Wind Speed Series Research Articles

Short-Term Wind Speed Forecasting Based on Low Redundancy Feature Selection

Wind speed forecasting is an indispensable part of wind energy assessment and power system scheduling. In the modeling of wind speed forecasting, there are problems of insufficiency of the high input feature dimension, weak pertinence of the model and a lack of consideration about the redundancy between features. To address these problems, a short-term wind speed forecast method based on low redundancy feature selection is proposed. Firstly, complementary ensemble empirical mode decomposition (CEEMD) is used to pretreat the wind speed data to reduce the randomness and fluctuation of wind speed data. Secondly, conditional mutual information (CMI) is used to analyze the correlation between the input features on different predicted days and wind speed series. The feature order based on conditional mutual information is used to reduce the redundancy between candidate features and establish subsets with candidate features. After that, according to different candidate feature subsets of different predicted days, the outlier-robust extreme learning machine (ORELM) is used to carry out the forward feature selection and obtain optimal feature subsets for different predicted days. Finally, the optimal prediction model is constructed by using the optimal feature subset and the short-term wind speed forecasting is carried out. The validity and advance of the new method are verified by measured data through comparison experiments.

A probabilistic assessment approach for wind turbine-site matching

This article provides a new methodology for wind turbine-site matching by using a probabilistic approach. The random behavior of the wind speed climate and the uncertainties of wind turbine characteristics are important to take into account in models used to evaluate the performance of the wind turbine. The proposed formulation of the wind turbine-site matching is derived based on the probabilistic reliability assessment approach. It was experimented using different power curve approximation models, for different random conditions, using time series of wind speed in two sites in Morocco: Dakhla and Essaouira. A comparison based on methods used in literature for the estimation of two-parameter of the Weibull function to fit the wind speed distribution is also carried out. The results revealed that the introduced performance indicators are less sensitive to the models used to approximate the wind power curves compared to the deterministic conventional indicator that leads to different rankings and problems of over-sizing or under-sizing. However, those performance indicators are more sensitive to the variation of the wind speed distribution parameter’s and can help on accurately estimate the wind power. Moreover, the proposed formulation allows a global sensitivity analysis using Sobol’s indices to observe the influence of each input parameter on the observed variances of the performance of a wind turbine. A numerical application illustrates the interpretation of sensitivity indices and shows the impact of the wind speed and the rated wind speed on the variance of the wind turbine performance. This method can help wind energy developers and manufacturers to optimally select WTGs for their future project and accurately forecast the performance of their WTGs for monitoring and maintenance scheduling under uncertainty.

Research on a combined model based on linear and nonlinear features - A case study of wind speed forecasting

Abstract As one of the most promising sustainable energy sources, wind energy is being paid more attention by the researchers. Because of the volatility and instability of wind speed series, wind power integration faces a severe challenge; thus, an accurate wind energy forecasting plays a key role in smart grid planning and management. However, many traditional forecasting models do not consider the necessity and importance of data preprocessing and neglect the limitation of using a single forecasting model, which leads to poor forecasting accuracy. To solve these problems, a novel combined model based on two linear and four nonlinear forecasting algorithms is proposed to adapt both the linear and nonlinear characteristics of the wind energy time series. In addition, a modified Artificial Fish Swarm Algorithm and Ant Colony Optimization (AFSA-ACO) algorithm is proposed and employed to determine the optimal weight coefficients of the combined models. To verify the forecasting performance of the developed combined model, several experiments were implemented by using 10-min interval wind speed data in Shandong, China. Then, one-step (10-min), three-step (30-min) and five-step (50-min) predictions were conducted. The experimental results indicate that the developed combined model is remarkably superior to all benchmark models for the high precision and stability of wind-speed predictions.

Multi-step wind speed forecasting using EWT decomposition, LSTM principal computing, RELM subordinate computing and IEWT reconstruction

The wind speed forecasting is crucial for the wind power conversion and management. In this study, a new hybrid model consisting of the EWT (Empirical Wavelet Transform) decomposition, the LSTM (Long Short Term Memory) network, the RELM (Regularized Extreme Learning Machine) network and the IEWT (Inverse Empirical Wavelet Transform) reconstruction is proposed. The hybrid model are carried out as follows: the EWT is employed to decompose the raw wind speed series into several sub-layers; the LSTM network is executed as the principal predictor of each sub-layer; the RELM network is utilized as the subordinate predictor to model the forecasting error series of each sub-layer; the IEWT is adopted to construct the final forecasting series and filter the outliers. To validate the forecasting capacity of the proposed hybrid EWT-LSTM-RELM-IEWT model, seven different forecasting models are implemented on five wind speed time series. The experimental results demonstrate that: (1) the single LSTM model cannot provide satisfactory wind speed forecasting results in the involved wind speed time series; (2) the EWT can promote the wind speed forecasting accuracy and stability of the LSTM network significantly; (3) the RELM network based error modeling method improves the performance of the proposed EWT-LSTM-IEWT forecasting structure significantly; (4) the IEWT based outlier correction method is effective in promoting the wind speed forecasting accuracy and stability in the proposed EWT-LSTM-RELM structure; and (5) among all the involved models, the proposed hybrid model has the best performance in one-step to five-step predictions.

Power system security assessment with high wind penetration using the farms models based on their correlation

Increasing the wind energy penetration in a power system presents some technical challenges to the transmission expansion planning (TEP). In the first stage of TEP, the transmission bottlenecks should be determined and ranked via security assessment. The high penetration of wind energy means a large number of wind farms exist in various geographic areas. It is found that there is a correlation between the wind speed series of different farms. Therefore, integration of the correlated wind farms into security assessment is addressed in this study. Hence, a new model of wind speed prediction is presented based on the correlated autoregressive moving average time series. The copula functions are used to make the predefined correlation among wind speed series. Here a linear correlation using a Gaussian copula is implemented. Then, the risk-based security assessment is performed using the proposed sequential time simulation. The proposed process is applied to the modified IEEE 39-bus test system which comprises 15 wind farms. Then, the transmission bottlenecks are identified and ranked regarding their overload risks. Finally, the impacts of the wind farms correlation on the risk index are investigated and those contingencies which impose the highest influence on this risk are identified.

Research and application of an innovative combined model based on a modified optimization algorithm for wind speed forecasting

Wind energy is emerging as a promising substitute for conventional energy and plays a pivotal role in the power industry. For wind speed forecasting, many challenges have exposed due to its fluctuation and intermittence. To address these difficulties, different models have been adopted to various wind speed time series in previous studies. However, few methodologies have focused on the importance of model parameter optimization or data pre-processing, resulting in undesirable forecasting performance. In this study, an innovative combined model that combines data pre-processing, modified optimization algorithms, three neural networks and an effective deciding weight method is proposed for short-term wind speed forecasting. To improve the forecasting capacity of the combined model, a modified optimization algorithm is proposed and employed to determine the parameters of the single models. Furthermore, a deciding weight method based on multivariate statistical estimation is applied for weight optimization. Additionally, ten-minute wind speed data from a wind farm in Penglai, China, are selected for multi-step ahead forecasting. The results obtained confirmed an adequate approximation of the actual wind speed series and a significant improvement of the forecasting accuracy of the proposed model.

An intelligent method for wind power forecasting based on integrated power slope events prediction and wind speed forecasting

In this paper, we study an intelligent wind power prediction method by taking the prediction time horizons and prediction accuracy into account. The wind power slope events are defined, and multiple support vector machines are applied to the classification of slope down/up events for multistep‐ahead scenarios. The wind speed series are decomposed by using the maximum overlap discrete wavelet transform (MODWT), and each decomposed signal is forecast using an adaptive wavelet neural network (AWNN) individually. The network is trained for wind speed prediction up to 24 h ahead. Based on slope events forecasting and wind speed forecasting, an improved radial basis function neural network (RBFNN) is proposed to predict wind power up to 24 h ahead. The proposed model is tested by using wind power data collected from a real wind farm. The analysis results validate that both the prediction time horizons and the prediction accuracy are guaranteed, and the proposed method can be applied to the optimal scheduling of wind farms 1 day in advance. © 2018 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.

Seasonal and continual wind speed modelling for the coastal urban city, Karachi

ABSTRACT. Variation in wind speed not only indicates the strengthening or weakening of pressure systems but its role in wind farm in the vicinity of coastal area is also crucial. Probability distributions through time series of wind speed data serves foremost basic need for the said parameters. Exploratory data analysis revealed that for coastal city Karachi, maximum wind speed (~23 m/s) occurred during monsoon with its peak during postmonsoon with maximum deviation (~3.5 m/s). Mean / trimmed mean during spring and postmonsoon (~11.5 m/s) as well as in premonsoon and monsoon (~18.5 m/s) remain almost identical while minimum wind blowing during winter and postmonsoon are also identical (~6 m/s). Autumn and winter exhibits least standard deviations. Critical and statistical values have been compared for distribution modelling, while parametric values of different seasonal and continual distributions are also estimated. The study is supported by cumulative distribution functions and probability-probability plots. It is not uncommon to use Weibull distribution for wind speed modelling. By using daily data time series of wind speed for the coastal station Karachi, it has been explored that widely accepted Weibull distribution provides comparatively poor distribution results when compared to other more complicated models (i.e., Wakeby and generalized extreme value distributions]. It is found that annual and seasonal wind comes after the Wakeby distribution except premonsoon summer which follows the generalized extreme value distribution (GEV) for the city. No continual and / or seasonal wind speed follows the Weibull distribution, ultimately and / or more appropriately. The study may give some new insights for aviation and wind engineering purposes.

Non-stationary statistical modeling of extreme wind speed series with exposure correction

Extreme wind speed analysis has been carried out conventionally by assuming the extreme series data is stationary. However, time-varying trends of the extreme wind speed series could be detected at many surface meteorological stations in China. Two main reasons, exposure change and climate change, were provided to explain the temporal trends of daily maximum wind speed and annual maximum wind speed series data, recorded at Hangzhou (China) meteorological station. After making a correction on wind speed series for time varying exposure, it is necessary to perform non-stationary statistical modeling on the corrected extreme wind speed data series in addition to the classical extreme value analysis. The generalized extreme value (GEV) distribution with time-dependent location and scale parameters was selected as a non-stationary model to describe the corrected extreme wind speed series. The obtained non-stationary extreme value models were then used to estimate the non-stationary extreme wind speed quantiles with various mean recurrence intervals (MRIs) considering changing climate, and compared to the corresponding stationary ones with various MRIs for the Hangzhou area in China. The results indicate that the non-stationary property or dependence of extreme wind speed data should be carefully evaluated and reflected in the determination of design wind speeds.

Multifractal analysis of the time series of daily means of wind speed in complex regions

In this paper, we applied the multifractal detrended fluctuation analysis to the daily means of wind speed measured by 119 weather stations distributed over the territory of Switzerland. The analysis was focused on the inner time fluctuations of wind speed, which could be linked with the local conditions of the highly varying topography of Switzerland. Our findings point out to a persistent behaviour of almost all measured wind speed series (indicated by a Hurst exponent larger than 0.5), and to a high multifractality degree indicating a relative dominance of the large fluctuations in the dynamics of wind speed, especially on the Swiss Plateau, which is comprised between the Jura and Alps mountain ranges. The study represents a contribution to the understanding of the dynamical mechanisms of wind speed variability in mountainous regions.

An experimental investigation of three new hybrid wind speed forecasting models using multi-decomposing strategy and ELM algorithm

The wind speed forecasting is important for the wind power industry to achieve the intelligent management. Three new hybrid methods using the WPD (Wavelet Packet Decomposition), the EMD (Empirical Mode Decomposition) and the ELM (Extreme Learning Machine) are presented for wind speed multi-step predictions. In the proposed architectures, the WPD is chosen to decompose the actual wind speed series into several sub-layers, while the EMD is adopted to further decompose the obtained LF (Low Frequency) sub-layers, the obtained HF (High Frequency) sub-layers and all the obtained sub-layers into a number of IMFs (Intrinsic Mode Functions), respectively. Finally, the ELM is used to complete the wind speed predicting computation for these decomposed wind speed sub-layers. To investigate the performance of the proposed hybrid models in the wind speed multi-step forecasting and find which kind of signal decomposing approach is the most suitable for the ELM based wind speed forecasting, the PM (Persistent Model), the ARIMA model, the SVM model, the ELM model, the WPD-ELM model, the WPD-EMD (LF)-ELM model, the WPD-EMD (HF)-ELM model and the WPD-EMD-ELM model are all included in the forecasting performance comparisons. The results of the two real experiments indicate that among all the involved models, the WPD-EMD (LF)-ELM model has the best predicting performance.

An improved combination approach based on Adaboost algorithm for wind speed time series forecasting

As one of promising renewable energy, wind energy has an important position in the field of energy market and it has been always used to generate electricity, thus, the high precision wind speed forecasting is important but challenging for power generation system. Many researchers have devoted their attention to establish efficient wind speed forecasting models, limited by the structure of original models and database, these models could not solve overfitting problem very well and it is rare that a single wind speed forecasting model is always best in all cases since each model has its own particular strengths and weaknesses. The combining method, composed of multiple forecasting models, is regarded as a type of outstanding approach to take advantage of strengths of each model. However, the properties of the individual forecasting models may vary over time, which leads to poorly performance of the combining method using fixed weights, thus, it is more appropriate to allow the combining weights to change according to the time-varying underlying process. This study develops a reliable combination model for wind speed forecasting based on an improved Adaboost algorithm named time-vary-forecasting-effectiveness (TW-FE-Adaboost) algorithm in order to improve the overall forecasting accuracy. In the proposed model, concept drift is firstly used to deal with wind speed time series mainly because the contributions of samples which are varying with time, the second order forecasting effectiveness is used to measure the performance of weak learners. Then, the multi-step ahead forecasting for each site is conducted using TW-FE-Adaboost model in which the input-output sample pairs are determined in a reasonable way. Finally, the ultimate forecast result of wind speed is obtained by aggregating the forecast result of each weak learner. The proposed model is tested using four sites wind speed series collected in Hexi corridor from wind farms located in northwest of China. The experimental results show that the proposed model outperforms all other comparison models in this paper, which demonstrates that the proposed model has superior performances for wind speed forecasting.

Data mining-assisted short-term wind speed forecasting by wavelet packet decomposition and Elman neural network

On the basis of data-mining technology, a hybrid method of short-term wind speed forecast is proposed by the wavelet packet decomposition, density-based spatial clustering of applications with noise, and the Elman neural network (WPD-DBSCAN-ENN). First, the WPD is applied to decompose a raw wind speed series into several sub-series. The gradient boosted regression trees (GBRT) algorithm is then applied to determine the structure of the ENNs for each sub-wind series. Next, the training dataset is clustered by the DBSCAN to select the representative data for the ENNs. A key parameter in the DBSCAN is chosen through a new method. Finally, the wind speed forecast is conducted by the ENNs. Case studies are adopted to validate the accuracy of the hybrid methods. The results are compared with those obtained using the WPD-ENN hybrid method and a single ENN via four general error criteria. The performance of the WPD-DBSCAN-ENN hybrid method outperformed those of the other methods indicated above.

Methodology of Investment Risk Analysis for Wind Power Plants in the Brazilian Free Market

Despite the strong growth of wind power in the world, it is considered a high risk investment due to variability and unpredictability of wind speed. If the energy trade occurs in the free market, there is another risk factor that is the short-term price. This study proposes a methodology of investment risk analysis for wind power plants using innovative stochastic models to generate synthetic time series of wind speed and short-term price. The simulation is implemented using the Monte Carlo method associated with a Cholesky decomposition. The cashflow's gross revenue is obtained through an energy trading model for the Free Contracting Environment (FCE) in Brazil. The investment analysis is based on probability distribution of Net Present Value (NPV) of the power plant's cash flow, as well as the Value at Risk (VaR) and the Conditional Value at Risk (CVaR). A case study was performed for Natal city of Rio Grande do Norte (RN) state in Brazil, and the results indicated the economic viability of the power plant. A sensitivity analysis is developed considering important parameters of the modeling, and its results provide information to the decision-making process.

Homogeneity analysis of wind data from 213 m high Cabauw tower

ABSTRACTHomogeneous meteorological data are a prerequisite for reliable climatological studies. This paper investigates the homogeneity of wind data from 213 m high Cabauw tower located in The Netherlands. The wind measurements are conducted at 10, 20, 40, 80, 140 and 200 m above ground. The analysed data cover the period from February 1986 to January 1997 and from April 2000 to December 2015. This study presents the first homogeneity analysis of wind data from a tall meteorological mast. Homogeneities of wind speed and wind direction series were investigated independently using the ReDistribution Method. Overall, the wind measurements at Cabauw tower are very homogeneous. The only wind speed inhomogeneity was detected at 200 m above ground and it seems to be, at least to a certain extent, caused by the rapid expansion of the town of Lopik in the 1990s. Lopik's growth to the west, however, only influenced the east winds on the Cabauw tower. Small inhomogeneities in wind direction data were detected at 20, 40 and 80 m levels, whereas a fairly large inhomogeneity was observed at 10 m above ground. Several potential causes of inhomogeneities in wind direction data are discussed, but the major contributor could not be determined with certainty. In addition, the homogeneity of real measurements from Cabauw tower is compared against the synthetically created wind data for Cabauw tower using the Monte‐Carlo method of random sampling. The results show that the detected anomalies are not due to the random noise in the time series.

Point Downscaling of Surface Wind Speed for Forecast Applications

AbstractA statistical downscaling algorithm is introduced to forecast surface wind speed at a location. The downscaling algorithm consists of resolved and unresolved components to yield a time series of synthetic wind speeds at high time resolution. The resolved component is a bias-corrected numerical weather prediction model forecast of the 10-m wind speed at the location. The unresolved component is a simulated time series of the high-frequency component of the wind speed that is trained to match the variance and power spectral density of wind observations at the location. Because of the stochastic nature of the unresolved wind speed, the downscaling algorithm may be repeated to yield an ensemble of synthetic wind speeds. The ensemble may be used to generate probabilistic predictions of the sustained wind speed or wind gusts. Verification of the synthetic winds produced by the downscaling algorithm indicates that it can accurately predict various features of the observed wind, such as the probability distribution function of wind speeds, the power spectral density, daily maximum wind gust, and daily maximum sustained wind speed. Thus, the downscaling algorithm may be broadly applicable to any application that requires a computationally efficient, accurate way of generating probabilistic forecasts of wind speed at various time averages or forecast horizons.

РЕЖИМ ПРИЗЕМНОЙ АТМОСФЕРНОЙ ЦИРКУЛЯЦИИ В РАЙОНЕ АНТАРКТИЧЕСКОГО ПОЛУОСТРОВА

The main objective of the research is to analyze the near-surface wind regime in accordance with the data from Ukrainian Antarctic Akademik Vernadsky station and compare it with the state of the atmosphere circulation in order to supplement knowledge of the regional climate. Traditional methods of climatological processing, correlation analysis were used. According to the data of Vernadsky station, there is an increase in surface wind speed in conditions of air temperature rise. The statistical inhomogeneity in the wind speed series is detected. The main conclusion is that the air temperature growth and the increase in surface wind speed is a single manifestation of climate change in the region of the study that reflects changes in atmospheric circulation, intensification of westerly and deepening of cyclogenesis in Antarctica.

Method for selecting parameters and assessing efficiency of wind-diesel power plants for autonomous electrical supply systems

The article presents an original technique for selecting parameters and evaluating the efficiency of wind-diesel power plants for isolated power supply systems. The initial data to perform energy calculations are simulation models of electric load and wind speed. The load is simulated using typical schedules of electric loads of a decentralized consumer, taking into account a random component for each hour of the day. To create a simulation model of the wind, a typical climatic series of wind speeds at a prospective site of the power plant has been constructed according to the data of long-term meteorological observations. The proposed technique was verified through the example of choosing a wind-diesel power plant for the village of Ust-Olenyok of the Republic of Sakha (Yakutia).

Wind-stilling in the light of wind speed measurements: the Czech experience

CR Climate Research Contact the journal Facebook Twitter RSS Mailing List Subscribe to our mailing list via Mailchimp HomeLatest VolumeAbout the JournalEditorsSpecials CR 74:131-143 (2017) - DOI: https://doi.org/10.3354/cr01492 Wind-stilling in the light of wind speed measurements: the Czech experience Rudolf Brázdil1,2,*, Adam Valík1, Pavel Zahradníček2,3, Ladislava Řezníčková1,2, Radim Tolasz4, Martin Možný5 1Institute of Geography, Masaryk University, Kotlářská 2, 611 37 Brno, Czech Republic 2Global Change Research Institute, Czech Academy of Sciences, Bělidla 986/4a, 603 00 Brno, Czech Republic 3Czech Hydrometeorological Institute, Brno Regional Office, Kroftova 43, 616 67 Brno, Czech Republic 4Czech Hydrometeorological Institute, Na Šabatce 17, 143 06 Praha 4 - Komořany, Czech Republic 5Czech Hydrometeorological Institute, Doksany Observatory, 411 82 Doksany 105, Czech Republic *Corresponding author: brazdil@sci.muni.cz ABSTRACT: Changes of instruments often give rise to significant break-points in wind-speed series. This is particularly applicable when measurements are automated, a process that started in the Czech Republic in the mid-1990s, when standard universal anemographs were progressively replaced by the Vaisala WAA251 sensor (cup anemometer) and the WS425 sensor (ultrasonic). Parallel wind speed measurements, by universal anemographs and Vaisala sensors, at the Doksany (2000-2016) and Kocelovice (2000-2016) stations enabled differences in the 2 types of measurement to be analysed. Vaisala sensors measure, on average, higher wind-speeds than universal anemographs, particularly in calm situations and at low wind speeds. The differences between the 2 types of instrument do not depend on wind direction. Linear trends of homogenised daily mean wind-speed series from only a universal anemograph or combined from universal anemograph and Vaisala sensors generally exhibit no important differences in their significance or values. This could indicate that observed decreasing trends in mean daily wind-speeds (‘stilling’) cannot be attributed to changes of wind-speed measurements to automated devices; with respect to only 2 stations being investigated, this is biased by high uncertainty. In contrast, important differences in the 2 types of measurement, both in linear trends and their significance, appear for series of 3 daily readings (07:00, 14:00 and 21:00 h LMT). KEY WORDS: Universal anemograph · Vaisala wind-speed sensors · Wind speed · Homogenisation · Wind stilling · Czech Republic Full text in pdf format PreviousNextCite this article as: Brázdil R, Valík A, Zahradníček P, Řeznícčková L, Tolasz R, Možný M (2017) Wind-stilling in the light of wind speed measurements: the Czech experience. Clim Res 74:131-143. https://doi.org/10.3354/cr01492 Export citation RSS - Facebook - Tweet - linkedIn Cited by Published in CR Vol. 74, No. 2. Online publication date: December 27, 2017 Print ISSN: 0936-577X; Online ISSN: 1616-1572 Copyright © 2017 Inter-Research.

Spatio-temporal analysis of prodelta dynamics by means of new satellite generation: the case of Po river by Landsat-8 data

This paper describes a procedure to perform spatio-temporal analysis of river plume dispersion in prodelta areas by multi-temporal Landsat-8-derived products for identifying zones sensitive to water discharge and for providing geostatistical patterns of turbidity linked to different meteo-marine forcings. In particular, we characterized the temporal and spatial variability of turbidity and sea surface temperature (SST) in the Po River prodelta (Northern Adriatic Sea, Italy) during the period 2013–2016. To perform this analysis, a two-pronged processing methodology was implemented and the resulting outputs were analysed through a series of statistical tools. A pixel-based spatial correlation analysis was carried out by comparing temporal curves of turbidity and SST hypercubes with in situ time series of wind speed and water discharge, providing correlation coefficient maps. A geostatistical analysis was performed to determine the spatial dependency of the turbidity datasets per each satellite image, providing maps of correlation and variograms. The results show a linear correlation between water discharge and turbidity variations in the points more affected by the buoyant plumes and along the southern coast of Po River delta. Better inverse correlation was found between turbidity and SST during floods rather than other periods. The correlation maps of wind speed with turbidity show different spatial patterns depending on local or basin-scale wind effects. Variogram maps identify different spatial anisotropy structures of turbidity in response to ambient conditions (i.e. strong Bora or Scirocco winds, floods). Since the implemented processing methodology is based on open source software and free satellite data, it represents a promising tool for the monitoring of maritime ecosystems and to address water quality analyses and the investigations of sediment dynamics in estuarine and coastal waters.