法.该方法结合了变分模态分解方法和长短期记忆神经网络.首先,通过变分...     

Prediction of wind speed time series using modified Taylor Kriging method

Wind speed forecasting is critical for the operations of wind turbine and penetration of wind energy into electricity systems. In this paper, a novel time series forecasting method is proposed for this purpose. This method originates from TK (Taylor Kriging) model, but is properly modified for the forecasting of wind speed time series. To investigate the performance of this new method, the wind speed data from an observation site in North Dakota, USA, are adopted. One-year hourly wind speed data are divided into 10 samples, and forecast is made for each sample. In the case study, both the modified TK method and (ARIMA) autoregressive integrated moving average method are employed and their performances are compared. It is found that on average, the proposed method outperforms the ARIMA method by 18.60% and 15.23% in terms of (MAE) mean absolute error and (RMSE) root mean square error. Meanwhile, further theoretical analysis is provided to discuss why the modified TK method is potentially more accurate than the ARIMA method for wind speed time series prediction.     

Support vector machines for wind speed prediction

This paper introduces support vector machines (SVM), the latest neural network algorithm, to wind speed prediction and compares their performance with the multilayer perceptron (MLP) neural networks. Mean daily wind speed data from Madina city, Saudi Arabia, is used for building and testing both models. Results indicate that SVM compare favorably with the MLP model based on the root mean square errors between the actual and the predicted data. These results are confirmed for a system with order 1 to system with order 11.     

基于PAM-SSD-LSTM的短期风速预测

为提高短期风速预测的准确性,提出一种基于PAM聚类、奇异谱分解（SSD）和LSTM神经网络的组合预测模型来预测短期风速,以解决上述问题。首先,为提高神经网络的学习效率,采用PAM算法对原始风速数据进行相似日聚类;其次,SSD具有抑制模态混叠和虚假分量产生的优点,使用SSD分解风速序列,提取多尺度规律;最后,由于LSTM神经网络捕捉长时间依赖的序列的波动规律的能力较强,使用LSTM神经网络对分解后的风速分量进行预测,将各分量预测值叠加得到最终预测结果。实验结果表明,基于PAM-SSD-LSTM的组合预测模型可有效提高风速短期预测的准确率。     

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。     

ARMA based approaches for forecasting the tuple of wind speed and direction

Short-term forecasting of wind speed and direction is of great importance to wind turbine operation and efficient energy harvesting. In this study, the forecasting of wind speed and direction tuple is performed. Four approaches based on autoregressive moving average (ARMA) method are employed for this purpose. The first approach features the decomposition of the wind speed into lateral and longitudinal components. Each component is represented by an ARMA model, and the results are combined to obtain the wind direction and speed forecasts. The second approach employs two independent ARMA models – a traditional ARMA model for predicting wind speed and a linked ARMA model for wind direction. The third approach features vector autoregression (VAR) models to forecast the tuple of wind attributes. The fourth approach involves employing a restricted version of the VAR approach to predict the same. By employing these four approaches, the hourly mean wind attributes are forecasted 1-h ahead for two wind observation sites in North Dakota, USA. The results are compared using the mean absolute error (MAE) as a measure for forecasting quality. It is found that the component model is better at predicting the wind direction than the traditional-linked ARMA model, whereas the opposite is observed for wind speed forecasting. Utilizing VAR approaches rather than the univariate counterparts brings modest improvement in wind direction prediction but not in wind speed prediction. Between restricted and unrestricted versions of VAR models, there is little difference in terms of forecasting performance.     

Estimating daily wind speed under climate change

A semi-empirical downscaling approach is presented to estimate spatial and temporal statistical properties of local daily mean wind speed under global climate change. The present semi-empirical downscaling method consists of two elements. Since general circulation models (GCMs) are able to reproduce the features of the present atmospheric general circulation quite correctly, the first element represents the large-scale circulation of the atmosphere. The second element is a link between local wind speed and large-scale circulation pattern (CP). The linkage is expressed by a stochastic model conditioned on CP types. Parameters of the linkage model are estimated using observed data series; then this model is utilized with GCM-generated CP type data corresponding to a 2 × CO₂ scenario. Under the climate of Nebraska the lognormal distribution is the best two-parameter distribution to describe daily mean wind speed. The space-time variability of wind speed is described by a transformed multivariate autoregressive (AR) process, and the linkage between local wind and large-scale circulation is expressed as a conditional AR process, i.e. the autoregressive parameters depend on the actual daily CP type. The basic tendency of change under 2 × CO₂ climate is a considerable increase of wind speed from the beginning of summer to the end of winter and a somewhat smaller wind decrease in spring.     

基于季节指数调整的循环神经网络风速时间序列预测

提出一种基于季节指数调整的神经网络风速预测方法.针对历史风速之间的非线性关系,运用神经网络非线性拟合能力并结合季节性指数调整对风速时间序列进行预测.通过时序图法和增广Dickey-Fullerd检验法判断时间序列的平稳性,结果表明该序列为非平稳序列.这种不稳定性说明时间序列中可能包含趋势、季节性、循环和不规则成分的一种...     

Application of artificial neural networks for the wind speed prediction of target station using reference stations data

In this study, artificial neural networks (ANNs) were applied to predict the mean monthly wind speed of any target station using the mean monthly wind speeds of neighboring stations which are indicated as reference stations. Hourly wind speed data, collected by the Turkish State Meteorological Service (TSMS) at 8 measuring stations located in the eastern Mediterranean region of Turkey were used. The long-term wind data, containing hourly wind speeds, directions and related information, cover the period between 1992 and 2001. These data were divided into two sections. According to the correlation coefficients, reference and target stations were defined. The mean monthly wind speeds of reference stations were used and also corresponding months were specified in the input layer of the network. On the other hand, the mean monthly wind speed of the target station was utilized in the output layer of the network. Resilient propagation (RP) learning algorithm was applied in the present simulation. The hidden layers and output layer of the network consist of logistic sigmoid transfer function (logsig) and linear transfer function (purelin) as an activation function. Finally, the values determined by ANN model were compared with the actual data. The maximum mean absolute percentage error was found to be 14.13% for Antakya meteorological station and the best result was found to be 4.49% for Mersin meteorological station.     

Nonlinear model identification of wind turbine with a neural network

A nonlinear model of wind turbine based on a neural network (NN) is described for the estimation of wind turbine output power. The proposed nonlinear model uses the wind speed average, the standard deviation and the past output power as input data. An anemometer with a sampling rate of one second provides the wind speed data. The NN identification process uses a 10-min average speed with its standard deviation. The typical local data collected in September 2000 is used for the training, while those of October 2000 are used to validate the model. The optimal NN configuration is found to be 8-5-1 (8 inputs, 5 neurons on the hidden layer, one neuron on the output layer). The estimated mean square errors for the wind turbine output power are less than 1%. A comparison between the NN model and the stochastic model mostly used in the wind power prediction is done. This work is a basic tool to estimate wind turbine energy production from the average wind speed.     

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.     

Integration of time series forecasting in a dynamic decision support system for multiple reservoir management to conserve water sources

In most of arid and semi-arid regions, there are limited sources of available fresh water for different domestic and environmental demands. Strategic and parsimonious fresh water-use in water-scarce areas such as Southern New Mexico is crucially important. Elephant Butte and Caballo reservoirs are two integrated reservoirs in this region that provide water supply for many water users in downstream areas. Since Elephant Butte Reservoir is in a semi-arid region, it would be rational to utilize other energy sources such as wind energy to produce electricity and use the water supply to other critical demands in terms of time and availability. This study develops a strategy of optimal management of two integrated reservoirs to quantify the savable volume of water sources through optimal operation management. To optimize operations for the Elephant Butte and Caballo reservoirs as an integrated reservoir operation in New Mexico, the authors in this case study utilized two autoregressive integrated moving average models, one non-seasonal (daily, ARIMA model) and one seasonal (monthly, SARIMA model), to predict daily and monthly inflows to the Elephant Butte Reservoir. The coefficient of determination between predicted and observed daily values and the normalized mean of absolute error (NMAE) were 0.97 and 0.09, respectively, indicating that the daily ARIMA prediction model was significantly reliable and accurate for a univariate based streamflow forecast model. The developed time series prediction models were incorporated in a decision support system, which utilizes the predicted values for a day and a month ahead and leads to save significant amount of water volume by providing the optimal release schedule from Elephant Butte into the Caballo Reservoir. The predicted daily and monthly values from the developed ARIMA prediction models were integrated successfully with the dynamic operation model, which provides the optimal operation plans. The optimal operation plan significantly minimizes the total evaporation loss from both reservoirs by providing the optimal storage levels in both reservoirs. The saved volume of the water would be considered as a significant water supply for environmental conservation actions in downstream of the Caballo Reservoir. Providing an integrated optimal management plan for two reservoirs led to save significant water sources in a region that water shortage has led to significant environmental consequences. Finally, since the models are univariate, they demonstrate an approach for reliable inflow prediction when information is limited to only streamflow values. We find that hydroelectric power generation forces the region to lose significant amount of water to evaporation and therefore hinder the optimal use of freshwater. Based on these findings, we conclude that a water scarce region like Southern New Mexico should gain independence from hydroelectric power and save the freshwater for supporting ecosystem services and environmental purposes.     

A new strategy for wind speed forecasting using artificial intelligent methods

A new strategy in wind speed prediction based on fuzzy logic and artificial neural networks was proposed. The new strategy for fuzzy logic not only provides significantly less rule base but also has increased estimated wind speed accuracy when compared to traditional one. Meanwhile, applying the proposed approach to artificial neural network leads to less neuron numbers and less learning time process along with accurate wind speed prediction results. The experimental results demonstrate that the proposed method not only provides less computational time but also a better wind speed prediction performance.     

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。     

Synthesis of long-term hourly wind speed time series on the basis of European wind atlas data

A method for the synthesis of annual wind speed time series with a time resolution of 1 hour is presented. It is based upon statistical information on the wind climate given in the European Wind Atlas. The synthetic time series reproduce the monthly average daily time pattern of the site. The distribution of the synthetic wind speed data shows the correct mean value of the cubed wind speed. The site-specific variance of the wind speed and the power spectrum of the wind speed fluctuations are closely approximated. Results of time step simulations for small stand-alone wind energy systems using synthetic and measured data sets as input data show a close agreement.     

Generation of autocorrelated wind speeds for wind energy conversion system studies

This paper describes a new model and a new generator of hourly wind speeds which were obtained using the Box-Jenkins method. All the steps leading to the determination of an autoregressive model are described. Tests were performed to verify the adequacy of the model and comparisons were made between generated and real series to check whether the wind speed behavior is faithfully reproduced. Good results were obtained. In fact, hourly wind speed data prove sufficient to reproduce the main statistical characteristics of wind speed: monthly mean, standard deviation, high hourly autocorrelation and persistence. This simple model is, therefore, easily adaptable to the study of any wind energy conversion system or to mixed power system planning and reliability studies.