Performance analysis of modeling framework for prediction in wind farms employing artificial neural networks

This paper introduces the concept and practice of Neural Network architectures for wind speed prediction in wind farms. The wind speed prediction method has been analyzed by using back propagation network and radial basis function network. Artificial neural network is used to develop suitable architecture for predicting wind speed in wind farms. The key of wind speed prediction is rational selection of forecasting model and effective optimization of model performance. To verify the effectiveness of neural network architecture, simulations were conducted on real time wind data with different heights of wind mill. Due to fluctuation and nonlinearity of wind speed, accurate wind speed prediction plays a major role in the operational control of wind farms. The key advantages of Radial Basis Function Network include higher accuracy, reduction of training time and minimal error. The experimental results show that compared to existing approaches, proposed radial basis function network performs better in terms of minimization of errors.     

Bayesian inference for wind field retrieval

In many problems in spatial statistics it is necessary to infer a global problem solution by combining local models. A principled approach to this problem is to develop a global probabilistic model for the relationships between local variables and to use this as the prior in a Bayesian inference procedure. We use a Gaussian process with hyper-parameters estimated from numerical weather prediction models, which yields meteorologically convincing wind fields. We use neural networks to make local estimates of wind vector probabilities. The resulting inference problem cannot be solved analytically, but Markov Chain Monte Carlo methods allow us to retrieve accurate wind fields.     

Forecasting wind speed using empirical mode decomposition and Elman neural network

Because of the chaotic nature and intrinsic complexity of wind speed, it is difficult to describe the moving tendency of wind speed and accurately forecast it. In our study, a novel EMD–ENN approach, a hybrid of empirical mode decomposition (EMD) and Elman neural network (ENN), is proposed to forecast wind speed. First, the original wind speed datasets are decomposed into a collection of intrinsic mode functions (IMFs) and a residue by EMD, yielding relatively stationary sub-series that can be readily modeled by neural networks. Second, both IMF components and residue are applied to establish the corresponding ENN models. Then, each sub-series is predicted using the corresponding ENN. Finally, the prediction values of the original wind speed datasets are calculated by the sum of the forecasting values of every sub-series. Moreover, in the ENN modeling process, the neuron number of the input layer is determined by a partial autocorrelation function. Four prediction cases of wind speed are used to test the performance of the proposed hybrid approach. Compared with the persistent model, back-propagation neural network, and ENN, the simulation results show that the proposed EMD–ENN model consistently has the minimum statistical error of the mean absolute error, mean square error, and mean absolute percentage error. Thus, it is concluded that the proposed approach is suitable for wind speed prediction.     

EMD与NARX神经网络的风电场总功率组合预测

探索构建对风电场总功率进行直接预测的高精度组合预测算法。考虑到风速的非平稳性导致风电总功率表现为非平稳时间序列,采用NARX神经网络作为初步预测模型,提出了经验模态分解与NARX神经网络相结合的混合预测模型。对风电场总功率非平稳时间序列进行经验模态分解,得到不同频带本征模式分量的平稳序列。对不同频带的平稳分量建立相应的NARX神经网络预测模型,并将各分量模型的预测值进行等权求和得到最终预测值。此外,为研究不同时间间隔对预测结果的影响,采用某大型风电场时间间隔为5 min与15 min的数据进行实验。预测结果表明,提出的组合预测模型适合于总功率预测,其预测效果比传统模型的效果更佳,且时间间隔为5 min的数据比时间间隔为15 min的数据预测精度更高。     

Locally recurrent neural networks for wind speed prediction using spatial correlation

This paper deals with the wind speed prediction in wind farms, using spatial information from remote measurement stations. Owing to the temporal complexity of the problem, we employ local recurrent neural networks with internal dynamics, as advanced forecast models. To improve the prediction performance, the training task is accomplished using on-line learning algorithms based on the recursive prediction error (RPE) approach. A global RPE (GRPE) learning scheme is first developed where all adjustable weights are simultaneously updated. In the following, through weight grouping we devise a simplified method, the decoupled RPE (DRPE), with reduced computational demands. The partial derivatives required by the learning algorithms are derived using the adjoint model approach, adapted to the architecture of the networks being used. The efficiency of the proposed approach is tested on a real-world wind farm problem, where multi-step ahead wind speed estimates from 15 min to 3 h are sought. Extensive simulation results demonstrate that our models exhibit superior performance compared to other network types suggested in the literature. Furthermore, it is shown that the suggested learning algorithms outperform three gradient descent algorithms, in training of the recurrent forecast models.     

Comparative analysis on hidden neurons estimation in multi layer perceptron neural networks for wind speed forecasting

In this paper methodologies are proposed to estimate the number of hidden neurons that are to be placed numbers in the hidden layer of artificial neural networks (ANN) and certain new criteria are evolved for fixing this hidden neuron in multilayer perceptron neural networks. On the computation of the number of hidden neurons, the developed neural network model is applied for wind speed forecasting application. There is a possibility of over fitting or under fitting occurrence due to the random selection of hidden neurons in ANN model and this is addressed in this paper. Contribution is done in developing various 151 different criteria and the evolved criteria are tested for their validity employing various statistical error means. Simulation results prove that the proposed methodology minimized the computational error and enhanced the prediction accuracy. Convergence theorem is employed over the developed criterion to validate its applicability for fixing the number of hidden neurons. To evaluate the effectiveness of the proposed approach simulations were carried out on collected real-time wind data. Simulated results confirm that with minimum errors the presented approach can be utilized for wind speed forecasting. Comparative analysis has been performed for the estimation of the number of hidden neurons in multilayer perceptron neural networks. The presented approach is compact, enhances the accuracy rate with reduced error and faster convergence.     

基于NARX神经网络的热负荷预测中关键影响因素分析

在区域供热（DH）网络中,精确预测热负荷已被认为是提高效率和节省成本的重要环节。为了提高预测精度,研究不同影响因素对热负荷预测的影响极为重要。使用引入不同影响因素的数据集训练得到带外部输入的非线性自回归（NARX）神经网络模型,并比较其预测性能,以讨论直接太阳辐射和风速对热负荷预测的影响程度。实验结果表明,直接太阳辐射和风速都是热负荷预测中的关键影响因素。只引入风速时,预测模型的平均绝对百分比误差（MAPE）和均方根误差（RMSE）均低于只引入直接太阳辐射,同时引入风速和直接太阳辐射能够得到最佳的模型预测性能,但是对于MAPE和RMSE降低的贡献不大。     

Estimating the energy production of the wind turbine using artificial neural network

Due to fluctuating weather conditions, estimating wind energy potential is still a significant problem. Artificial neural networks (ANNs) have been commonly used in short-term and just-in-time modeling of wind power generation systems based on main weather parameters such as wind speed, temperature, and humidity. Two different datasets called hourly main weather data (MWD) and daily sub-data (DSD) are used to estimate a wind turbine power generation in this study. MWD are based on historically observed wind speed, wind direction, air temperature, and pressure parameters. Besides, DSD created with statistical terms of MWD consist of maximum, minimum, mean, standard deviation, skewness, and kurtosis values. The main purpose of this study in particular was to develop a multilinear model representing the relationship between the DSD with the calculated minimum (P _min) and maximum (P _max) power generation values as well as the total power generation (P _sum) produced in a day by a wind turbine based on the MWD. While simulation values of the turbine, P _min, P _max, and P _sum, were used as the separately dependent parameters, DSD were determined as independent parameters in the estimation models. Stepwise regression was used to determine efficient independent parameters on the dependent parameters and to remove the inefficient parameters in the exploratory phase of study. These efficient parameters and simulated power generation values were used for training and testing the developed ANN models. Accuracy test results show that interoperability framework models based on stepwise regression and the neural network models are more accurate and more reliable than a linear approach.     

Dynamic ensemble wind speed prediction model based on hybrid deep reinforcement learning

Prediction of wind speed can provide a reference for the reliable utilization of wind energy. This study focuses on 1-hour, 1-step ahead deterministic wind speed prediction with only wind speed as input. To consider the time-varying characteristics of wind speed series, a dynamic ensemble wind speed prediction model based on deep reinforcement learning is proposed. It includes ensemble learning, multi-objective optimization, and deep reinforcement learning to ensure effectiveness. In part A, deep echo state network enhanced by real-time wavelet packet decomposition is used to construct base models with different vanishing moments. The variety of vanishing moments naturally guarantees the diversity of base models. In part B, multi-objective optimization is adopted to determine the combination weights of base models. The bias and variance of ensemble model are synchronously minimized to improve generalization ability. In part C, the non-dominated solutions of combination weights are embedded into a deep reinforcement learning environment to achieve dynamic selection. By reasonably designing the reinforcement learning environment, it can dynamically select non-dominated solution in each prediction according to the time-varying characteristics of wind speed. Four actual wind speed series are used to validate the proposed dynamic ensemble model. The results show that: (a) The proposed dynamic ensemble model is competitive for wind speed prediction. It significantly outperforms five classic intelligent prediction models and six ensemble methods; (b) Every part of the proposed model is indispensable to improve the prediction accuracy.     

计及光伏及风电并网的电力系统短期负荷预测

为提升光伏、风电等分布式能源大量接入电网后短期电力负荷的预测精度,促进电网消纳能力提升,本文对光伏出力及短期用电负荷采用小波——径向基函数(RBF)神经网络预测方法;对风力发电首先利用总体平均经验模态分解(EEMD)方法对其功率数据分解,再采用BP神经网络、RBF神经网络、小波神经网络、ELMAN神经网络四种神经网络预测方法进行预测,并用粒子群算法(PSO)和灰色关联度(GRA)修正。最后,利用等效负荷的概念,分析光伏、风力发电并网对于短期电力负荷预测的影响,并将三种模型有效结合,得到了考虑光伏及风力发电并网的电力系统短期负荷预测的等效负荷预测模型。实例分析表明,本文所提方法相较于其他方法在该预测项目上具有相对更高的预测精度。     

基于关联规则的PSO-Elman短期风速预测

传统神经网络在短期风速预测中,存在易陷入局部极值和动态性能不足等问题,从而导致风速预测精度较低。为了提高风速预测精度,提出一种基于关联规则的粒子群优化Elman神经网络风速预测模型。利用粒子群算法优化Elman神经网络模型参数,以提高算法的收敛速度,避免陷入局部极值,以得到最优的预测值。同时结合关联规则分析考虑气象因素,采用Apriori算法对风速与其他气象因素进行关联规则挖掘,并利用得到的关联规则对风速预测值进行修正与补偿。实验结果表明,所提出的预测模型的预测效果比传统模型的效果更佳,同时验证了结合关联规则考虑气象因素能够降低风速预测误差。     

基于混合卷积神经网络算法的风场预测研究

在农业生产中,准确的风速预报对农作物安全防范有着至关重要的作用。针对云南地区的高海拔和多山,基于卷积神经网络框架,提出了卷积长短时序分析神经网络-卷积门控循环单元神经网络(ConvLSTM-ConvGRU)混合风速预测模型。通过神经网络框架的改进,有效的提高了模型对风场空间特征的提取。利用美国国家环境预报中心(NCEP)提供的再分析风速数据集,使用ConvLSTM、ConvGRU、ConvLSTM-ConvGRU混合模型分别对云南地区的风速进行。实验结果表明：ConvLSTM-ConvGRU混合风速预测模型能够有效对云南地区风场进行预测,相较于另外两个模型提高了预测准确度。     

基于CNN-LSTM的短期风电功率预测

短期风电功率预测对电力系统的安全稳定运行和能源的优化配置具有重要意义。鉴于卷积神经网络(CNN)高效的数据特征提取能力,以及长短期记忆网络(LSTM)描述时间序列长期依赖关系的能力。为了提高短期风电功率预测的精度,设计了一种基于CNN和LSTM的风电功率预测模型。该模型利用卷积神经网络对风电功率、风速、风向数据进行多层卷积和池化堆叠计算,提取风电功率相关数据的特征图谱。为了描述风电功率序列的时序依从关系,将图谱特征信息作为长短期记忆网络的输入信息,计算得到风电功率的预测结果。采用西班牙某风电场的实测数据进行模型预测精度验证。结果表明,该模型较LSTM、Elman模型具有更好的预测性能。     

Multiscale prediction of wind speed and output power for the wind farm

This paper focuses on establishing the multiscale prediction models for wind speed and power in wind farm by the average wind speed collected from the history records. Each type of the models is built with different time scales and by different approaches. There are three types of them that a short-term model for a day ahead is based on the least squares support vector machine (LSSVM), a medium-term model for a month ahead is on the combination of LSSVM and wavelet transform (WT), and a long-term model for a year ahead is on the empirical mode decomposition (EMD) and recursive least square (RLS) approaches. The simulation studies show that the average value of the mean absolute percentage error (MAPE) is 4.91%, 6.57% and 16.25% for the short-term, the medium-term and the long-term prediction, respectively. The predicted data also can be used to calculate the predictive values of output power for the wind farm in different time scales, combined with the generator’s power characteristic, meteorologic factors and unit efficiency under various operating conditions.     

Survey of four models of probability density functions of wind speed and directions by adaptive neuro-fuzzy methodology

The probabilistic distribution of wind speed is one of the discriminating wind qualities for the assessment of wind energy potential and for the execution of wind energy conversion frameworks. The wind energy spread might be obtained when wind speed probability function is known. Thusly, the probability movement of wind speed is an uncommonly huge touch of information needed in the assessment of wind energy potential. The two-parameter Weibull circulation has been normally used, recognized and endorsed in expositive interpretation to express the wind speed repeat transport for most wind regions. The Gumbel and Frechet dissemination is frequently used to model large wind speeds. The joint probability density functions (JPDF) model is advanced by minimal disseminations of wind speed and wind direction that is expected as an Extreme-Value mathematical statement. In the present study an exertion has been made to figure out the best fitting circulation of wind speed information by a soft computing methodology. We used adaptive neuro-fuzzy inference framework (ANFIS) in this paper, which is a specific kind of the neural frameworks family, to foresee the wind speed probability density dispersion. For this reason, two parameters Weibull and JPDF and three parameter Frechet and Gumbel conveyances are fitted to data and parameters for each distribution and utilized as preparing and checking information for ANFIS model. At long last, ANFIS effects are contrasted and the four introduced appropriations recommending that ANFIS conveyances are discovered to be most suitable as contrasted with the Weibull, JPDF, Frechet and Gumbel circulations.     

A novel hybrid model for short-term wind power forecasting

Wind energy prediction has a significant effect on the planning, economic operation and security maintenance of the wind power system. However, due to the high volatility and intermittency, it is difficult to model and predict wind power series through traditional forecasting approaches. To enhance prediction accuracy, this study developed a hybrid model that incorporates the following stages. First, an improved complete ensemble empirical mode decomposition with adaptive noise technology was applied to decompose the wind energy series for eliminating noise and extracting the main features of original data. Next, to achieve high accurate and stable forecasts, an improved wavelet neural network optimized by optimization methods was built and used to implement wind energy prediction. Finally, hypothesis testing, stability test and four case studies including eighteen comparison models were utilized to test the abilities of prediction models. The experimental results show that the average values of the mean absolute percent errors of the proposed hybrid model are 5.0116% (one-step ahead), 7.7877% (two-step ahead) and 10.6968% (three-step ahead), which are much lower than comparison models.     

基于多模式的我国冬季风速预报误差特性分析

风电在我国能源结构转型中具有重要地位,但其波动性也带来严峻挑战。数值模式预报的风速数据是风电出力预测和高效消纳的重要基础,需要评估不同模式的预报效果。本文通过对比分析4种主流数值模式的风速预报效果,全面评估它们在我国冬季不同区域和不同条件下的预报精度,以期为我国冬季大风期风速预报提供参考。基于不同分辨率、不同初始场、不同同化方案的4种数值预报模式,结合我国131个站点观测资料,对预报风速的误差分布特征与预报能力进行了研究与分析;同时聚焦典型站点,分析了不同风速段、不同区域的预报误差特征及预报能力。研究结果表明：集合预报模式的预报结果在复杂地形条件下更科学;高分率单一模式对简单下垫面的风速波动性预报较好;白天预报效果好于夜间;对平原风速预报效果最好。     

Ordinal and nominal classification of wind speed from synoptic pressurepatterns

Wind speed reconstruction is a challenging problem in areas (mainly wind farms) where there are not direct wind measures available. Different approaches have been applied to this reconstruction, such as measure-correlate-predict algorithms, approaches based on physical models such as reanalysis methods, or more recently, indirect measures such as pressure, and its relation to wind speed. This paper adopts the latter method, and deals with wind speed estimation in wind farms from pressure measures, but including different novelties in the problem treatment. Existing synoptic pressure-based indirect approaches for wind speed estimation are based on considering the wind speed as a continuous target variable, estimating then the corresponding wind series of continuous values. However, the exact wind speed is not always needed by wind farm managers, and a general idea of the level of speed is, in the majority of cases, enough to set functional operations for the farm (such as wind turbines stop, for example). Moreover, the accuracy of the models obtained is usually improved for the classification task, given that the problem is simplified. Thus, this paper tackles the problem of wind speed prediction from synoptic pressure patterns by considering wind speed as a discrete variable and, consequently, wind speed prediction as a classification problem, with four wind level categories: low, moderate, high or very high. Moreover, taking into account that these four different classes are associated to four values in an ordinal scale, the problem can be considered as an ordinal regression problem. The performance of several ordinal and nominal classifiers and the improvement achieved by considering the ordering information are evaluated. The results obtained in this paper present the support vector machine as the best tested classifier for this task. In addition, the use of the intrinsic ordering information of the problem is shown to significantly improve ranks with respect to nominal classification, although differences in accuracy aresmall.     

Wind Speed Prediction Using Chicken Swarm Optimization with Deep Learning Model

High precision and reliable wind speed forecasting have become a challenge for meteorologists. Convective events, namely, strong winds, thunderstorms, and tornadoes, along with large hail, are natural calamities that disturb daily life. For accurate prediction of wind speed and overcoming its uncertainty of change, several prediction approaches have been presented over the last few decades. As wind speed series have higher volatility and nonlinearity, it is urgent to present cutting-edge artificial intelligence (AI) technology. In this aspect, this paper presents an intelligent wind speed prediction using chicken swarm optimization with the hybrid deep learning (IWSP-CSODL) method. The presented IWSP-CSODL model estimates the wind speed using a hybrid deep learning and hyperparameter optimizer. In the presented IWSP-CSODL model, the prediction process is performed via a convolutional neural network (CNN) based long short-term memory with autoencoder (CBLSTMAE) model. To optimally modify the hyperparameters related to the CBLSTMAE model, the chicken swarm optimization (CSO) algorithm is utilized and thereby reduces the mean square error (MSE). The experimental validation of the IWSP-CSODL model is tested using wind series data under three distinct scenarios. The comparative study pointed out the better outcomes of the IWSP-CSODL model over other recent wind speed prediction models.     

A regime-switching recurrent neural network model applied to wind time series

This paper proposes a regime-switching recurrent network model (RS-RNN) for non-stationary time series. The RS-RNN model emits a mixture density with dynamic nonlinear regimes that fit flexibly data distributions with non-Gaussian shapes. The key novelties are: development of an original representation of the means of the component distributions by dynamic nonlinear recurrent networks, and derivation of a corresponding expectation maximization (EM) training algorithm for finding the model parameters. The results show that the RS-RNN applied to a real-world wind speed time series achieves standardized residuals similar to popular previous models, but it is more accurate distribution forecasting than other linear switching (MS-AR) and nonlinear neural network (MLP and RNN) models.