Wind Speed Fluctuations Research Articles

Improving wind power forecast accuracy for optimal hybrid system energy management

Abstract Due to its renewable and sustainable features, the wind energy is growing up around the word. However, the wind speed fluctuation induces the intermittent character of the generated wind power. Thus, wind power estimation, through wind speed forecasting, is very inherent to ensure an effective power scheduling. Four wind speed predictors based on deep learning networks and optimization algorithms, were developed. The designed topologies are the multilayer perceptron neural network, the long short-term memory network, the convolutional short-term memory network and the bidirectional short-term neural network coupled with the Bayesian optimization. The models performance was evaluated through evaluation indicators mainly, the root mean squared error, the mean absolute error and the mean absolute percentage. Based on the simulation results, all of them show a considerable prediction results. Moreover, the combination of the the long short-term memory network and the optimization algorithm is more robust on wind speed forecasting with a mean absolute error equal to 0.23 m/s. The estimated wind power was investigated for an optimal Wind/PV/Battery/Diesel energy management. The handling approach lies on the continuity of the load supply through the renewable sources as priority, the batteries on second order and finally the diesels. The proposed management strategy respects the designed criteria with satisfactory contribution percentage of the renewable sources equal to 71%.

Wind speed estimation and maximum power point tracking using neuro-fuzzy systems for variable-speed wind generator

This paper proposes a novel method using a machine learning-based Adaptive Neuro-Fuzzy Inference System (ANFIS) to optimize Maximum Power Point Tracking (MPPT) in variable-speed Wind Turbines (WT). The ANFIS algorithm, blending artificial neural networks and fuzzy logic, addresses issues with traditional wind speed sensors, such as cost, imprecision, and susceptibility to adverse weather conditions. An initial offline-trained ANFIS is suggested to understand turbine power characteristics, and subsequently estimate varying wind speed, addressing strong nonlinearity due to WT aerodynamics and wind speed fluctuations. A second ANFIS efficiently tracks the maximum power point, overcoming limitations of linear controllers. Implemented in Matlab/Simulink for a 3.5 kW WT, the approach demonstrates effectiveness, precision, and faster response time in wind speed estimation and accurate MPPT compared to alternatives. A notable advantage is its independence from instantaneous wind speed measurement, providing a cost-effective solution for wind energy systems.

Voltage Control Strategy for Large-Scale Wind Farm with Rapid Wind Speed Fluctuation

Voltage Control Strategy for Large-Scale Wind Farm with Rapid Wind Speed Fluctuation

Intelligent control of the power generation system using DSPACE

AbstractWind power systems (WPs) are complex non‐linear systems with varying parameters affected by environmental changes, including wind speed fluctuations. Extracting maximum power from WPs poses a significant challenge due to these factors. Direct power control (DPC) is a highly effective technique known for its simplicity and ease of implementation. However, it suffers from power ripples caused by the use of hysteresis comparators and switching tables that operate at variable frequencies. To address this issue, this paper presents the robust neural controller (NC) based on DPC, which replaces the switching tables. The Double‐Fed Induction Generator (DFIG) is the chosen generator for the studied WP system due to its advantageous features. The NC‐DPC effectively regulates the exchange of active and reactive powers between the DFIG and the system, maximizing power extraction from the WP system while reducing Total Harmonic Distortion and enhancing overall system quality. The effectiveness of the NC‐DPC is evaluated through MATLAB simulations and further supported by experimental data obtained using the Real‐Time Interface of the dSPACE‐DS1104 Controller card.

Experimental study on rooftop flow field of building based on the operation of vertical-axis wind turbines

Vertical-axis wind turbines (VAWTs) demonstrate good adaptability for harnessing wind energy on the building rooftops. However, knowledge gaps still exist in the understanding of the wind resources on the rooftop, the operation of VAWTs, and its effect on the wind field. To add new knowledge on this subject, the operation of wind turbines modeled by the NACA0018 airfoil on the rooftop of a building is experimentally studied via wind tunnel. The results indicate that flow above the rooftop of building shows an obvious speed reduction due to the blunt body effect of the turbines, and the turbulence intensities are dramatically enhanced. The different tip-speed ratios, wind directions, and installation locations of wind turbine have significant effect on flow field on the roof. Due to the flow characteristics above the rooftop, the power spectral density of the fluctuating wind speed exhibits high energy below the top position of the VAWT on the rooftop. Additionally, the wind profiles and probability distribution of the wake of VAWTs on the rooftop are analyzed and mathematically fitted for quantifying wind field characteristics rooftop turbines on the roof. For the VAWTs investigated in this study, the impacts of the operation of VAWTs on the wind field are non-negligible on the roof of building. The findings of this study will provide valuable insights for the optimal placement of VAWTs and utilization of wind energy on the rooftops.

A Novel Adaptive Third-Order Continuous Super-Twisting Controller of a Five Phase Permanent Magnet Synchronous Wind Generator

The aim of this research is to enhance the control of a Wind Energy Generating System (WEGS) incorporating a Five-phase Permanent Magnet Synchronous Generator (5 ph-PMSG) and addressing operational challenges in the presence of disturbances. The commonly employed Second-Order Super-Twisting Controller (SOSTC), with constant gains, has limitations, including uncertainties, significant transient state errors, and chattering effects, hindering its practical applicability. To overcome these drawbacks, the study proposes the application of an Adaptive Third-Order Continuous Super-Twisting Control (ATOCSTC). This novel approach integrates a third-order sliding mode surface, a smoothly continuous switching control term, and an adaptation law. Unlike the conventional SOSTC using discontinuous “sign” functions, ATOCSTC dynamically adjusts gains using tangent hyperbolic functions, providing a continuous and effective control mechanism. Comparative analysis with the conventional SOSTC under various disturbances such as wind speed fluctuations, parameter variations, and Grid Voltage Sag (GVS), reveals significant improvements with ATOCSTC. Notably, ATOCSTC leads to a 75% reduction in power ripples for grid active power and a 40.38% reduction for grid reactive power. These findings underscore the superior performances obtained with the proposed ATOCSTC in WEGS.

Wake measurement of wind turbine under yawed conditions using UAV anemometry system

This study employs a UAV anemometry system to assess the wind field around a yawed wind turbine, particularly focusing on its wake during operational conditions. The research findings reveal that the evolution of wind turbine wakes follows distinct patterns at various downstream distances. Turbulence intensity notably amplifies within regions characterized by significant fluctuations in mean wind speed. Specifically, in yawed conditions, the areas with the highest turbulence generated by the rotor coincide with zones exhibiting pronounced variations in mean wind speed. The heightened turbulence within the wake region to some extent constrains the safety and economic viability of wind farms. Turbulence intensity increases significantly in the region where the average wind speed changes greatly, that is, under the yaw state of the wind turbine, this region is characterized with the strongest turbulence generated by the rotor. The UAV anemometry system's wind speed assessment closely matches predictions from the Y-3DJGF model, accounting for wake experience coefficient adjustments. Furthermore, in yaw conditions, the wind turbine's wake trajectory exhibits some deviation from the incident flow's direction, with an initial increase in slope followed by gradual stabilization. As the downstream distance increases, the trajectory will eventually establish a consistent trend with the incident flow. The cost-effective and flexible UAV anemometry system enhances wind field measurements, offering an innovative approach for wind energy sector research and engineering.

Anomaly detection of wind turbine based on norm-linear-ConvNeXt-TCN

The supervisory control and data acquisition (SCADA) system of wind turbines continuously collects a large amount of monitoring data during their operation. These data contain abundant information about the operating status of the turbine components. Utilizing this information makes it feasible to provide early warnings and predict the health status of the wind turbine. However, due to the strong coupling between the various components of the wind turbine, the data exhibits complex spatiotemporal relationships, multiple state parameters, strong non-linearity, and noise interference, which brings great difficulty to anomaly detection of the wind turbine. This paper proposes a new method for detecting abnormal operating conditions of wind turbines, based on a cleverly designed multi-layer linear residual module and the improved temporal convolutional network (TCN) with a new norm-linear-ConvNeXt architecture (NLC-TCN). Initially, the NLC-TCN deep learning reconstruction model is trained with historical data of normal behavior to extract the spatiotemporal features of state parameters under normal operational conditions. Subsequently, the condition score of the unit is determined by calculating the average normalized root mean square error between the reconstructed data and actual data. The streaming peaks-over-threshold real-time calculation of the anomaly warning threshold, based on extreme value theory, is then used for preliminary fault monitoring. Moreover, by shielding the fault alarm for low wind speeds and implementing a continuous delay perception mechanism, issues related to wind speed fluctuations and internal and external interference are addressed, enabling early warning for faulty units. Finally, the effectiveness and reliability of the proposed method are validated through comparative experiments using actual offshore wind farm SCADA data. The performance of the proposed method surpasses that of other compared methods. Additionally, the results of the proposed method were evaluated using the uniform manifold approximation and projection dimensionality reduction technique and kernel density estimation.

Diurnal variations in wind power density analysis for optimal wind energy integration in different Indian sites

Wind power is becoming increasingly crucial in the global transition to sustainable energy systems. It is rare to find studies based on diurnal variation of wind energy potential for different sites. Seasonal patterns could lead to overestimating the night-time and underestimating the daytime wind power density (WPD), resulting in load losses and higher generation costs. Present study includes Diurnal variations in WPD, that will estimate energy generation patterns more accurately. Current analysis uses hourly wind speed data collected from IMD for six coastal Indian sites spanning 1969–2007. Seasonal, monthly, and diurnal variations at 30 m and 60 m hub heights are analyzed using Weibull distribution model. The peak diurnal WPD of 714.53 W/m2 is observed in Tuticorin during July at 60 m hub height, and the lowest is found during December. The results show substantial differences between day and night WPD, emphasizing the importance of accounting for diurnal wind speed fluctuations. This study can be helpful for the proper sizing of energy storage systems to ensure uninterrupted energy supply throughout the day and night, installing hybrid energy storage systems. It can also help designing hybrid energy systems for power generation, reducing operational costs and environmental impacts.

Large eddy simulation of aerodynamic wind pressure on a tall rectangular building by modified synthetic volume forcing method

To accurately predict wind pressures on a tall building by numerical Computational Fluid Dynamics (CFD) using the Large-Eddy Simulation (LES) turbulent model, it is essential to generate inflow with realistic turbulence characteristics. The Discretizing and Synthesizing Random Flow Generation (DSRFG) method, as one of the synthetic Fourier methods, has received significant attention in the Computational Wind Engineering (CWE) community because of its ability to strictly satisfy the continuity condition and generate turbulent wind with the desired power spectra. In traditional LES, the desired turbulent wind is normally generated and specified at the inlet. However, this treatment often leads to significant attenuation in turbulence energy in the high-frequency band of the fluctuating wind speed spectrum along the flow direction and unrealistic large-amplitude wind pressure fluctuations, resulting in unsatisfactory prediction performance. The Synthetic Volume Forcing (SVF) method effectively overcomes these limitations by introducing turbulence as volume force into the moment Navier-Stokes (N-S) equations. In this study, the DSRFG method is applied to generate a fluctuating wind field in combination with the SVF method to simulate dynamic wind pressures on a tall rectangular building through open-source software OpenFOAM. The turbulence intensity amplification factor (TIAF) is introduced in the SVF method to further improve its simulation accuracy. Comparison of results with wind tunnel test results verifies that the proposed TIAF-SVF numerical method developed in this study achieved sufficient accuracy in predicting wind pressures on tall buildings.

Increased power capture efficiency of large-scale wind turbines using model-free coordinated pitch, yaw, and torque control with wind direction estimation in diverse environmental conditions

Offshore large-scale wind turbine systems (LSWTS) face challenges in pitch and yaw management mainly due to unreliable wind direction measurements, delayed responses, and redundant yaw movements, reducing their optimal efficiency under various offshore renewable environmental conditions. To address this problem and increase power capture, this study introduces a model-free coordinated super-twisting pitch, yaw, and generator torque control for LSWTS under various wind speed and direction conditions. To achieve this, a dynamic model of the weather vane is first designed to accurately measure the wind directions under fluctuating wind speed and environmental conditions. At the same time, the onshore/offshore LSWTS weather vane model is formulated to operate under optimal conditions considering air density, temperature, humidity, and external disturbances. Then, super-twisting control based on an enhanced adaptive barrier function is proposed for the coordinated control operation of the pitch, yaw, and generator torque actuators for stable maximum power extraction of the offshore LSWTS. Finally, simulation and comparative studies are presented to signify the increased power capture ability of the proposed scheme for both a 4.8 MW benchmark and a 20 MW PMVG-based offshore LSWTS to verify robustness against wind gusts, direction changes, and model uncertainties.

A novel dynamic spatio-temporal graph convolutional network for wind speed interval prediction

It is crucial to predict the wind speed for the utilization of renewable wind energy and the operation of transmission lines with increased capacity. The intermittency and stochastic fluctuations of wind speed pose a significant challenge for the high-quality wind speed prediction, and a novel wind speed interval prediction (WSIP) model is constructed in this study by employing the residual estimation (RE)-oriented dynamic spatio-temporal graph convolutional network (DSTGCN) approach. Firstly, a dynamic adjacency matrix is designed to obtain time-varying global spatial weight allocations among each wind speed node. Then, the spatio-temporal features are extracted by using gated recurrent units (GRUs) and GCNs to construct the wind speed graph networks. Moreover, the RE-oriented strategy incorporating the pinball loss is designed to provide a guidance the parameter training of the constructed model, thus eliminating the quantile crossings problem. As a result, the deterministic point prediction of the wind speed is expanded to the quantile-based probabilistic interval prediction. Finally, the experimental results are presented to demonstrate the validity and superiority of proposed scheme in both qualitative and quantitative performance.

Active power smoothing control strategy of offshore wind power system based on reduced matrix converter

On account of the fluctuation and randomness of wind speed, the output power of wind turbines fluctuates greatly, which may cause the frequency change of the power grid and increase the difficulty of power system dispatching. To solve this problem, an active power smoothing control (APSC) strategy based on RMC for offshore wind power systems is proposed in this paper. Compared with existing wind power converter systems, RMC adopted in this paper has the advantages of compact structure, small volume and high conversion efficiency. Based on the analysis of the exponential moving average (EMA) algorithm, a method for determining active power based on the fuzzy EMA algorithm is proposed. The method adjusts the cycle number N in real-time according to the wind speed, taking into account both the wind energy utilization rate and the smoothing performance of active power. The control principle of offshore wind power generation system (WPGS) based on RMC is analyzed in detail and the coordinated control strategy of RMC and inverter is proposed. Simulation results demonstrate the validity of the proposed method and control strategy.

Experimental Study of Wake Evolution under Vertical Staggered Arrangement of Wind Turbines of Different Sizes

During the expansion of a wind farm, the strategic placement of wind turbines can significantly improve wind energy utilization. This study investigates the evolution of wake turbulence in a wind farm after introducing smaller wind turbines within the gaps between larger ones, focusing on aspects such as wind speed, turbulence intensity, and turbulence integral length scale. The flow field conditions are described using parameters like turbulence critical length and power spectral density, as determined through wind tunnel experiments. In these experiments, a single large wind turbine model and nine smaller wind turbine models were used to create a small wind farm unit, and pressure distribution behind the wind turbines was measured under various operating conditions. The results indicate that downstream wind speed deficits intensify as the number of small wind turbines in operation increases. The impact of these smaller turbines varies with height, with a relatively minor effect on the upper blade tip and increasingly adverse effects as you move from the upper blade tip to the lower blade tip. Through an analysis of power spectral density, the contribution of vortex motion to wake turbulence kinetic energy is further quantified. In the far wake region, the number of small wind turbines has a relatively small impact on wind speed fluctuations.

Enhancing Frequency Regulation Support through Several Synthetic Inertial Approaches for WDPS

The aim of this paper is to propose an enhancement to the primary frequency control (PFC) of the San Cristobal Island hybrid wind–diesel power system (WDPS). Naturally, variable speed wind turbines (VSWT) provide negligible inertia. Therefore, various control strategies, i.e., modified synthetic inertial control, droop control and traditional inertial control, if introduced into VSWT, enable them to release hidden inertia. Based on these strategies, a WDPS has been simulated under seven different control strategies, to evaluate the power system performance for frequency regulation (FR). Furthermore, the student psychology-based algorithm (SBPA) methodology is used to optimize the WDPS control. The results show that modified synthetic inertial control is the most suitable approach to provide FR. However, further exhaustive research validates that droop control is a better alternative than modified synthetic inertial control due to the negligible system performance differences. In addition, droop control does not require a frequency derivative function in the control system. Therefore, the hybrid system is more robust. Moreover, it reduces the steady state error, which makes the power system more stable. In addition, a pitch compensation control is introduced in blade pitch angle control (BPAC) to enhance the pitch angle smoothness and to help the power system to return to normal after perturbations. Moreover, to justify the performance of hybrid WDPS, it is tested under certain real-world contingency events, i.e., loss of a wind generator, increased wind speed, fluctuating wind speed, and simultaneously fluctuating load demand and wind speed. The simulation results validate the proposed WDPS control strategy performance.

A wind speed forcasting model based on rime optimization based VMD and multi-headed self-attention-LSTM

Due to the nonlinearity, fluctuation, and intermittency of wind speed, its accurate prediction is essential for improving efficiency in wind power operation systems. In this regard, a hybrid model that combines the rime optimization algorithm (RIME), variational mode decomposition (VMD), multi-headed self-attention (MSA) mechanism and long short-term memory (LSTM) is proposed for wind speed prediction. First, the number of modes and VMD penalty parameter are optimized with RIME, the optimized parameters are brought into the VMD to decompose the raw wind speeds, and a Lagrange multiplier and quadratic penalty function are introduced to obtain the input series. Then, a LSTM short-term wind speed prediction model is constructed based on the MSA mechanism and solved for the hidden states and weights of each layer of attention in the model. Finally, a ReLU activation function is used to activate the hidden states of the LSTM model, and a weighted sum vector is used as the final sequence representation, which is inputted to the output layer for specific prediction to obtain the short-term wind speed prediction results. To verify the effectiveness of the proposed model, wind speed data from four wind farms in Ningxia, China, and two sets of wind speed data from an M2 tower in the USA are selected, and 19 models are built to compare the performance of the proposed model. The results show that the proposed model outperforms other models on all datasets in terms of all five performance metrics, with smaller errors and higher prediction accuracy.

A New Thermal Management Strategy of IGBT in DFIG for Economic Benefit Maximization

Wind speed fluctuation generally shortens the lifetime of the insulated gate bipolar transistor (IGBT) module in the doubly fed induction generator (DFIG), which leads to frequent component replacement and cost increase of wind power generation. Conventional power control strategies consider solely the wind turbine output power maximization, and existing junction temperature thermal management strategies focus on IGBT lifetime extension, both of which are not effective under turbulent wind speed conditions and ignore the trade-off between the device reliability and output power for the overall DFIG economic benefit. To bridge the gap between the IGBT reliability and the output power under turbulent wind speed conditions, we propose a novel IGBT thermal management strategy for optimal economic benefit. Specifically, we first smooth the output power through a linear power control (LPC) method with conditions on the wind speed and turbine speed to reduce the IGBT low-frequency junction temperature fluctuation, which extends IGBT lifetime. We then propose a grid encirclement and suppression search (GESS) method that maximizes the economic benefit defined by LPC-smoothed output power and IGBT lifetime. Simulation shows that our proposed LPC-GESS strategy outperforms a competing strategy at economic benefit by a large margin, up to 15.3%. Our proposed strategy can potentially be used in wind power stations for fast and reliable economic benefit-oriented IGBT thermal management.

A novel intelligent control approach for wind energy conversion systems with synchronous reluctance generators

SummaryThis study addresses a significant research gap in the field of wind energy, focusing on the underutilized potential of synchronous reluctance generators (SynRG) in wind power conversion systems (WPCS). Despite notable advancements in wind energy controls, the capabilities of SynRG within these systems have not been fully explored. In response, we introduce an innovative model‐free control (MFC) approach, termed intelligent proportional (iP), specifically designed and optimized for WPCS equipped with SynRG. This research encompasses the modeling, control, and simulation of SynRG‐based WPCS, aiming to optimize system performance and enhance the quality of grid power supply. The proposed vector control (VC) method utilizes a MFC approach (VC‐iP) to address the limitations inherent in traditional VC methods with proportional‐integral (PI) controllers (VC‐PI). Although widely used for their simplicity, VC‐PI methods often lead to power fluctuations and decreased power and current quality, consequently reducing overall system efficiency. In contrast, VC‐iP markedly enhances power quality and system efficiency, especially in situations involving fluctuating power demand and variable wind speeds. The efficacy of VC‐iP is demonstrated through simulations in two distinct test scenarios that include variations in power demand and random wind speed fluctuations. The results affirm the superiority of VC‐iP in maintaining stable, high‐quality power output from WPCS. This method notably minimizes fluctuations, improves current quality, reduces harmonic distortion and steady‐state error, ensures reliable grid integration, and contributes to a more efficient and sustainable energy system.

Applicability Analysis of Single-Machine Equivalent Method for Modeling Wind Farm Containing Full-Converter Wind Turbine Generators with PMSG

For the analysis of the applicability of single machine equivalent method for modeling wind farm containing full-converter wind turbine generators(WTG) with permanent magnet synchronous generator(PMSG), at frist, single-machine equivalent methods of equivalent model are provided, then the detailed and equivalent wind farm model is built on simulation software DIgSILENT/Power Factory platform. At last, for wind speed fluctuations and grid disturbance, the applicability of single-machine equivalent method is analyzed by comparing dynamic response at point of interconnection between equivalent model and the detailed model of wind farms. Results show that this method is suitable for the dynamic equivalent modeling of wind farm containing directly driven wind turbine with PMSG in certain situations.

WGformer: A Weibull-Gaussian Informer based model for wind speed prediction

Accurate wind speed forecasting can improve energy management efficiency and promote the use of renewable energy. However, the inherent nonlinearity and fluctuation of wind speed make prediction challenging. To address these issues, we design an efficient Informer-based model, with improved calculation speed, forecasting accuracy and generalization ability. The proposed model in this paper reasonably integrates the Weibull-Gaussian transform, Informer and kernel mean square error loss and addresses the combination of various components. The Weibull-Gaussian transform is used as the data preprocessing module, which can remove non-Gaussian characteristics from the original data, and thus achieve noise reduction. The Informer is used as the main predictor, which can efficiently output accurate forecasting results based on an encoder-decoder architecture and self-attention mechanism. The kernel mean square error loss function, which shows strong robustness to outliers, is used to evaluate the nonlinearity of errors in reproducing kernel Hilbert space. To evaluate the performance of the proposed model, it is compared with several widely used models and state-of-the-art models. The experimental results indicate that the proposed model weakens the effect of outliers, yields high forecasting accuracy with mean square error = 0.35, and outperforms the baselines up to 8.5% on three datasets.