Estimation of variability and predictability of large‐scale wind energy in The Netherlands

This paper presents a data‐driven approach for estimating the degree of variability and predictability associated with large‐scale wind energy production for a planned integration in a given geographical area, with an application to The Netherlands. A new method is presented for generating realistic time series of aggregated wind power realizations and forecasts. To this end, simultaneous wind speed time series—both actual and predicted—at planned wind farm locations are needed, but not always available. A 1‐year data set of 10‐min averaged wind speeds measured at several weather stations is used. The measurements are first transformed from sensor height to hub height, then spatially interpolated using multivariate normal theory, and finally averaged over the market resolution time interval. Day‐ahead wind speed forecast time series are created from the atmospheric model HiRLAM (High Resolution Limited Area Model). Actual and forecasted wind speeds are passed through multi‐turbine power curves and summed up to create time series of actual and forecasted wind power. Two insights are derived from the developed data set: the degree of long‐term variability and the degree of predictability when Dutch wind energy production is aggregated at the national or at the market participant level. For a 7.8 GW installed wind power scenario, at the system level, the imbalance energy requirements due to wind variations across 15‐min intervals are ±14% of the total installed capacity, while the imbalance due to forecast errors vary between 53% for down‐ and 56% for up‐regulation. When aggregating at the market participant level, the balancing energy requirements are 2–3% higher. Copyright © 2008 John Wiley & Sons, Ltd.     

Application of probabilistic wind power forecasting in electricity markets

This paper discusses the potential use of probabilistic wind power forecasting in electricity markets, with focus on the scheduling and dispatch decisions of the system operator. We apply probabilistic kernel density forecasting with a quantile‐copula estimator to forecast the probability density function, from which forecasting quantiles and scenarios with temporal dependency of errors are derived. We show how the probabilistic forecasts can be used to schedule energy and operating reserves to accommodate the wind power forecast uncertainty. We simulate the operation of a two‐settlement electricity market with clearing of day‐ahead and real‐time markets for energy and operating reserves. At the day‐ahead stage, a deterministic point forecast is input to the commitment and dispatch procedure. Then a probabilistic forecast is used to adjust the commitment status of fast‐starting units closer to real time, on the basis of either dynamic operating reserves or stochastic unit commitment. Finally, the real‐time dispatch is based on the realized availability of wind power. To evaluate the model in a large‐scale real‐world setting, we take the power system in Illinois as a test case and compare different scheduling strategies. The results show better performance for dynamic compared with fixed operating reserve requirements. Furthermore, although there are differences in the detailed dispatch results, dynamic operating reserves and stochastic unit commitment give similar results in terms of cost. Overall, we find that probabilistic forecasts can contribute to improve the performance of the power system, both in terms of cost and reliability. Copyright © 2012 John Wiley & Sons, Ltd.     

Fault diagnosis for a wind turbine transmission system based on manifold learning and Shannon wavelet support vector machine

Fault diagnosis for wind turbine transmission systems is an important task for reducing their maintenance cost. However, the non-stationary dynamic operating conditions of wind turbines pose a challenge to fault diagnosis for wind turbine transmission systems. In this paper, a novel fault diagnosis method based on manifold learning and Shannon wavelet support vector machine is proposed for wind turbine transmission systems. Firstly, mixed-domain features are extracted to construct a high-dimensional feature set characterizing the properties of non-stationary vibration signals from wind turbine transmission systems. Moreover, an effective manifold learning algorithm with non-linear dimensionality reduction capability, orthogonal neighborhood preserving embedding (ONPE), is applied to compress the high-dimensional feature set into low-dimensional eigenvectors. Finally, the low-dimensional eigenvectors are inputted into a Shannon wavelet support vector machine (SWSVM) to recognize faults. The performance of the proposed method was proved by successful fault diagnosis application in a wind turbine's gearbox. The application results indicated that the proposed method improved the accuracy of fault diagnosis.     

电力市场环境下风-水电联合优化运行策略研究

为了促进风电场在电力市场环境下的发展,提出了一种风-水电站联合参与电力市场优化运行的策略。该策略综合考虑了从日前能量市场及调节备用容量市场中取得的收益,以期望收益最大化为目标,加入了水电站运行的限制,建立了含全天24个时段的混合整数规划模型,通过求解模型得出了各市场中的最优能量及容量申报,并基于实际的水电站与风电场参数进行了算例仿真。测试结果表明,水电站与风电场联合运行可降低风电出力的随机性对收益的负面影响,经济效益明显;风电出力的波动、能量不平衡的惩罚系数等因素都会对结果造成影响。     

Comparative performance of AI methods for wind power forecast in Portugal

Because wind has a high volatility and the respective energy produced cannot be stored on a large scale because of excessive costs, it is of utmost importance to be able to forecast wind power generation with the highest accuracy possible. The aim of this paper is to compare 1‐h‐ahead wind power forecasts performance using artificial intelligence‐based methods, such as artificial neural networks (ANNs), adaptive neural fuzzy inference system (ANFIS), and radial basis function network (RBFN). The latter was implemented using three different learning algorithms: stochastic gradient descent (SGD), hybrid, and orthogonal least squares (OLS). The application dataset is the injected wind power in the Portuguese power systems throughout the years 2010–2014. The network architecture optimization and the learning algorithms are presented. An initial data analysis showed data seasonality; therefore, the wind power forecasts were performed according to the seasons of the year. The results showed that ANFIS was the best performer method, and ANN and RBFN‐OLS also showed strong performances. RBFN‐Hybrid and RBFN‐SGD performed poorly. In general, all methods outperformed persistence.     

A new recursive neural network algorithm to forecast electricity price for PJM day‐ahead market

This paper evaluates the usefulness of publicly available electricity market information in predicting the hourly prices in the PJM day‐ahead electricity market using recursive neural network (RNN) technique, which is based on similar days (SD) approach. RNN is a multi‐step approach based on one output node, which uses the previous prediction as input for the subsequent forecasts. Comparison of forecasting performance of the proposed RNN model is done with respect to SD method and other literatures. To evaluate the accuracy of the proposed RNN approach in forecasting short‐term electricity prices, different criteria are used. Mean absolute percentage error, mean absolute error and forecast mean square error (FMSE) of reasonably small values were obtained for the PJM data, which has correlation coefficient of determination (R²) of 0.7758 between load and electricity price. Error variance, one of the important performance criteria, is also calculated in order to measure robustness of the proposed RNN model. The numerical results obtained through the simulation to forecast next 24 and 72 h electricity prices show that the forecasts generated by the proposed RNN model are significantly accurate and efficient, which confirm that the proposed algorithm performs well for short‐term price forecasting. Copyright © 2009 John Wiley & Sons, Ltd.     

Non‐parametric probabilistic forecasts of wind power: required properties and evaluation

Predictions of wind power production for horizons up to 48–72 h ahead comprise a highly valuable input to the methods for the daily management or trading of wind generation. Today, users of wind power predictions are not only provided with point predictions, which are estimates of the conditional expectation of the wind generation for each look‐ahead time, but also with uncertainty estimates given by probabilistic forecasts. In order to avoid assumptions on the shape of predictive distributions, these probabilistic predictions are produced from non‐parametric methods, and then take the form of a single or a set of quantile forecasts. The required and desirable properties of such probabilistic forecasts are defined and a framework for their evaluation is proposed. This framework is applied for evaluating the quality of two statistical methods producing full predictive distributions from point predictions of wind power. These distributions are defined by a number of quantile forecasts with nominal proportions spanning the unit interval. The relevance and interest of the introduced evaluation framework are discussed. Copyright © 2007 John Wiley & Sons, Ltd.     

Optimizing hydrogen production capacity and day ahead market bidding for a wind farm in Texas

Producing green hydrogen from wind energy is one potential method to mitigate curtailment. This study develops a general approach to examine the economic benefit of adding hydrogen production capacity through water electrolysis along with the fuel cell and storage facilities in a wind farm in north Texas. The study also investigates different day ahead market bidding strategies in the existence of these technologies. The results show that adding hydrogen capacity to the wind farm is profitable when hydrogen price is greater than $3.58/kg, and that the optimal day ahead market bidding strategy changes as hydrogen price changes. The results also suggest that both the addition of a fuel cell to reconvert stored hydrogen to electricity and the addition of a battery to smooth the electricity input to the electrolyzer are suboptimal for the system in the case of this study. The profit of a particular bidding scenario is most sensitive to the selling price of hydrogen, and then the input parameters of the electrolyzer. This study also provides policy implications by investigating the impact of different policy schemes on the optimal hydrogen production level.     

基于AEWT-KELM的风电机组轴承故障诊断策略

针对风力发电机组轴承故障振动信号传递路径复杂多变,且故障信号易受到背景噪声的严重干扰,传统方法对故障特征难以准确提取的问题,提出一种自适应经验小波变换（AEWT）与奇异值分解（SVD）的特征提取方法,并结合核极限学习机（KELM）实现风电机组轴承的故障诊断,该方法同时考虑轴承不同故障类型及不同损伤等级的情况。其中,自适应EWT为两阶段调整过程：基于尺度空间法固有模态函数（IMF）分解-确保EWT分解的有效性、基于相关系数最大的敏感分量提取-实现相关特征最大化和冗余信息的消除。通过相关实验结果可明显发现,所提AEWT的分解效果优于EMD、EEMD、CEEMDAN、LMD等方法。对提取敏感分量利用SVD计算奇异值,构建故障特征向量;最后将特征向量作为KELM的输入,建立KELM轴承状态识别模型。通过西储大学平台轴承振动信号和实际风场采集的轴承振动信号对算法进行验证,结果表明,相比SVM、ELM、KNN等识别模型,该方法能有效识别出不同故障类型及不同损伤等级下的轴承故障,整体识别率达99%。     

基于PSO优化LS-SVM的短期风速预测

提出了一种基于粒子群(PSO)算法优化最小二乘支持向量机(LS-SVM)的风电场风速预测方法。以相关性较高的历史风速序列作为输入,建立预测模型,并用粒子群算法优化模型参数。在对未来1 h风速进行预测时,文章所提出的模型比最小二乘支持向量机模型及BP神经网络模型具有较高的预测精度和运算速度。算例结果表明,经粒子群优化的最小二乘支持向量机算法是进行短期风速预测的有效方法。     

Trading wind energy on the basis of probabilistic forecasts both of wind generation and of market quantities

Wind power is not easily predictable and non‐dispatchable. Nevertheless, wind power producers are increasingly urged to participate in electricity market auctions in the same manner as conventional power producers. The aim of this paper is to propose an operational strategy for trading wind energy in liberalized electricity markets and to assess its performance. At first, the so‐called optimal quantile strategy is revisited. It is proved that without market power, i.e. under the price‐taker assumption, this strategy maximizes expected market revenues. Forecasts of wind power production, of day‐ahead and real‐time market prices and of the system imbalance are inputs to this strategy. Subsequently, constraining of the bid that maximizes the expected revenues is proposed as a way to overcome the strategy's disregard of practical limitations and, at the same time, of risk. Two constraining techniques are introduced: constraining in the decision space and in the probability space. Finally, the trade of a wind power producer is simulated in a test case for the Eastern Danish (DK‐2) price area of the Nordic Power Exchange (Nord Pool) during a 10 month period in 2008. The results of the test case show the financial benefits of the aforementioned strategy as well as the consequent interaction with the electricity market. This study will support a demonstration in the framework of the EU project ANEMOS.plus. Copyright © 2012 John Wiley & Sons, Ltd.     

Statistical post‐processing of turbulence‐resolving weather forecasts for offshore wind power forecasting

Accurate short‐term power forecasts are crucial for the reliable and efficient integration of wind energy in power systems and electricity markets. Typically, forecasts for hours to days ahead are based on the output of numerical weather prediction models, and with the advance of computing power, the spatial and temporal resolutions of these models have increased substantially. However, high‐resolution forecasts often exhibit spatial and/or temporal displacement errors, and when regarding typical average performance metrics, they often perform worse than smoother forecasts from lower‐resolution models. Recent computational advances have enabled the use of large‐eddy simulations (LESs) in the context of operational weather forecasting, yielding turbulence‐resolving weather forecasts with a spatial resolution of 100 m or finer and a temporal resolution of 30 seconds or less. This paper is a proof‐of‐concept study on the prospect of leveraging these ultra high‐resolution weather models for operational forecasting at Horns Rev I in Denmark. It is shown that temporal smoothing of the forecasts clearly improves their skill, even for the benchmark resolution forecast, although potentially valuable high‐frequency information is lost. Therefore, a statistical post‐processing approach is explored on the basis of smoothing and feature engineering from the high‐frequency signal. The results indicate that for wind farm forecasting, using information content from both the standard and LES resolution models improves the forecast accuracy, especially with a feature selection stage, compared with using the information content solely from either source.     

Machine learning based switching model for electricity load forecasting

In deregulated power markets, forecasting electricity loads is one of the most essential tasks for system planning, operation and decision making. Based on an integration of two machine learning techniques: Bayesian clustering by dynamics (BCD) and support vector regression (SVR), this paper proposes a novel forecasting model for day ahead electricity load forecasting. The proposed model adopts an integrated architecture to handle the non-stationarity of time series. Firstly, a BCD classifier is applied to cluster the input data set into several subsets by the dynamics of the time series in an unsupervised manner. Then, groups of SVRs are used to fit the training data of each subset in a supervised way. The effectiveness of the proposed model is demonstrated with actual data taken from the New York ISO and the Western Farmers Electric Cooperative in Oklahoma.     

Wind turbine fault diagnosis method based on diagonal spectrum and clustering binary tree SVM

Renewable energy sources like wind energy are copiously available without any limitation. Reliability of wind turbine is critical to extract maximum amount of energy from the wind. The vibration signals in wind turbine's rotation parts are of universal non-Gasussian and nonstationarity and the fault samples are usually very limited. Aiming at these problems, this paper proposed a wind turbine fault diagnosis method based on diagonal spectrum and clustering binary tree Support Vector Machines (SVM). Firstly, the diagonal spectrum is calculated from vibration rotating machine as the input feature vector. Secondly, self-organizing feature map neural network is introduced to cluster the fault feature samples and construct a cluster binary tree. Then the multiple fault classifiers are designed to train and test samples. The wind turbine gear-box fault experiment results proved that this method can effectively extract features from nonstationary signals, and can obtain excellent results despite of less training samples.     

Integration of wind power in the liberalized Dutch electricity market

Wind power is becoming a large‐scale electricity generation technology in a number of European countries, including the Netherlands. Owing to the variability and unpredictability of wind power production, large‐scale wind power can be foreseen to have large consequences for balancing generation and demand in power systems. As an essential aspect of the Dutch market design, participants are encouraged to act according to their energy programs, as submitted day‐ahead to the system operator. This program responsibility shifts the burden of balancing wind power away from the system operator to the market. However, the system operator remains the responsible party for balancing any generation/load imbalances that may still be arising in real time. In this article, features that are unique for the Dutch market design are presented and their implications on the system integration of wind power are investigated. It is shown that the Dutch market design penalizes the intermittent nature of wind power. A discussion of opportunities and threats of balancing wind power by use of market forces is provided. Last, an outline is given of future work. Copyright © 2006 John Wiley &Sons, Ltd.     

Modeling and forecasting the mean hourly wind speed time series using GMDH-based abductive networks

Wind speed forecasts are important for the operation and maintenance of wind farms and their profitable integration into power grids, as well as many important applications in shipping, aviation, and the environment. Modern machine learning techniques including neural networks have been used for this purpose, but it has proved hard to make significant improvements on the performance of the simple persistence model. As an alternative approach, we propose here the use of abductive networks, which offer the advantages of simplified and more automated model synthesis and transparent analytical input–output models. Various abductive models for predicting the mean hourly wind speed 1 h ahead have been developed using wind speed data at Dhahran, Saudi Arabia during the month of May over the years 1994–2005. The models were evaluated on the data for May 2006. Models described include a single generic model to forecast next-hour speed from the previous 24 hourly measurements and an hour index, which give an overall mean absolute error (MAE) of 0.85 m/s and a correlation coefficient of 0.83 between actual and predicted values. The model achieves an improvement of 8.2% reduction in MAE compared to hourly persistence. The above model was used iteratively to forecast the hourly wind speed 6 h and 24 h ahead at the end of a given day, with MAEs of 1.20 m/s and 1.42 m/s which are lower than forecasting errors based on day-to-day persistence by 14.6% and 13.7%. Relative improvements on persistence exceed those reported for several machine learning approaches reported in the literature.     

Integrating wind output with bulk power operations and wholesale electricity markets

Wind farms have three characteristics that complicate their widespread application as an electricity resource: limited control, unpredictability and variability. Therefore the integration of wind output into bulk power electric systems is qualitatively different from that of other types of generators. The electric system operator must move other generators up or down to offset the time‐varying wind fluctuations. Such movements raise the costs of fuel and maintenance for these other generators. Not only is wind power different, it is new. The operators of bulk power systems have limited experience in integrating wind output into the larger system. As a consequence, market rules that treat wind fairly—neither subsidizing nor penalizing its operation—have not yet been developed. The lack of data and analytical methods encourages wind advocates and sceptics to rely primarily on their biases and beliefs in suggesting how wind should be integrated into bulk power systems. This project helps fill this data and analysis gap. Specifically, it develops and applies a quantitative method for the integration of a wind resource into a large electric system. The method permits wind to bid its output into a short‐term forward market (specifically, an hour‐ahead energy market) or to appear in real time and accept only intrahour and hourly imbalance payments for the unscheduled energy it delivers to the system. Finally, the method analyses the short‐term (minute‐to‐minute) variation in wind output to determine the regulation requirement the wind resource imposes on the electrical system. Copyright © 2002 John Wiley & Sons, Ltd.     

Short‐term hydropower planning coordinated with wind power in areas with congestion problems

In this paper, a day‐ahead planning algorithm for a multi‐reservoir hydropower system coordinated with wind power is developed. Coordination applies to real situations, where wind power and hydropower are owned by different utilities, sharing the same transmission lines, although hydropower has priority for transmission capacity. Coordination is thus necessary to minimize wind energy curtailments during congestion situations. The planning algorithm accounts for the uncertainty of wind power forecast. Only planning for the spot market is considered. Once the production bid is placed on the market, it cannot be changed. The solution of the stochastic optimization problem should, therefore, fulfill the transmission constraints for all wind power production scenarios. An evaluation algorithm is also developed to quantify the impact from the coordinated planning in the long run. The developed planning algorithm and the evaluation algorithm are applied in a case study. The results are compared with uncoordinated operation. The results of the case study show that coordination with wind power brings additional income to the hydropower utility and leads to significant reduction of wind energy curtailments. Copyright © 2007 John Wiley & Sons, Ltd.     

Energy storage sizing for wind power: impact of the autocorrelation of day‐ahead forecast errors

The availability of day‐ahead production forecast is an important step toward better dispatchability of wind power production. However, the stochastic nature of forecast errors prevents a wind farm operator from holding a firm production commitment. In order to mitigate the deviation from the commitment, an energy storage system connected to the wind farm is considered. One statistical characteristic of day‐ahead forecast errors has a major impact on storage performance: errors are significantly correlated along several hours. We thus use a data‐fitted autoregressive model that captures this correlation to quantify the impact of correlation on storage sizing. With a Monte Carlo approach, we study the behavior and the performance of an energy storage system using the autoregressive model as an input. The ability of the storage system to meet a production commitment is statistically assessed for a range of capacities, using a mean absolute deviation criterion. By parametrically varying the correlation level, we show that disregarding correlation can lead to an underestimation of a storage capacity by an order of magnitude. Finally, we compare the results obtained from the model and from field data to validate the model. Copyright © 2013 John Wiley & Sons, Ltd.     

From probabilistic forecasts to statistical scenarios of short‐term wind power production

Short‐term (up to 2–3 days ahead) probabilistic forecasts of wind power provide forecast users with highly valuable information on the uncertainty of expected wind generation. Whatever the type of these probabilistic forecasts, they are produced on a per horizon basis, and hence do not inform on the development of the forecast uncertainty through forecast series. However, this additional information may be paramount for a large class of time‐dependent and multistage decision‐making problems, e.g. optimal operation of combined wind‐storage systems or multiple‐market trading with different gate closures. This issue is addressed here by describing a method that permits the generation of statistical scenarios of short‐term wind generation that accounts for both the interdependence structure of prediction errors and the predictive distributions of wind power production. The method is based on the conversion of series of prediction errors to a multivariate Gaussian random variable, the interdependence structure of which can then be summarized by a unique covariance matrix. Such matrix is recursively estimated in order to accommodate long‐term variations in the prediction error characteristics. The quality and interest of the methodology are demonstrated with an application to the test case of a multi‐MW wind farm over a period of more than 2 years. Copyright © 2008 John Wiley & Sons, Ltd.