Wind Speed Series Research Articles

Ensemble of evolving optimal granular experts, OWA aggregation, and time series prediction

This paper presents an online-learning ensemble framework for nonstationary time series prediction. Optimal granular fuzzy rule-based models with different objective functions and constraints are evolved from data streams. Evolving optimal granular systems (eOGS) consider multiobjective optimization, the specificity of information, model compactness, and variability and coverage of the data within the process of modeling data streams. Forecasts of individual base eOGS models are combined using averaging aggregation functions: ordered weighted averaging (OWA), weighted arithmetic mean, median, and linear non-inclusive centered OWA. Some aggregation functions use specific weights for the relevance of the base models and exclude extreme values and outliers. The weights of other aggregation functions are adapted over time based on a quadratic programming problem and the data within a sliding window. This paper investigates whether an online-learning ensemble can outperform individual eOGS models, and which aggregation function provides the most accurate forecasts. Real multivariate weather time series, particularly time series of daily mean temperature, air humidity, and wind speed from different weather stations, such as Paris–Orly, Frankfurt–Main, Reykjavik, and Oslo–Blindern, are used for evaluation. The results show that ensemble schemes outperform individual models. The proposed linear non-inclusive centered OWA function provided the most accurate numerical predictions.

Analysis of temporal properties of extremes of wind measurements from 132 stations over Switzerland

In this study, the 10-min average wind speed series recorded at 132 stations distributed rather homogeneously over the territory of Switzerland were investigated, focusing on the challenging problem of the analysis and modelling of wind extreme events. Wind extremes are defined as a sequence of consecutive values above a percentile-based threshold of wind speed distribution. Considering temporal point process of wind extremes marked by their duration, the main findings of this study are that: 1) the average probability density function of the extreme duration does not depend on the percentile-based threshold and decreases with the increase of the extreme duration; 2) wind extremes are globally time-clustered, although they tend to behave as a Poisson process with the increase of the minimum extreme duration; 3) locally, wind extremes tend to be clustered for any percentile-based threshold for stations located above about 2000 m a.s.l.; 4) by using the Allan factor, it was revealed that wind extremes tend to be clustered even at lower timescales, especially for the higher stations.

An Optimal Scheduling Method for Multi-Energy Hub Systems Using Game Theory

The optimal scheduling of multi-energy hub systems plays an important role in the safety, stability, and economic operation of the system. However, due to the strong uncertainty of renewable energy access, serious coupling, and the interaction among energy hubs of multi-energy hub systems, it is difficult for the traditional optimal scheduling method to solve these problems. Therefore, game theory was used to solve the optimal scheduling problem of multi-energy hub systems. According to the internal connection mode and energy conversion relationship of energy hubs, along with the competitive and cooperative relationship between multi-energy hubs, the game theoretic optimal scheduling model of the multi-energy hub system was established. Then, two cases and 50 groups of wind speed series were used to test the robustness of the proposed method. Simulation results show that the total power injection is −16,805.8, 104.1847, and −865.561 and the natural gas injection is 46,046.81, 27,727.65, and 63,039.54 in spring/autumn, summer, and winter, respectively, which is consistent with the characteristics of the four seasons. Furthermore, the optimal scheduling method using game theory has a strong robustness in multi-energy hub systems.

Using Sample Entropy to assess complexity of wind speed dynamics

In this paper we analyzed the complexity of the time series of wind speed in Petrolina, Brazil at heights of 25 and 50 m. We applied the sample entropy ( SampEn ) method on wind speed temporal series for each month of 2010, in order to analyze the intra-annual variability of complexity for wind dynamics and its relation with the wind potential. The results showed that wind speed fluctuations are more regular when comparing consecutive data sequences over one hour periods. Although the average wind speed was higher at 50m, indicating higher wind potential, the values of SampEn were also higher between June and September indicating a greater complexity of wind dynamics and consequently lower efficiency in wind energy capture. In the months of February, October, and November, when the average wind speed exceeded the minimum value for generation of wind power (3.5 m s -1 ) at both heights, the average wind speed increased and the entropy decreased with height. This indicates a higher wind potential and more regularity of wind dynamics at a height of 50 m, both favorable for wind energy production. For the rest of the year the wind power generation was possible only at height of 50 m.

An approach to model extreme wind speed distributions using the Weather Research and Forecasting model

The aim of this study was to generate hourly mean monthly maximum wind speed return period curves for heights 60 m above the ground using Weather Research and Forecasting modeled data. The methodology introduced produces long-term wind speed data in places where the available measured series for such heights are not long enough for a correct extreme value analysis. Climate Forecast System Reanalysis data are used as input for the Weather Research and Forecasting simulations, providing information for the period 1979–2015. The modeled results are compared with wind speed series measured in anemometric towers, available for the period 2008–2015. Weather Research and Forecasting output is then adjusted to model properly the wind speed at the measuring sites. A good representation of the cumulative distribution of monthly maxima was reached after applying a double linear adjustment.

Smart wind speed deep learning based multi-step forecasting model using singular spectrum analysis, convolutional Gated Recurrent Unit network and Support Vector Regression

Wind speed forecasting can effectively improve the safety and reliability of wind energy generation system. In this study, a novel hybrid short-term wind speed forecasting model is proposed based on the SSA (Singular Spectrum Analysis) method, CNN (Convolutional Neural Network) method, GRU (Gated Recurrent Unit) method and SVR (Support Vector Regression) method. In the proposed SSA-CNNGRU-SVR model, the SSA is used to decompose the original wind speed series into a number of components as: one trend component and several detail components; the CNNGRU is used to predict the trend component, while the SVR is used to predict the detail components. To investigate the prediction performance of the proposed model, several models are used as the benchmark models, including the ARIMA model, PM model, GRU model, LSTM model, CNNGRU model, hybrid SSA-SVR model and hybrid SSA-CNNGRU model. The experimental results show that: in the proposed model, the CNNGRU can have good prediction performance in the main trend component forecasting, the SVR can have good prediction performance in the detail components forecasting, and the proposed model can obtain good results in wind speed forecasting.

Take control with DXA 5000—An innovative automation solution to deliver superior workflow and improve delivery of healthcare

This work analyzes the time series of wind speeds in different regions of the state of Bahia and the Abrolhos Archipelago, Brazil, through the use of the DFA technique (Detrended Fluctuation Analysis) to verify the existence of long-range correlations and associated power laws. The time series of wind velocities are derived from measurements with hourly means that are acquired in three towers equipped with anemometers at heights of 80, 100, 120 and 150 m, and in the Abrolhos Archipelago with measurements taken at 10 m. These measurements are then compared with numerical simulations of the wind speed obtained with the WRF mesoscale model (Weather Research and Forecasting model). In the onshore case, the results of the application of the DFA technique in the measured and simulated datasets show correlations with power laws in two regions of distinct scales (subdiffusive and persistent) for both time series. It is suggested that this occurs due to the mesoscale effects and local circulations acting on the planetary boundary layer, where the turbulence in the daily cycle is generated by thermal (buoyancy) and mechanical (wind shear) forcing. However, in regions that are not subject to local-effect conditions, such as small islands far from the mainland, the synoptic effects are the most important and active in the maritime boundary layer, so the series of real and simulated datasets exhibit only subdiffusive behavior.

A new methodology for local cross-correlation between two nonstationary time series

To measure the degree of local cross-correlation between two nonstationary time series, a new approach with a locally weighted Pearson correlation coefficient based on a simple locally weighted linear regression model was proposed. In this approach, a Gaussian decay-based function is selected as a weighting function. An appropriate bandwidth is selected using an alternative criterion. Some factors influencing the local cross-correlation degree, including long-range exponent estimated by means of a detrended fluctuation analysis (DFA) and seasonal change in the series, are discussed. Artificial and real-world datasets are analyzed. The results show that the proposed method can measure the degree of a locally intrinsic cross-correlation between two series. The contribution of this locally intrinsic cross-correlation is attributed to original input excitation sources and DFA scaling exponents. The effects of seasonal change with a high-frequency in the series on a locally intrinsic cross-correlation are significant. The effects of a low-frequency seasonal change are insignificant. A positive local cross-correlation between a synchronous wind speed and air pollution index series in Nanjing, China is observed, which is related to externally imported air pollution sources. Consistent results are obtained by comparing the new method with the detrended cross-correlation coefficientρDCCA. Therefore, the proposed approach is reliable, reasonable, and applicable, and can examine the degree of the local intrinsic cross-correlation between two nonstationary time series.

A novel non-linear combination system for short-term wind speed forecast

As an important clean energy source, wind power has strong influence on the safe operation of the power grid. Because its output depends directly on the wind speed, it is of great significance to accurately forecast the short-term wind speed. However, many previous studies have two shortcomings: they only focus on the original data without extracting the information of the error sequence; most of them are based on single optimization and neglected the importance of increasing the accuracy and stability simultaneously. Therefore, a novel hybrid model based on data feature extraction and multi-objective optimization combining the original wind speed series with the error sequence non-linearly is proposed for short-term forecasting. It consists of two steps: (a) obtain error sequence by the preliminary prediction, and (b) Combining the error sequence with the preliminary results to obtain the final predicted value. In addition, a hybrid Elman neural network (ENN) optimized by multi-objective grey wolf optimization (MOGWO) is proposed to achieve high accuracy and stability at the same time. To analyze the performance, four datasets collected from different wind fields are utilized as an example. The results demonstrate the proposed forecasting model reaches superior accuracy and stability when compared with other contrast models.

Short-term wind speeds prediction of SVM based on simulated annealing algorithm with Gauss perturbation

Wind speed prediction is an efficient means to reduce the downside effects of large-scale wind power generation on the grid, but the behaviour of wind speeds is nonlinear and non-stationary, which yields adverse challenge for its prediction. This work proposes a method of prediction for short-term wind speed, which makes Simulated Annealing Fruit fly Optimization Algorithm based on Gaussian Disturbance (GDSAFOA) to optimize the Support Vector Machine (SVM). In the method, Grey Relational Analysis (GRA) is used to select the factors which influence wind speeds prediction. A time series of wind speeds is decomposed by the Ensemble Empirical Mode Decomposition (EEMD). The wind speeds predication is the linear combination of the SVM and the dynamic neural network model based on the nonlinear autoregressive models with exogenous inputs (NARX). This method is applied for the model with wind speeds data measured from a wind farm in China’s Shanxi Province, where results exhibit that the proposed method is feasible and competitive.

A Data-Driven Short-Term Forecasting Model for Offshore Wind Speed Prediction Based on Computational Intelligence

Wind speed forecasting is an important element for the further development of offshore wind turbines. Due to its importance, many researchers have proposed different models for wind speed forecasting that differ in terms of the time-horizon of the forecast, types and number of inputs, complexity, structure, and others. Wind speed series present high nonlinearity and volatilities, and thus an effective model should successfully deal with those features. An approach to deal with the nonlinearities and volatilities is to utilize a time series processing technique such as the wavelet transform. In the present paper, an ensemble data-driven short-term wind speed forecasting model is developed, tested and applied. The term “ensemble” refers to the combination of two different predictors that run in parallel and the prediction is obtained by the predictor that leads to the lowest error. The proposed model utilizes the wavelet transform and is compared with other models that have been presented in the related literature and outperforms their accuracy. The proposed forecasting model can be used effectively for 1 min and 10 min ahead horizon wind speed predictions.

Implementation of Pattern Recognition Algorithms in Processing Incomplete Wind Speed Data for Energy Assessment of Offshore Wind Turbines

Offshore wind turbine (OWT) installations are continually expanding as they are considered an efficient mechanism for covering a part of the energy consumption requirements. The assessment of the energy potential of OWTs for specific offshore sites is the key factor that defines their successful implementation, commercialization and sustainability. The data used for this assessment mainly refer to wind speed measurements. However, the data may not present homogeneity due to incomplete or missing entries; this in turn, is attributed to failures of the measuring devices or other factors. This fact may lead to considerable limitations in the OWTs energy potential assessment. This paper presents two novel methodologies to handle the problem of incomplete and missing data. Computational intelligence algorithms are utilized for the filling of the incomplete and missing data in order to build complete wind speed series. Finally, the complete wind speed series are used for assessing the energy potential of an OWT in a specific offshore site. In many real-world metering systems, due to meter failures, incomplete and missing data are frequently observed, leading to the need for robust data handling. The novelty of the paper can be summarized in the following points: (i) a comparison of clustering algorithms for extracting typical wind speed curves is presented for the OWT related literature and (ii) two efficient novel methods for missing and incomplete data are proposed.

Multi-step short-term wind speed forecasting approach based on multi-scale dominant ingredient chaotic analysis, improved hybrid GWO-SCA optimization and ELM

Accurate wind speed prediction possesses a significant impact on reasonable scheduling and safe operation of power system. For this purpose, a novel hybrid approach based on multi-scale dominant ingredient chaotic analysis, improved hybrid GWO-SCA (IHGWOSCA) algorithm and extreme learning machine (ELM) is proposed for multi-step short-term wind speed prediction, in which the multi-scale dominant ingredient chaotic analysis combines the proposed optimal variational mode decomposition (OVMD), singular spectrum analysis (SSA) and phase space reconstruction (PSR). To begin with, the mode number and updating step of VMD are pre-determined by center frequency observation method and the proposed least-squares error index (LSEI), thus decomposing the non-stationary wind speed series into a set of intrinsic mode functions (IMFs). Later, the extraction of the dominant ingredient and residuary ingredient for each sub-series is implemented by SSA for the construction of forecasting components. Subsequently, the proposed IHGWOSCA algorithm coded with discrete integers and real-valued are investigated to search optimal parameters in PSR and ELM successively. Lastly, the ultimate forecasting results of the original wind speed are calculated by accumulating results of all the predicted components. Furthermore, seven data sets from Sotavento Galicia and Inner Mongolia have been employed to evaluate the proposed approach. The results illustrate that: (1) the proposed OVMD-based models obtained better RMSE, MAE and MAPE indexes comparing with the benchmark models through weakening the non-stationary of the original signal; (2) the proposed dominant ingredient chaotic analysis combining SSA and PSR enhanced the multi-steps prediction performance effectively; (3) the proposed IHGWOSCA optimization algorithm possessed good capability for optimal parameters searching and fast convergence.

An innovative hybrid system for wind speed forecasting based on fuzzy preprocessing scheme and multi-objective optimization

Abstract Wind energy is attracting increasing attention with its sustainability and cleanliness. However, owing to the volatility and intermittency of wind speed, it is challenging to establish a scientific and reliable forecasting system. Most research has mainly been based on simple data preprocessing, single objective optimization, and point prediction, which may lead to poor forecasting performance. Hence, in this study, an innovative wind speed forecasting system is developed that incorporates effective data preprocessing and a novel algorithm. In order to alleviate the complexity and chaos of a wind speed series, a fuzzy data preprocessing scheme is designed based on “decomposition and ensemble” and a fuzzy time series. Following this, a multi-objective imperialist competitive algorithm (MOICA) is proposed and applied for optimizing an extreme learning machine (ELM), and a corresponding hybrid predictor MOICA-ELM is conducted for wind speed forecasting. For further investigation the uncertainty of wind speed, both point and interval forecasting are employed in this system. Simulation results on four wind speed datasets collected from two wind farms in China are in good accordance with the empirical data with multiple criterion and scientific evaluation; these results and show a good performance of the proposed system in terms of accuracy and stability.

Scenario generation and probabilistic forecasting analysis of spatio-temporal wind speed series with multivariate autoregressive volatility models

This paper evaluates the application of a family of VAR-mGARCH (Vector AutoRegressive with multivariate AutoRegressive Conditional Heteroskedasticity) volatility models to the problem of modeling (i.e. generating correct in-sample scenarios) and forecasting in a probabilistic way three univariate but mutually dependent wind speed hourly series. The evaluation starts from the consideration that optimal modeling and optimal forecasting are not necessarily attained by the same models, and that they are assessed in different ways. The proposed VAR-mGARCH family, originated in Finance, consists of the VAR-BEKK (VAR - Baba, Engle, Kraft and Kroner) model and the VAR-DCC (VAR - Dynamic Conditional Correlation) model, the latter seen as the simplified and more scalable version of the former. These models were never used in wind speed studies before. Both models will be used with Gaussian innovations, and the VAR-DCC model will be also used with Student’s t innovations. These models, which are able to dynamically couple volatilities, are compared to two benchmark model sets, the first set consisting of three independent univariate AR-GARCH (i.e. non-vector) models, the second set consisting of an individual VAR model without the GARCH sector. These benchmark models cannot dynamically couple volatilities. Both benchmark model sets will be used with Gaussian innovations. The time series used for the evaluation are taken from three North-American wind metering sites located at few tens of kilometers from each other. In order to highlight the usefulness of choosing autoregressive coupled volatility schemes for modeling and forecasting spatially and temporally varying wind speed data, a controlled variance electricity generation portfolio example of Markowitz type, typical of Energy Finance, is also discussed at some length. In all, it is concluded that the VAR-DCC model with Student’s t innovations is the most balanced choice for this data set when the three goals of modeling, forecasting and scalability in the number of considered sites are taken into account at once.

A Copula Function Based Monte Carlo Simulation Method of Multivariate Wind Speed and PV Power Spatio-Temporal Series

As high penetration of uncertain wind and solar energy into power system, spatio-temporal correlation of wind and solar energy is of great necessity for planning and operation of wind farms and PV plants. A Copula function and first order Markov process based Monte Carlo simulation method of multivariate wind speed and PV power spatio-temporal series is proposed in this paper. In the proposed approach, either spatial correlation or temporal correlation of wind speed and PV power series is considered including cross-correlation between all series and self-correlation of every series. The results of case study based on National Renewable Energy Laboratory (NREL) of the U.S. Department of Energy are analyzed, which verify the scientific and feasibility of the proposed approach.

Research on Combined Model Based on Multi-Objective Optimization and Application in Wind Speed Forecast

Wind power is an important part of a power system, and its use has been rapidly increasing as compared with fossil energy. However, due to the intermittence and randomness of wind speed, system operators and researchers urgently need to find more reliable wind-speed prediction methods. It was found that the time series of wind speed not only has linear characteristics, but also nonlinear. In addition, most methods only consider one criterion or rule (stability or accuracy), or one objective function, which can lead to poor forecasting results. So, wind-speed forecasting is still a difficult and challenging problem. The existing forecasting models based on combination-model theory can adapt to some time-series data and overcome the shortcomings of the single model, which achieves poor accuracy and instability. In this paper, a combined forecasting model based on data preprocessing, a nondominated sorting genetic algorithm (NSGA-III) with three objective functions and four models (two hybrid nonlinear models and two linear models) is proposed and was successfully applied to forecasting wind speed, which not only overcomes the issue of forecasting accuracy, but also solves the difficulties of forecasting stability. The experimental results show that the stability and accuracy of the proposed combined model are better than the single models, improving the mean absolute percentage error (MAPE) range from 0.007% to 2.31%, and the standard deviation mean absolute percentage error (STDMAPE) range from 0.0044 to 0.3497.

Short-Term Wind Speed Forecasting Based on Hybrid Variational Mode Decomposition and Least Squares Support Vector Machine Optimized by Bat Algorithm Model

With the integration of wind energy into electricity grids, wind speed forecasting plays an important role in energy generation planning, power grid integration and turbine maintenance scheduling. This study proposes a hybrid wind speed forecasting model to enhance prediction performance. Variational mode decomposition (VMD) was applied to decompose the original wind speed series into different sub-series with various frequencies. A least squares support vector machine (LSSVM) model with the pertinent parameters being optimized by a bat algorithm (BA) was established to forecast those sub-series extracted from VMD. The ultimate forecast of wind speed can be obtained by accumulating the prediction values of each sub-series. The results show that: (a) VMD-BA-LSSVM displays better capacity for the prediction of ultra short-term (15 min) and short-term (1 h) wind speed forecasting; (b) the proposed forecasting model was compared with wavelet decomposition (WD) and ensemble empirical mode decomposition (EEMD), and the results indicate that VMD has stronger decomposition ability than WD and EEMD, thus, significant improvements in forecasting accuracy were obtained with the proposed forecasting models compared with other forecasting methods.

A Novel System for Wind Speed Forecasting Based on Multi-Objective Optimization and Echo State Network

Given the rapid development and wide application of wind energy, reliable and stable wind speed forecasting is of great significance in keeping the stability and security of wind power systems. However, accurate wind speed forecasting remains a great challenge due to its inherent randomness and intermittency. Most previous researches merely devote to improving the forecasting accuracy or stability while ignoring the equal significance of improving the two aspects in application. Therefore, this paper proposes a novel hybrid forecasting system containing the modules of a modified data preprocessing, multi-objective optimization, forecasting, and evaluation to achieve the wind speed forecasting with high precision and stability. The modified data preprocessing method can obtain a smoother input by decomposing and reconstructing the original wind speed series in the module of data preprocessing. Further, echo state network optimized by a multi-objective optimization algorithm is developed as a predictor in the forecasting module. Finally, eight datasets with different features are used to validate the performance of the proposed system using the evaluation module. The mean absolute percentage errors of the proposed system are 3.1490%, 3.0051%, 3.0618%, and 2.6180% in spring, summer, autumn, and winter, respectively. Moreover, the interval prediction is complemented to quantitatively characterize the uncertainty as developing intervals, and the mean average width is below 0.2 at the 95% confidence level. The results demonstrate the proposed forecasting system outperforms other comparative models considered from the forecasting accuracy and stability, which has great potential in the application of wind power systems.

Direct Multistep Wind Speed Forecasting Using LSTM Neural Network Combining EEMD and Fuzzy Entropy

Accurate wind speed forecasting is of great significance for a reliable and secure power generation system. In order to improve forecasting accuracy, this paper introduces the LSTM neural network and proposes a wind speed statistical forecasting method based on the EEMD-FuzzyEn-LSTMNN model. Moreover, the MIC is used to analyze the autocorrelation of wind speed series, and the predictable time of wind speed statistical forecasting method for direct multistep forecasting is taken as four hours. In the EEMD-FuzzyEn-LSTMNN model, the original wind speed series is firstly decomposed into a series of components by using EEMD. Then, the FuzzyEn is used to calculate the complexity of each component, and the components with similar FuzzyEn values are classified into one group. Finally, the LSTMNN model is used to forecast each subsequence after classification. The forecasting result of the original wind speed series is obtained by aggregating the forecasting result of each subsequence. Three forecasting cases under different terrain conditions were selected to validate the proposed model, and the BPNN model, the SVM model and the LSTMNN model were used for comparison. The experimental results show that the forecasting accuracy of the EEMD-FuzzyEn-LSTMNN model is much higher than that of the other three models.