Search

The paper aims to develop a decision tool for planning offshore wind farm locations, combining multi-criteria decision analysis and geographic information systems. This method considers several technological, environmental, social, and economic criteria. The criteria are used as evaluation factors and constraints to rank the identified potential locations through an Analytic Hierarchy Process. During the evaluation of the available areas, a pairwise comparison is used in which a group of experts determines the weights. Sensitivity and consensus analyses evaluate the results robustness. The methodology is developed for a case study in the Atlantic coastal areas of Portugal, Spain, and France. The results show the potential of this tool to support the planners in the designation of regions for floating wind farm development. [ABSTRACT FROM AUTHOR]

Extreme Wind Speed events (EWS) are responsible for the worst damages caused by wind in wind farms. An accurate estimation of the frequency and intensity of EWS is essential to avoid wind turbine damage and to minimize cut-out events in these facilities. In this paper we discuss how generative Data Augmentation (DA) techniques improve the performance of Machine Learning (ML) and Deep Learning (DL) algorithms in EWS prediction problems. These problems are usually tackled as classification tasks, which are highly unbalanced due to the small number of EWS events in wind farms. Different versions of Variational AutoEncoders (VAE) are proposed and analysed in this work (VAEs, Conditional VAEs (CVAEs) and Class-Informed VAEs (CI-VAE)) as generative DA techniques to balance the data in EWS problems, leading to better performance of the prediction systems. The proposed generative DA techniques have been compared against traditional DA algorithms in a real problem of EWS prediction in Spain, considering ERA5 reanalysis data as predictive variables. The results showed that the CI-VAE with a Convolutional Neural Network approach obtained the best results, with values of Precision 0.62, Recall 0.74 and F1 score 0.67, improving up to 4% the results of the method without data augmentation techniques. [Display omitted] • Generative data augmentation techniques can improve extreme wind prediction. • Variational Autoencoders modifications are used to generate synthetic wind extreme samples. • Experiments on real wind speed data from a Spanish wind farm are presented. • Comparisons with traditional data augmentation techniques show prediction improvements. [ABSTRACT FROM AUTHOR]

Finding an optimal bidding strategy for a wind farm in the electricity market is not straightforward due to the wind variability. This issue is becoming more relevant as renewable plants are more exposed to market signals. Considering the characteristics of the European markets, operators must submit the energy bidding between 12 and 36 h ahead the actual delivery time. This bidding can be adjusted later in any session of the intraday markets, but sometimes this is not enough to reduce significantly the deviation risk. This paper presents a practical application of a method to analytically calculate the optimal bidding of a wind power plant, based on the maximisation of the income function. The results show that, given the characteristics of the deviation markets in Spain, the optimal bidding strategy depends essentially on the deviation of the system. The proposed technique has been tested and validated in a real application by considering actual data for energy production and forecasts for an operating wind farm in Spain, as well as real market deviations and prices provided by the Spanish system and market operators; analysing the advantages of the proposed optimal bidding strategy over the most plausible option, based on bidding the forecasted energy. [ABSTRACT FROM AUTHOR]

This paper analyses the influence of the variation of meteorological and operational parameters on estimation of the power output of a dispatchable wind farm (WF). The active power set-points (APSPs), established to regulate the wind farm power output (WFPO), are one of the analysed parameters. The WF considered as case study is integrated in the Gorona del Viento wind-hydro power plant (El Hierro-Canary Islands-Spain), which supplies the primary energy demand of the island. Statistical inference between the errors generated by different WFPO estimation models, each fed with different input features, is performed. These models are based on supervised machine learning (ML) regression algorithms, namely support vector regression, random forest, and a combination of the strengths of these two base learning algorithms constructed using stacked regression ensemble techniques. From the results obtained, the following conclusions are drawn: a) There is a marked difference between the errors obtained with the model that only considers wind speed and direction and that which additionally incorporates the APSP parameter, showing the importance of considering this particular parameter; b) the model which incorporates air density and turbulence intensity in addition to the APSP improves the values of all the metrics, independently of the ML technique employed. • The active power set-point (APSP) parameter is very important in WFPO estimation. • Air density, turbulence intensity and APSP parameters improve WFPO estimation. • Eight models are compared for wind farm power output (WFPO) estimation. • Three machine learning techniques implemented in the models are analysed. • Non-parametric statistical inference is used to compare the models. [ABSTRACT FROM AUTHOR]

Inaccurate wind forecasts create negative technical and economic effects on power systems such as wind curtailments, increase of operating reserves or economic penalties that wind owners have to face. In the Spanish market, wind energy units deviating against the system incur in significant extra costs. Taking advantage of the geographical dispersion of wind farms, wind aggregation poses a solution to imperfect predicting techniques reducing wind portfolio differences between predicted and real production. In the Spanish electric power system, we measure in this paper the efficacy of aggregating wind promoters in reducing deviations and costs. For this purpose, an empirical method using measures of real productions and schedules is proposed, taking advantage of an optimization model that builds a wind portfolio with the minimum wind deviation, and defining key performance indexes to compute the benefits of the aggregation. To obtain significant and reliable values, the whole year of 2016 is assessed using 67 wind farms representing 7% of the total wind power installed in the Spanish peninsula at the end of 2016. It will be shown that aggregation is able to reduce a maximum of 65% of individual wind deviations which translates in a reduction of no more than 58% of individual wind deviation extra-costs. In addition, this limit of maximum extra-costs reduction represents 2% of loss of income in the daily energy market. • Optimization model that builds a wind portfolio with the minimum wind deviations. • Definition of Key Performance Indexes to measure the efficacy of wind aggregation. • Application case to the Spanish power system: 7% wind installed capacity in year 2016. • Aggregation in Spain reduces a maximum of 65% of individual wind deviations. [ABSTRACT FROM AUTHOR]

There is a growing interest on how climate change may affect the energy sector, including changes in wind energy generation. This paper builds on existing research adding an economic component that considers how climate change can affect operating margins and investment values in specific wind farms in Spain. A projection of wind speed was carried out using an ensemble of three climate models, two scenarios (RCP 4.5 and 8.5) and two time periods (2018–2041 and 2042–2065) per plant. Using historical power curves, the changes in wind speed were converted to production output. The results show variations in production of up to 8% and changes in operating margins up to 10%. Seasonal generation may fluctuate as well, with an increase in summer and decrease in winter. An investment analysis was also conducted to consider how climate change may influence future developments in the sector. • Climate change will affect wind speed and therefore wind energy production. • In four wind farms in Spain we project variations in wind speed of up to ± 5%. • This will imply changes in production (±8%) and in operative margins (±10%). • The regulatory framework is more relevant in comparison. [ABSTRACT FROM AUTHOR]

The repowering of already installed wind farms is considered one of the most promising and cost-effective short-term strategies to scale-up wind capacity. In this study, we apply Markowitz's mean-variance (MV) portfolio optimization theory to explore alternative repowering actions in Spain. The efficient portfolios – a direct outcome of the MV optimization – offer optimal repowering alternatives to current wind farm generation mixes. They deliver the highest possible average power output (yield) for a given level of supply risk. Different repowering scenarios are considered in this paper that range from a full restructuring of the existing wind generation mix to restricting by certain amounts the percentage of down-/uprating of each reference region. Results show that, depending on the configuration of the MV portfolio optimization problem, hourly fluctuations in the aggregate power supply can be reduced as much as 12–31%, while retaining the current level of energy productivity. In addition, for the level of energy supply risk experienced with the existing portfolio of Spanish wind farms; we can derive more efficient mixes that boost-up productivity by 16–55%. This work aims at providing valuable insight for energy policy-making in the direction of optimally repowering future renewable generation. [ABSTRACT FROM AUTHOR]

Optimal siting of wind farms based on a pre-assessment of the spatiotemporal variability of wind resources is considered a suitable method for reducing fluctuations in the delivered output. In this study, we explore the potential for balancing wind energy generation in the Iberian Peninsula using Principal Component Analysis (PCA). This technique permits the discovery of possibly new promising locations for wind power harvesting and an evaluation of the existing wind farm network in terms of reliability in energy generation. Data input to the PCA consists of hourly wind capacity factor in a 5-km spatial resolution grid covering the entire peninsula. These data are derived from an equivalent wind farm power curve fed by modeled wind speed data from 80 m above ground level. PCA reveals three significant balancing patterns prevailing over the IP, where half of the currently operating wind farms in Spain are placed. Hence, among the many constituents of the existing wind farm network, these spots offer the best opportunity for stable power supply. The paper concludes by making proposals on an optimum wind capacity allocation based on the idea of equally distributing installed power between positive/negative dipoles emerging from balancing principal components. [ABSTRACT FROM AUTHOR]

Abstract: The turbine synchronization phenomenon is of great interest in order to estimate the flicker produced by a wind farm. This paper proposes an initial approach to analyze the appearance of this phenomenon by the use of various image processing techniques: a method to automatically calculate the angular frequency of an unknown number of wind turbines from a video. The recorded video images were obtained at the Manzanal wind farm, province of León (Spain). [Copyright &y& Elsevier]