基于AdaBoost与BP神经网络的风速预测研究

介绍了基于AdaBoost的多神经网络集成预测方法。集成方法的预测结果优于其他方法的预测结果,这一点在理论上和经验上已经得到证明。AdaBoost是适用于时间序列预测的集成方法。基于AdaBoost算法,采用多个BP神经网络训练随机生成的风速样本,再由多个训练结果生成最终的风速预测值。用该方法预测的误差低于用单一BP神经网络进行的预测,其分析和仿真结果表明了其优越性。     

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...     

A prediction approach using ensemble empirical mode decomposition‐permutation entropy and regularized extreme learning machine for short‐term wind speed

Accurate prediction of short‐term wind speed is of great significance to the operation and maintenance of wind farms, the optimal scheduling of turbines, and the safe and stable operation of power grids. A prediction approach for short‐term wind speed using ensemble empirical mode decomposition‐permutation entropy and regularized extreme learning machine is proposed. Firstly, wind speed time series is decomposed into several components with different frequency by ensemble empirical mode decomposition, which can reduce the non‐stationarity of the original time series. The permutation entropy value for each component is used to analyze its complexity. The components can be recombined to obtain a set of new subsequences. Then, different prediction models based on regularized extreme learning machine are used to predict each subsequence. Fivefold cross validation is used to improve the reliability of the regularized extreme learning machine model. Finally, the predicted value of each subsequence is superimposed to obtain the final predictive result. Ten minutes, 30 minutes, and 1 hour short‐term wind speed data from wind farms in Liaoning Province, China, are used for conducting experiments. The experimental results indicate that the values of the root mean square error of the developed prediction approach utilizing 10 minutes, 30 minutes, and 1 hour interval data are 0.5629, 0.4473, and 0.5697; mean absolute error are 0.4427, 3.0701, and 0.4897; mean absolute percentile error are 4.1456%, 16.8166%, and 6.8166%; relative root mean square are 0.0505, 0.2997, and 0.2609; square sum error are 55.5263, 59.6347, and 64.9154; and the Theil inequality coefficient are 0.0235, 0.0808, and 0.0625, which are much lower than those of the comparison methods. The values of the R square of the developed prediction approach utilizing 10 minutes, 30 minutes, and 1 hour interval data are 0.9363, 0.9161, and 0.9472, and the index of agreement are 0.9994, 0.9925, and 0.9894, which are higher than those of the comparison methods. The Pearson's test results show that the association strength between the actual value and the predicted values of the proposed approach is stronger. Also, the proposed prediction approach in this paper has higher reliability under the same confidence level. The effectiveness of the proposed prediction approach for short‐term wind speed is verified.     

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.     

基于风速误差校正和ALO-LSSVM的风电功率预测

风资源的随机波动性引起的相位滞后性问题,导致风电功率预测精度不高,尤其是风速变化较快时,滞后性引起的预测误差较大。考虑到风速波动与风功率变化密切相关,提出一种非参数核密度估计和数值天气预报(NWP)相结合的方法,并对预测风速误差进行校正,改善了预测风速的相位滞后性;然后将校正后的风速和风功率作为输入数据进行风电功率预测;采用蚁狮算法(ALO)优化最小二乘支持向量机(LSSVM)参数,从而建立基于风速误差校正和ALO-LSSVM组合的风电功率预测模型。算例结果表明,所提方法风功率预测精度更高。     

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.     

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.     

基于变分模式分解和深度门控循环网络的风速短期预测模型

考虑到风速时间序列非平稳特性和时序关联难以建模的问题,提出一种基于变分模态分解和深度门控循环网络的风速短期预测模型。该模型首先使用变分模态分解非递归地将原始风速序列分解为预先设定层数的子分量,以期降低原始序列的不平稳度,使用深度门控网络分别对各子分量建模预测,最后叠加各分量的预测结果,得到风速的预测结果。实例研究表明所提模型能够有效地跟踪风速的变化,具有较高的短期预测精度。     

Short term wind speed forecasting for wind turbine applications using linear prediction method

In this paper a new method, based on linear prediction, is proposed for wind speed forecasting. The method utilizes the ‘linear prediction’ method in conjunction with ‘filtering’ of the wind speed waveform. The filtering eliminates the undesired parts of the frequency spectrum (i.e. smoothing) of the measured wind speed which is less effective in an application, for example, in a wind energy conversion system. The linear prediction method is intuitively explained with some easy to follow case studies to clarify the complex underlying mathematics. For verification purposes, the proposed method is compared with real wind speed data based on experimental results. The results show the effectiveness of the linear prediction method.     

基于物理原理的风电场短期风速预测研究

对符合功率预测要求的短期风速预测进行研究,提出了基于物理原理的预测方法,该方法以数值天气预报(Numerical-Weather-Prediction,NWP)风速为输入数据,采用粗糙度变化模型与地形变化模型反映风电场局地效应对大气边界层风的影响;通过与不同风况下的实测风速进行比较,表明预测结果基本能满足预测精度的要求,但预测准确性会随风速变化剧烈程度的增强而有所降低;根据误差分析,NWP风速的准确性是影响预测结果的最主要因素。     

基于最优邻域的动态加权混沌风速预测模型

提出了短期风速的混沌预测方法。首先利用关联积分法确定滞时和嵌入维数,重构风速时间序列的相空间。在此基础上,采用基于最优邻域的动态加权混沌预测模型进行风速预测。该模型综合考虑了邻近点权重和广义自由度,能够给出确定最优邻域的判定指标。实际计算中对2个测风点的数据进行了预测分析,结果表明,在合适的模型参数条件下,该方法可取得较好的预测效果,邻近点权重的引入确实提高了模型的预测精度。     

基于改进经验小波变换和最小二乘支持向量机的短期风速预测

针对原始风速信号非线性和非平稳性的特征,提出一种新的改进经验小波变换(IEWT)方法,该方法可将风速信号分解成一组有限带宽的子序列,以降低其不稳定性。在此基础上,结合最小二乘支持向量机(LSSVM),提出基于改进经验小波变换和最小二乘支持向量机(IEWT-LSSVM)的短期风速预测方法,并通过模拟退火粒子群优化算法(SAPSO)对相空间重构参数以及LSSVM模型的2个超参数进行共同优化。最后以华北某风电场采集的风速信号为算例,结果表明基于IEWT-LSSVM的预测模型能有效追踪风速信号的变化,在单步预测和多步预测上均具有较高的预测精度。     

Anticipatory Control of Wind Turbines With Data-Driven Predictive Models

The concept of anticipatory control applied to wind turbines is presented. Anticipatory control is based on the model predictive control (MPC) approach. Unlike the MPC method, noncontrollable variables (such as wind speed) are directly considered in the dynamic equations presented in the paper to predict response variables, e.g., rotor speed and turbine power output. To determine future states of the power drive with the dynamic equations, a time series model was built for wind speed. The time series model was fused with the dynamic equations to predict the response variables over a certain prediction horizon. Based on these predictions, an optimization model was solved to find the optimal control settings to improve the power output without incurring large rotor speed changes. As both the dynamic equations and time series model were built by data mining algorithms, no gradient information is available. A modified evolutionary strategy algorithm was used to solve a nonlinear constrained optimization problem. The proposed approach has been tested on the data collected from a 1.5 MW wind turbine.      

Extraction of synoptic pressure patterns for long-term wind speed estimation in wind farms using evolutionary computing

In this paper we present an evolutionary approach for the problem of discovering pressure patterns under a quality measure related to wind speed and direction. This clustering problem is specially interesting for companies involving in the management of wind farms, since it can be useful for analysis of results of the wind farm in a given period and also for long-term wind speed prediction. The proposed evolutionary algorithm is based on a specific encoding of the problem, which uses a dimensional reduction of the problem. With this special encoding, the required centroids are evolved together with some other parameters of the algorithm. We define a specific crossover operator and two different mutations in order to improve the evolutionary search of the proposed approach. In the experimental part of the paper, we test the performance of our approach in a real problem of pressure pattern extraction in the Iberian Peninsula, using a wind speed and direction series in a wind farm in the center of Spain. We compare the performance of the proposed evolutionary algorithm with that of an existing weather types (WT) purely meteorological approach, and we show that the proposed evolutionary approach is able to obtain better results than the WT approach.     

基于卷积和共享权系数长短时记忆网络时融合机制在风速预测上的应用研究

针对对于风能规划和应用都具有重大影响的风速存在强随机性问题,该文提出结合卷积神经网络（CNN）和共享权重长短期记忆网络（SWLSTM）的空时融合模型（CSWLSTM）,充分提取风速序列中蕴含的空域和时域信息,以提升预测精度。此外,为了获得可靠的风速概率预测结果,提出一种新的结合CNN、SWLSTM和高斯过程回归（GPR）的混合模型,称为 CSWLSTM-GPR。将CSWLSTM-GPR应用于中国内蒙古风速预测案例,从点预测精度、区间预测适用性和概率预测综合性能3个方面与相同结构的CNN和SWLSTM模型的风速预测方法进行比较。CSWLSTM-GPR的可靠性测试保证了预测结果的可靠性和说服力。实验结果表明,CSWLSTM-GPR在风速预测问题上能获得高精度的点预测、合适的预测区间和可靠的概率预测结果,也充分展现了该研究所提出CSWLSTM在风速预测方面具有较好的应用潜力。     

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。     

A novel method based on Weibull distribution for short-term wind speed prediction

Wind speed prediction (WSP) is essential in order to predict and analyze efficiency and performance of wind-based electricity generation systems. More accurate WSP may provide better opportunities to design and build more efficient and robust wind energy systems. Precious short-term prediction is difficult to achieve; therefore several methods have been developed so far. We notice that the statistics of the alterations, which occur between sequential values of the predicted wind speed data, may differ significantly from observed wind statistics. In this study, we investigate these alterations and compare them and, accordingly, propose a novel method based on Weibull and Gaussian probability distribution functions (PDF) for short-term WSP. The proposed method stands on an algorithm, which examines comparison of the statistical features of the observed and generated wind speed in order to achieve more accurate estimation. We have examined this method on the wind speed data set observed and recorded in Ankara in 2013 and in 2014. The obtained results show that the new algorithm provides better wind speed prediction with an enhanced wind speed model.     

Hybrid boosting algorithms and artificial neural network for wind speed prediction

Energy sources are an important foundation for national economic growth. The future of energy sources depend on the energy controls. The reserves of fossil energy have declined significantly, and environmental pollution has increased dramatically due to excessive fossil fuel consumption. At this point, wind energy can be used as one of the key source of renewable energy. It has a remarkable importance among the low-carbon energy technologies. The primary aim of wind energy production is to reduce dependence on fossil fuels that affect environment adversely. Therefore, wind energy is analyzed to develop new energy resources. The main issue related to evaluation of the wind energy potential is wind speed prediction. Due to the high volatile and irregular nature of wind speed, wind speed prediction is difficult. To cope with complex data structure, this study presents the development of extreme gradient boosting (XGBoost), adaptive boosting (AdaBoost), and artificial neural network (ANN) within particle swarm optimization (PSO) parameter optimization for hourly wind speed prediction. To compare the proposed hybrid methods, various performance measures, the Pearson's test, and the Taylor diagram are used. The results showed that proposed hybrid methods provide reasonable prediction results for wind speed prediction.     

Wind speed forecast model for wind farm based on a hybrid machine learning algorithm

This paper presents a new strategy for wind speed forecasting based on a hybrid machine learning algorithm, composed of a data filtering technique based on wavelet transform (WT) and a soft computing model based on the fuzzy ARTMAP (FA) network. The prediction capability of the proposed hybrid WT+FA model is demonstrated by an extensive comparison with some other existing wind speed forecasting methods. The results show a significant improvement in forecasting error through the application of a proposed hybrid WT+FA model. The proposed wind speed forecasting strategy is applied to real data acquired from the North Cape wind farm located in PEI, Canada.     

基于小波变换的输电线路绝缘子串风偏模拟研究

为提高输电线路绝缘子串风偏角的预测精度,减少因风偏引起的输电线路故障,提出在Matlab系统中对实测脉动风速进行数值分析及多项式拟合,基于小波变换理论对拟合风速所产生的风偏角时程进行分解、重构,求出绝缘子串在10 min内的最大风偏角,在一典型220 kV输电线路模型上的应用表明,该方法不仅考虑了脉动风的影响且简洁、实用、合理。