Real Wind Speed Research Articles

A State-of-the-Art Fractional Order-Driven Differential Evolution for Wind Farm Layout Optimization

The wind farm layout optimization problem (WFLOP) aims to maximize wind energy utilization efficiency and mitigate energy losses caused by wake effects by optimizing the spatial layout of wind turbines. Although Genetic Algorithms (GAs) and Particle Swarm Optimization (PSO) have been widely used in WFLOP due to their discrete optimization characteristics, they still have limitations in global exploration capability and optimization depth. Meanwhile, the Differential Evolution algorithm (DE), known for its strong global optimization ability and excellent performance in handling complex nonlinear problems, is well recognized in continuous optimization issues. However, since DE was originally designed for continuous optimization scenarios, it shows insufficient adaptability under the discrete nature of WFLOP, limiting its potential advantages. In this paper, we propose a Fractional-Order Difference-driven DE Optimization Algorithm called FODE. By introducing the memory and non-local properties of fractional-order differences, FODE effectively overcomes the adaptability issues of advanced DE variants in WFLOP’s discreteness while organically applying their global optimization capabilities for complex nonlinear problems to WFLOP to achieve more efficient overall optimization performance. Experimental results show that under 10 complex wind farm conditions, FODE significantly outperforms various current state-of-the-art WFLOP algorithms including GA, PSO, and DE variants in terms of optimization performance, robustness, and applicability. Incorporating more realistic wind speed distribution and wind condition data into modeling and experiments, further enhancing the realism of WFLOP studies presented here, provides a new technical pathway for optimizing wind farm layouts.

Wind Shear Coefficient Estimation Based on LIDAR Measurements to Improve Power Law Extrapolation Performance

This study aims to improve power law extrapolation accuracy by proposing a new methodology for wind shear coefficient calculation. Real wind speed profiles, measured with a LIDAR remote sensor at two different sites, were extrapolated according to the power law at heights up to 200 m. Two different definitions of the wind shear coefficient are proposed considering wind speed profiles measured at three, four, and five different heights using either the first height as a reference or all of the heights successively. These two definitions were tested, along with the generally accepted constant values of 1/7, 0.25 at the first site, and 0.2 at the second site, to identify the most efficient one. The extrapolated wind profiles were compared with those measured using LIDAR. The results show that the computed wind shear coefficients provide more accurate results compared with constant wind shear coefficients, as the mean absolute errors at 200 m were reduced from 1.396 m/s to 0.437 m/s at the first site and from 1.203 m/s to 0.411 m/s at the second site.

Enhancing vector control performance in DFIG-based wind turbine through ANFIS controller using real variable wind speed profile

This article focuses on enhancing vector control for a Doubly Fed Induction Generator (DFIG) through the integration of the Adaptive Neuro-Fuzzy Inference System (ANFIS) method and comparing it with the classical Proportional-Integral (PI) controller. In this study, the wind turbine operates on a DFIG connected to the AC power grid. The proposed vector-ANFIS controller is implemented on the rotor-side converter to regulate the current and achieve the desired torque for Maximum Power Point Tracking (MPPT). The system was modeled and simulated using MATLAB Simulink. The simulation employed a real variable wind speed profile to reflect a real-world scenario. our contribution was also to compress several hours of collected data into a matter of seconds, enabling us to simulate a multi-hour period and observe the results in MATLAB. The results demonstrate the superior performance of ANFIS compared to PI, indicating its potential utility in enhancing the power quality and stability of wind power systems.

Profit enhancement and imbalance cost reduction with solar PV-fuel cell-EV hybrid system in a wind-integrated day-ahead power market

Abstract Renewable sources’ volatility and dynamic nature lend several challenges in ensuring power system safety and steadiness. It is crucial to properly evaluate the potential system hazards that may arise in different power system conditions. In a wind-integrated deregulated electricity network, the wind farm (WF) must intimate the power-generating capacity bids to the market controller at least one day before it begins operations. The wind farm’s bid submissions are based on the estimated wind speed (EWS); nevertheless, slight differences between the real wind speed (RWS) and the EWS will result in penalties or incentives imposed by the Independent System Operator (ISO). This occurrence is known as the power market imbalance cost, and it has a direct influence on the system’s profitability. To mitigate this effect, solar PV and fuel cell storage technologies are used with the wind farm to enhance system profit by offsetting the negative effects of the imbalance cost. Here, solar PV and fuel cells are used to function in the required time i.e. operate in the charging mode when the RWS is greater than the EWS and in discharging mode when the EWS is greater than the RWS to balance the power supply in the grid as to fulfill the power bidding conditions. Furthermore, the study focuses on minimizing potential system risks, which have been assessed using several risk assessment tools such as Value-at-Risk (VaR) and Cumulative Value-at-Risk (CVaR). The work was conducted using an IEEE 14 bus test system. Initially, the solar PV-fuel cell system supplies power to meet local needs, and the remaining energy is sent to the grid to maximize the system’s profit. Electric vehicles (EVs) have also been incorporated to maximize the system economy in more quantities and to reduce the system risk further as compared to the solar PV-fuel cell operation. Three different optimization methods, i.e. AGTO (Artificial Gorilla Troops Optimizer Algorithm), ABC (Artificial Bee Colony Algorithm), and SQP (Sequential Quadratic Programming), were used in a comparative analysis to assess the effectiveness of the proposed approach. The use of AGTO in risk assessment and reduction is a major focus of this study.

Complementary Analysis and Performance Improvement of a Hydro-Wind Hybrid Power System

Hydropower as a flexible regulation resource is a rare choice to suppress the ever-increasing penetration of wind power in electrical power systems. The complementary characteristics and performance improvement of a hydro–wind hybrid power system based on a mathematical model of the hybrid power system is studied in this paper. This established model takes into account the stochastic variation in wind speeds in the wind power subsystem and the hydraulic–mechanical–electrical coupling characteristics of the hydropower subsystem. The complementary analysis is conducted based on the evaluation variables outputted by the established model, such as the wind power, hydro-regulation power, hydraulic power, and frequency. To make full use of the regulation capability of the hydropower system, the optimization of parameter settings is also carried out to improve complementary performances of the hybrid power system. The results from the complementary analysis show the detailed characteristics of hydro–wind coordinated operation under different types of real wind speeds. Here, 95% of installed hydro-capacity is used to complement the power shortage of the intermittent wind energy under the low wind speed. Alternatively, only around 66% of the installed hydro-capacity can be utilized to cope with the fluctuation in wind power under the medium and high wind speeds before the optimization of parameter settings. The recommended values and change rules of the control, hydraulic, and electrical parameters for the hydropower system are subsequently revealed from the analysis of parameter settings to contribute to a stable and safe hybrid power system. The results show that the optimized parameter can increase the maximal regulating capacity of the hydropower system by nearly 9 MW, approximately a sixth of the total installed hydropower capacity. The method and results obtained in this paper provide theoretical and technical guidance for the safe and economical operation of power stations.

Investigation of static and dynamic mechanical loads on light-weight PV modules for offshore floating applications

Photovoltaic (PV) systems are significant for the transition towards renewable energy. However, their expansion is constrained by the scarcity of suitable land in proximity to electric grids. To address this issue, floating PV is a promising solution. Ensuring the robustness of floating PV installations remains a major concern, particularly regarding the mechanical load due to strong winds in open water. This study aims to assess the impact of wind on floating PV modules, by considering real wind speed values occurring at the North Sea. To achieve this objective, the influence of PV module configuration, such as inclination, is examined. Moreover, different thicknesses of PV glass are considered to find an optimum between mechanical stability and material consumption. Lastly, a resonance vibration test is performed and compared to simulations to estimate the effects of vibration on PV module stress. The findings indicate that a low inclination installation is preferable, and a glass-glass PV module with a 2.5 mm glass thickness can withstand static and dynamic mechanical loads, although long-term durability requires further investigation. Additionally, it is crucial for the standard Dynamic Mechanical Load (DML) test to include higher pressure values and an extended vibration test at the resonance frequency with the highest measured acceleration, identified after a frequency sweep.

Seasonality in synthetic average wind speed

There is a growing demand for computer-generated realistic high-fidelity wind speed data for various applications in the wind industry. Such data should capture the non-stationary dynamics of real-world wind time series, as well as be consistent with the statistical descriptors – the probability density function and power spectral density – of the observed wind speed. However, complying with the statistical descriptors is not a guarantee that the seasonality will be correctly reproduced in synthetic data. The seasonality, characterized by the average diurnal and seasonal variations, is driven by the periodicities embedded in diurnal and annual harmonic series respectively. Those periodicities are determined by the long-term orbital forcing components, which establish the insolation for a given latitude and longitude. We show that average diurnal and seasonal variations can be visualized as the output of comb filters, whose fundamental frequencies match the diurnal and annual fundamental frequency respectively. The aforementioned theoretical findings are readily reproduced in synthetic wind speed, generated by a non-parametric data-driven statistical model, based on the phase-randomized Fourier transform. The model, tested on both 10-min and 1-min resolution real-world datasets, yields average non-stationarities in synthetic wind speed with the accuracy close to the computing precision.

Interpretable extreme wind speed prediction with concept bottleneck models

Concept-bottleneck models (CBMs) are a new paradigm to construct interpretable classifiers. The CBM architecture can be regarded as a neural network with a single hidden layer whose neurons are replaced by binary classifiers. Each of these binary classifiers implements a concept, that is, it attempts to answer a meaningful yes/no question: the presence or absence of a concept in the observation presented to the network. The output layer is usually implemented as a linear stage that combines the concepts into final decisions. This paper presents an application of the CBM paradigm to a problem of Extreme Wind Speed prediction, such that the forecasting properties of the system can be interpreted in terms of different concepts considered for this problem. A significant contribution of this paper is the proposal of an automated concept generation method, with controlled sparsity, in which the concepts are automatically extracted from the branches of decision trees fitted with informative features that capture the dynamics of the wind speed time series. The final forecasting system is able to predict extreme wind speed values in wind farms with good accuracy and interpretable results, as experiments over real wind speed data from a wind farm in Spain show.

A wind speed forecasting framework for multiple turbines based on adaptive gate mechanism enhanced multi-graph attention networks

Accurately forecasting wind speed is crucial for efficiently utilizing wind energy and scheduling power grids. Recently, Graph Neural Network (GNN) models have been widely utilized to forecast wind speed, which explicitly utilizes the correlation between turbine sites in a wind farm. However, it is challenging to appropriately construct graphs to characterize multiple latent but unknown interdependencies among turbines. This paper proposes a novel multi-site wind speed forecasting framework AG-MGAT, based on an adaptive gate mechanism enhanced multi-graph attention networks. In detail, the contributions of our work are threefold. Firstly, multiple graphs are explicitly constructed, which respectively measure the wind behavioral similarity and the directional causality between turbine sites. Secondly, to calibrate the potential misalignment of spatial-temporal GNNs using these task-agnostic graphs, an adaptive gate mechanism enhanced Graph Attention Network (GAT), AG-GAT, is innovatively designed, which uses a learnable adjacency matrix as gate to adaptively weight the sites' embeddings from the current GAT layer and these directly from the previous AG-GAT layer. At each timestep, the proposed AG-GATs working on the constructed graphs are used to extract the turbine sites' representations that embed the multiple correlations among sites, which are then sent to recurrent neural network for further processing the temporal interdependency. Finally, thorough experiments on real wind speed dataset are conducted and the experimental results show the superiority of our schemes over other state-of-the-art GNN-based forecasting schemes.

Enhancing wind power with permanent magnet synchronous generator control strategies

AbstractDue to the substantial rise in wind power generation, the direct-drive permanent magnet synchronous generator has emerged as a leading technology for efficient variable speed operation, meeting grid demands effectively. This paper presents a comparative analysis of control strategies for permanent magnet synchronous generator based wind turbine using real variable wind speed data from a 2 MW of Tetouan wind farm in Morocco. The proposed approach is based on evaluating two primary control strategies: the adaptive fuzzy-proportional-integral controller and the conventional proportional-integral controller aimed at enhancing the wind turbine's output power. The simulation performed on MATLAB-Simulink indicates that pitch control mechanisms play a crucial role in optimizing power generation, also demonstrating its ability to achieve satisfactory performance.

Multistep short‐term wind speed prediction with rank pooling and fast Fourier transformation

AbstractShort‐term wind speed prediction is essential for economical wind power utilization. The real‐world wind speed data are typically intermittent and fluctuating, presenting great challenges to existing shallow models. In this paper, we present a novel deep hybrid model for multistep wind speed prediction, namely, LR‐FFT‐RP‐MLP/LSTM (linear fast Fourier transform rank pooling multiple‐layer perceptron/long short‐term memory). Our hybrid model processes the local and global input features simultaneously. We leverage RP for the local feature extraction to capture the temporal structure while maintaining the temporal order. Besides, to understand the wind periodic patterns, we exploit FFT to extract global features and relevant frequency components in the wind speed data. The resulting local and global features are, respectively, integrated with the original data and are fed into an MLP/LSTM layer for the initial wind speed predictions. Finally, we leverage a linear regression layer to collaborate these initial predictions to produce the final wind speed prediction. The proposed hybrid model is evaluated using real wind speed data collected from 2010 to 2020, demonstrating superior forecasting capabilities when compared with state‐of‐the‐art single and hybrid models. Overall, this study presents a promising approach for improving the accuracy of wind speed forecasting.

Artificial neural network-based direct power control to enhance the performance of a PMSG-wind energy conversion system under real wind speed and parameter uncertainties: An experimental validation

With the increasing emphasis on embedding advanced technology into system controls, the Direct Power Control (DPC) approach has garnered considerable attention due to its simple and highly adaptable algorithm. This approach has been increasingly recognized in numerous applications. However, the variable frequency, harmonic distortion of the currents, and power ripples caused by Hysteresis controllers and switching tables decrease its effectiveness and robustness, affecting the system’s performance. For this reason, this paper proposed a new DPC based on Artificial Neural Network (ANN) approaches. In this approach, the hysteresis comparator and the switching table are substituted with ANN controllers and then applied on both sides: machine-side converter (MSC) and grid-side converter (GSC) of a Permanent Magnet Synchronous Generator based Wind Energy Conversion System (PMSG-WECS). Moreover, to make the system more efficient in varying wind conditions, this study expands the utilization of the artificial neural networks (ANN) to encompass the maximum power point tracking (MPPT) control strategy. To demonstrate the effectiveness of the proposed approach on the system behaviors, a simulation test was carried out in the Matlab/Simulink environment, using a real wind profile of a Moroccan city (Essaouira). In comparison to the classical DPC control, the simulation results showed the superior performance of the proposed ANN-DPC control in terms of reference tracking, response time, overshoot, precision, and its capacity to reduce the rate of power ripples and total harmonic distortion (THD) in the injected currents. Furthermore, a robustness test was also included in this work to check the robustness of the proposed control against parameters variation. In conclusion, the feasibility and effectiveness of the ANN-DPC control approach were confirmed through experimental validation using the dSPACE DS1104 board.

Real-Time Hardware Simulator for Grid-Tied PMSG Wind Power System

This paper describes a real-time hardware simulator for the grid-tied PMSG wind power system, which consists of an anemometer, a data logger, a motor-generator set with vector drive, and a back-to-back power converter with DSP controller. The anemometer measures the real wind speed, and it is sent to the data logger to calculate the turbine torque. The calculated torque is sent to the vector drive for induction motor after scaled down to the rated simulator power. The motor generates the mechanical power for the PMSG, and the generated electrical power is connected to the grid through a back-to-back converter. The developed simulator can be utilized for analyzing various mechanical and electrical characteristics of grid-tied PMSG wind power system

Analysis, Modeling and Cascade Operation of Wind Energy Fed Dual Active Bridge Converter Operating in Extended Phase Shift and Single Phase Shift Modes: A Comparative Study

In this work, cascade control of wind energy conversion System (WECS) fed Dual Active Bridge (DAB) converter is presented. The Permanent Magnet Synchronous Generator (PMSG) is used to feed the DAB. The real time wind speed data of Muppandal, Tamilnadu, India is fed to the PMSG. The DAB is operated in Extended Phase Shift (EPS) and Single-Phase Shift (SPS) control modes. An outer voltage controller in cascade with an inner current controller is used for closed loop operation of the DAB. The proposed controller is tested for small wind speed variations (13 m/s to 10 m/s) with a step load change and wide changes in wind speed (13 m/s to 8 m/s) accompanied with a step load change. DAB controls the power flow from the WECS to resistive load and its power carrying capability when controlled via the proposed controller is exhibited in the presented work. The proposed configuration controlled via the new cascade EPS controller draws lower power (100 Watts) and offers superior efficiency (85.10%) when compared with cascade SPS controlled microgrid configuration. The cascade controller is tested in MATLAB/Simulink environment and a prototype of DAB is developed in lab for which the cascade controller is tested through the TI-Piccolo-F280049 microcontroller.

Simultaneous Confidence Intervals for All Pairwise Differences between Means of Weibull Distributions

The Weibull distribution is a continuous probability distribution that finds wide application in various fields for analyzing real-world data. Specifically, wind speed data often adhere to the Weibull distribution. In our study, our aim is to compare the mean wind speed datasets from different areas in Thailand. To achieve this, we proposed simultaneous confidence intervals for all pairwise differences between the means of Weibull distributions. The generalized confidence interval (GCI), method of variance estimates recovery (MOVER), and a Bayesian approach, utilizing both gamma and uniform prior distributions, are proposed to construct simultaneous confidence intervals. Through simulations, we find that the Bayesian highest posterior density (HPD) interval using a gamma prior distribution demonstrates satisfactory performance, while the GCI proves to be a viable alternative. Finally, we applied these proposed approaches to real wind speed data in northeastern and southern Thailand to illustrate their effectiveness and practicality.

Estimation of renewable energy systems for mobile network based on real measurements using HOMER software in Egypt

With the increasing of global awareness of the importance of reducing polluting emissions and maintaining a clean and healthy environment. So, the tendency to generate electric energy from new and renewable sources has become an urgent need to achieve this goal. In this paper an optimal economic cost analysis using hybrid renewable energy sources to generate the electricity needed for long-term evolution mobile phone systems was estimated. The proposed electric system accounts for the reduction of polluting emissions to the environment. The electrical profile of the optimal approaches or the hybrid technology and traditional methods which contain solar photovoltaic’, batteries, wind turbines, diesel generator were estimated and provides the electrical power for a Long-Term Evolution mobile network (LTE) as the load at a remote located area. A real time optimal cost analysis of each proposed network is done based on the real load profile, wind speed and solar radiation was placid on from 6 October city in Egypt. Statistical analysis was performed by varying the systems through comparison to determine the optimal approaches based on the Hybrid Optimization Model for Electrical Renewables software (HOMER).

Kernel estimator of extreme value index (EVI) and high quantiles for heavy-tailed distributions under dependence serials using the Box-Cox transformation

The Box-Cox transformation is used to render the data more conducive to statistical analysis. Its application to extreme values statistics improves the convergence rate of certain classical tail index estimators and reduces bias in the context of independent and identically distributed (i.i.d) random variables. In this paper, we explore a bias reduction estimator for the extreme value index under $\beta$-mixing serial dependence. Our approach is based on kernel estimation of the extreme value index and the Box-Cox transformation methodology. Under specific regular conditions, we establish the asymptotic normality of the proposed estimator and deduce an asymptotically unbiased estimator for high quantiles. Through a simulation study, we delineate the performance of our proposals, comparing them to alternative estimators recently introduced in the literature. We further illustrate these theoretical results by applying them to real wind speed data.

Forecasting Wind Power Generation Using Artificial Neural Network

Today, among renewable energy sources, wind energy is used effectively as a clean and sustainable energy source in electricity generation. The uncertain nature of renewable energy sources and the smart ability of the neural network approach to process complex time series inputs have allowed the use of artificial neural network (ANN) methods in the prediction of renewable energy generation. In this study, the speed and power of wind turbines and electricity generation were estimated from wind speed data using artificial neural networks. In our calculations, the real wind speed data were used in the test phase, and the speed-power data of six different types of wind turbines were used in the training phase. It has been shown that the predictions made by our ANN model from the regression curves of the training, validation, and test data obtained are quite successful and reliable. According to our results, it has been understood that the wind potential of our selected region is good enough and that the electrical energy need for this region can be met from wind energy by using the appropriate wind turbine type, so it is quite appropriate to invest in wind energy.

Estimating average wind speed in Thailand using confidence intervals for common mean of several Weibull distributions.

The Weibull distribution has been used to analyze data from many fields, including engineering, survival and lifetime analysis, and weather forecasting, particularly wind speed data. It is useful to measure the central tendency of wind speed data in specific locations using statistical parameters for instance the mean to accurately forecast the severity of future catastrophic events. In particular, the common mean of several independent wind speed samples collected from different locations is a useful statistic. To explore wind speed data from several areas in Surat Thani province, a large province in southern Thailand, we constructed estimates of the confidence interval for the common mean of several Weibull distributions using the Bayesian equitailed confidence interval and the highest posterior density interval using the gamma prior. Their performances are compared with those of the generalized confidence interval and the adjusted method of variance estimates recovery based on their coverage probabilities and expected lengths. The results demonstrate that when the common mean is small and the sample size is large, the Bayesian highest posterior density interval performed the best since its coverage probabilities were higher than the nominal confidence level and it provided the shortest expected lengths. Moreover, the generalized confidence interval performed well in some scenarios whereas adjusted method of variance estimates recovery did not. The approaches were used to estimate the common mean of real wind speed datasets from several areas in Surat Thani province, Thailand, fitted to Weibull distributions. These results support the simulation results in that the Bayesian methods performed the best. Hence, the Bayesian highest posterior density interval is the most appropriate method for establishing the confidence interval for the common mean of several Weibull distributions.

Multi-Step-Ahead Wind Speed Forecast Method Based on Outlier Correction, Optimized Decomposition, and DLinear Model

Precise and dependable wind speed forecasting (WSF) enables operators of wind turbines to make informed decisions and maximize the use of available wind energy. This study proposes a hybrid WSF model based on outlier correction, heuristic algorithms, signal decomposition methods, and DLinear. Specifically, the hybrid model (HI-IVMD-DLinear) comprises the Hampel identifier (HI), the improved variational mode decomposition (IVMD) optimized by grey wolf optimization (GWO), and DLinear. Firstly, outliers in the wind speed sequence are detected and replaced with the HI to mitigate their impact on prediction accuracy. Next, the HI-processed sequence is decomposed into multiple sub-sequences with the IVMD to mitigate the non-stationarity and fluctuations. Finally, each sub-sequence is predicted by the novel DLinear algorithm individually. The predictions are reconstructed to obtain the final wind speed forecast. The HI-IVMD-DLinear is utilized to predict the real historical wind speed sequences from three regions so as to assess its performance. The experimental results reveal the following findings: (a) HI could enhance prediction accuracy and mitigate the adverse effects of outliers; (b) IVMD demonstrates superior decomposition performance; (c) DLinear has great prediction performance and is suited to WSF; and (d) overall, the HI-IVMD-DLinear exhibits superior precision and stability in one-to-four-step-ahead forecasting, highlighting its vast potential for application.