Operation Of Wind Power Systems Research Articles

A coordination control between energy storage based DVR and wind turbine for continuous fault ride‐through

AbstractContinuous fault ride‐through (CFRT) issues often arise in wind power systems. CFRT results in continuous voltage fluctuations which is characterized by “initially decreasing and then increasing” and can significantly disrupt the normal operation of wind power systems. To mitigate CFRT related problems, one approach is the utilization of energy storage (ES) based dynamic voltage restorers (DVRs). Nevertheless, the prohibitive costs and substantial ES requirements hamper practical implementation. In this article, a control scheme incorporating adaptive mode switching and coordinated control is proposed. First, the adaptive mode switching control leverages the advantages of two DVR compensation methods to reduce the injected voltage amplitude. The mode switching is activated by the DC link voltage and utilizes the PQR transformation to unlock the phase‐locked loop (PLL). Subsequently, an adaptive coordination coefficient is introduced, which considers the margin of ES regulation power and rotor inertia, to maintain power balance during CFRT. This proposed control strategy not only enables wind turbines to seamlessly ride through continuous faults without disconnecting from the grid but also leads to a reduction in the ES compensation requirement. To validate the effectiveness of the proposed approach, simulations based on Simulink and hardware‐in‐loop (HIL) experiments are conducted.

Medium-term wind power prediction based on LSTM classification aided Pelt-Neuralprophet HHO-SVM

The precision of wind power prediction plays a vital role in ensuring the stable operation of wind power systems. To elevate this accuracy and enhance the real-time performance, this paper proposes a hybrid Support Vector Machine (SVM) method, with using the Long Short-Term Memory Network (LSTM) to categorize the wind data based on the statistical features and feedback to the trained SVM model. The hybrid Harris Hawk Optimization (HHO) SVM method adopts the Neuralprophet algorithm to model the seasonality of wind power data and then uses the Pelt technique to the LSTM aided Pelt-Neuralprophet HHO-SVM (i.e., PN-HHO-SVM) scheme, which can utilize the seasonal fluctuations inherent in wind power data. The Neuralprophet algorithm is employed to formulate the seasonal regression model of wind power data. Then, the Pelt technique is used to process the modeled data to locate the change points, so as to classify the time series with similar statistical properties. Furthermore, to tune the SVM hyperparameters for each identified cluster, the HHO algorithm is adopted. Consequently, the LSTM aided PN-HHO-SVM is achieved. The real data sourced from the National Renewable Energy Laboratory (NREL) are used for validation case studies, demonstrating the superiorities of the prediction performance, especially in distinguishing and discriminating the seasonal dynamics of wind power data characters.

An Algorithm for Calculating the Parameter Selection Area of a Doubly-Fed Induction Generator Based on the Guardian Map Method

Large-scale wind farms incorporating doubly-fed induction generators (DFIGs) are considered a promising direction for modern energy supply systems due to their role in reducing dependence on fossil energy sources. However, the dynamic interactions between DFIGs and AC grids sometimes lead to sub-synchronous oscillation (SSO) that threatens the safe and stable operation of wind power systems. Therefore, it is essential to develop a mathematical model and design an algorithm to quantitatively design the control parameters. Such algorithms are helpful in preventing or mitigating system stability problems coming from wind power connected to the grid and reducing damage to power equipment. The traditional state-space model is mainly established to determine the stable operating point and analyze the influence of parameters on the system operating mode. However, this method does not provide the selection area for the system parameters. To address this shortcoming, this paper introduces a modular state-space model for DFIGs containing series compensation lines and proposes an algorithm for calculating the parameter selection area based on the Guardian map method. First, a detailed modular state-space model based on the virtual synchronous generator (VSG) control is established. The modular model helps to reflect the relationship between state variables and focuses on describing the operating state of DFIGs in wind farms. Second, this paper focuses on the influence of VSG control parameters and compensation capacitance on SSO. It aims to clarify the role of the series compensation level and control parameters on SSO based on VSG control. Then, an algorithm for the parameter selection area based on the Guardian map is proposed and the area of the VSG-controlled DFIG is obtained. Finally, the accuracy and validity of the algorithm are verified by time domain simulation in MATLAB/Simulink and HIL experiment.

A short-term wind power prediction approach based on an improved dung beetle optimizer algorithm, variational modal decomposition, and deep learning

Accurate short-term wind power prediction is crucial for the efficient and safe operation of wind power systems. To enhance the accuracy of short-term wind power prediction, this paper proposes a hybrid short-term wind power prediction model, IDBO-VMD-TCN-GRU-Attention, based on the Improved Dung Beetle Optimizer algorithm (IDBO), Variational Modal Decomposition (VMD), Temporal Convolutional Network (TCN), Gated Recurrent Unit (GRU), and Attention Mechanism. The IDBO is used to optimize the parameters of the VMD. Then the optimized IDBO-VMD is used to decompose the original data into modal components with lower volatility to fully extract the data features. These modal components are inputted into the TCN-GRU-Attention to predict the short-term wind power and obtain the final prediction value. The model is tested and validated using real data from four different months and compared against 11 other models. Results demonstrate that our proposed model significantly reduces the Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE) by an average of at least 22.86 %, 18.82 %, and 19.99 %, respectively, across the four different months. This indicates that the proposed model provides a superior fit to the data, offers higher prediction accuracy, and holds significant practical value.

A new methodology to improve wind power prediction accuracy considering power quality disturbance dimension reduction and elimination

The proper integration of wind power-driven grids relies heavily on a reliable balance between electricity production and demand. Therefore, accurate prediction is essential for planning and efficient operation of wind power systems to ensure their continuous supply. However, increasingly severe power quality disturbance (PQD) constantly disturbs this equilibrium, which affects the accuracy of wind power prediction to a large extent. For this purpose, this paper developed a novel optimization methodology to improve wind power prediction accuracy considering micro PQD dimension reduction and elimination for wind-storage integrated systems. A novel idea has been presented in this optimization methodology to eliminate the barrier of PQD and wind power prediction. In the micro aspect, a PQD dimension reduction and elimination strategy based on dynamic mode decomposition (DMD) and Wiener Filter (WF) is proposed to eliminate the autonomy of PQD. This elimination of autonomy allows the WF to get a higher signal-to-noise ratio (SNR). In the macro aspect, this paper takes PQD of different complexity into full consideration, and compares their effects on improving wind power prediction accuracy based on deep learning-based approaches. Through the experimental verification, it is confirmed that the proposed DMD-WF optimization method has demonstrated an effective dimension reduction and elimination of PQD. Moreover, it is found that the proposed PQD optimization method contributes to improve the deep learning-based prediction accuracy when PQD is more complex. The proposed methodology creates a novel perspective to improve the short-term wind power prediction accuracy, which provides a theoretical and methodological guidance for future development of large-scale integrated wind-storage systems.

A novel hybrid model based on GA-VMD, sample entropy reconstruction and BiLSTM for wind speed prediction

Accurate wind speed prediction is of great significance to the stable operation of wind power systems. In this study, a hybrid model integrating variational mode decomposition optimized by genetic algorithm (GA-VMD), sample entropy (SE) and bidirectional long short-term memory (BiLSTM) is proposed for wind speed prediction. Firstly, the original wind speed sequence is decomposed using GA-VMD to obtain modal components with different center frequencies. Secondly, modal components with similar complexity are reconstructed into new components by SE theory to reduce the input complexity. Finally, the forecasting results of each component predicted by BiLSTM are superimposed to get the final prediction results. The proposed method is applied to the Sotavento wind farm dataset and different comparative models are developed for validation. The experimental results show that the RMSE, MAE, MAPE, SMAPE, U1 statistic of the proposed model are 0.1301, 0.0988, 0.2493, 0.1005, and 0.0145 respectively, which are lower than most those of other comparative models, and the R2 value is 0.9954, the highest among all the methods. Therefore, the proposed model has the best prediction results and achieves satisfactory performance.

Optimal maximum power point tracking of wind turbine doubly fed induction generator based on driving training algorithm

The operation of wind power system at optimum power point is a big challenge particularly under uncertainty of wind speed. As a result, it is necessary to install an effective maximum power point tracking (MPPT) controller for extracting the available maximal power from wind energy conversion system (WECS). Therefore, this paper aims to obtain the optimal values of injected rotor phase voltage for doubly fed induction generator (DFIG) to ensure the extraction of peak power from wind turbine under different wind speeds as well as to get the optimal performance of DFIG. A new metaheuristic optimization approach; Driving Training Algorithm (DTA) is used to crop the optimal DFIG rotor voltages. Three different scenarios are presented to have MPPT, the first one is the MPPT with unity stator power factor, the second one is the MPPT with minimum DFIG losses, and the third scenario is MPPT with minimum rotor current to reduce the rating of rotor inverter. The MATLAB environment is used to simulate and study the proposed controller with 2.4 MW wind turbine. The optimum power curve of wind turbine has been estimated to get the reference values of DFIG mechanical power. The results ensured the significance and robust of the proposed controller to have MPPT under different wind speeds. The DTA results are compared with other two well-known optimization algorithms; water cycle algorithm (WCA) and particle swarm optimizer (PSO) to verify the accuracy of results.

Operation state assessment of wind power system based on PSO + AHP—FCE

Aiming at the shortcomings of the analytic hierarchy process in the comprehensive evaluation of wind power system operation status with strong subjectivity in determining weights, this thesis proposes an analytic hierarchy process (AHP) based on particle swarm optimization (PSO) and constructs an analytic hierarchy process combined with a particle swarm optimization algorithm (PSO + AHP) model to optimize the weights. It overcomes the disadvantage that once given the judgment matrix in the AHP method, the weight values and consistency cannot be improved. In this article, the comparison chart of the consistency indexes calculated according to this method shows that the one-time indexes of Ca as well as C1−C7 are reduced to different degrees, so a weight value with a relatively high degree of consistency can be obtained by this method. Second, for the situation that there are several judgment indexes in the sub-project layer that deviate seriously at the same time, introduce the degradation index, and apply the fuzzy comprehensive judgment method to establish the model of wind power system operation status assessment. Finally, based on the actual monitoring data of a wind farm over a period of time, its operational status was evaluated using the proposed PSO-AHP model based on FCE, and a score that can indicate the operational status can be obtained by calculation. In this article, the evaluation score of a wind farm is 0.556, indicating that the staff needs to carry out maintenance at this time. The comparative analysis shows that compared to the traditional AHP-FCE evaluation method, the assessment results proposed in this article are relatively good and have practical value and significance for improving the real-time reliability of grid-connected operation of wind turbines, optimizing the maintenance strategy of wind turbines, and reducing the cost of wind power generation.

Short-term wind speed forecasting based on spatial-temporal graph transformer networks

Wind energy is a widely concerned renewable energy source. Accurate short-term wind speed forecasting is helpful for the stable operation of wind power systems, which is crucial to the wind power industry. In this paper, a Spatial-Temporal Graph Transformer Network (STGTN) is proposed to improve the performance of short-term wind speed forecasting. The proposed model consists of a temporal feature extraction module and a spatial feature extraction module and thus it can capture the temporal and spatial correlations between wind turbine nodes. A transformer based on the external attention mechanism and the graph convolutional layer is proposed to extract spatial features while a multilayer perceptron is employed to derive temporal features. Since the graph convolutional layer relies on the Euclidean spatial topology input, the location distribution of wind turbine nodes is not considered in the proposed model. To verify the performance of the STGTN model, five wind speed forecasting methods (with and without spatial dependencies) are employed as benchmarks. Experimental results show that the proposed model performs the best in terms of the mean absolute error, root mean square error and mean absolute percentage error for each forecasting horizon.

Short-term wind speed forecasting using deep reinforcement learning with improved multiple error correction approach

The safe and stable operation of wind power systems requires the support of wind speed prediction. To ensure the controllability and stability of smart grid dispatching, a novel hybrid model consisting of data-adaptive decomposition, reinforcement learning ensemble, and improved error correction is established for short-term wind speed forecasting. In decomposition module, empirical wavelet transform algorithm is used to adaptively disassemble and reconstruct the wind speed series. In ensemble module, Q-learning is utilized to integrate gated recurrent unit, bidirectional long short-term memory, and deep belief network. In error correction module, wavelet packet decomposition and outlier-robust extreme learning machine are combined to developing predictable components. An appropriate correction shrinkage rate is used to obtain the best correction effect. Ljung-Box Q-Test is utilized to judge the termination of the error correction iteration. Four real data are utilized to validate model performance in the case study. Experimental results show that: (a) The proposed hybrid model can accurately capture the changes of wind data. Taking 1-step prediction results as an example, the mean absolute errors for site #1, #2, #3, and #4 are 0.0829 m/s, 0.0661 m/s, 0.0906 m/s, and 0.0803 m/s, respectively; (b) Compared with several state-of-the-art models, the proposed model has the best prediction performance.

Design of a combined system based on two-stage data preprocessing and multi-objective optimization for wind speed prediction

Reliable wind speed forecasting is crucial for the operation of wind power systems, and many efforts have been made to develop methods for wind speed prediction. However, most of them ignored feature extraction from original data, leading to poor performance. In this study, a novel combined forecasting system is proposed based on a two-stage data preprocessing technique, three component forecasting models and a novel combination method of a multi-objective optimization algorithm to compensate for their shortcomings. Through the two-stage data preprocessing, the raw data is decomposed and reshaped to reduce noisy and chaotic disturbance, which improves the quality of data input. The forecasting module uses component forecasting and a combination strategy that takes advantages of each model to achieve both accurate and stable results. Four 10-min wind speed datasets are employed for experiments, and the results of deterministic and probabilistic forecasting indicate that the proposed system achieves optimal accuracy and robustness comparing with contrastive models. For point and interval forecasting, the system achieves 3.1112%, 4.7375%, 2.7459%, and 2.1110% mean absolute percent errors and 96.6667%, 100%, 97.3333%, and 98% interval coverage probabilities for spring, summer, autumn and winter dataset, respectively, connoting a considerable potential for application in wind power production.

Probabilistic model of wind power output considering temporal autocorrelation and cross-correlation with forecast output

Wind power output possesses temporal autocorrelation and cross-correlation with the forecast output. However, these two types of correlations are quite different. Existing studies fail to model them simultaneously, which reduces the accuracy of the conditional probability distribution of wind power output and has a negative effect on the economic operation of wind power systems. Therefore, this paper proposes a method for modeling the conditional probability distribution of wind power output that can take both correlations into account. The copula function is used to separately model the dependency between wind power outputs and the uncertainty of actual/forecast output. Based on pair-copula theory, the modeling of the conditional probability distribution of wind power output with respect to the two correlations is broken down into the chain transfer process of the traditional two-dimensional copula function. The probability distribution function of wind power output can be obtained as long as enough historical data is available. No specific forecast techniques are required. Using the actual wind field output data in Belgium, the proposed method is compared with the methods that only consider one of the correlations to prove its effectiveness.

Power and Current Limiting Control of Wind Turbines Based on PMSG Under Unbalanced Grid Voltage

Unbalanced grid voltage sags are the severe challenge for wind power generation system which connected to the grid successfully. The dc bus voltage and output power will fluctuate under unbalanced grid voltage. Moreover, the voltage sags will lead to the increase of peak current, which will bring potential safety hazards to the operation of wind power system. This paper proposes a simple current limiting control scheme without auxiliary equipment, which based on the detailed analysis of the excessive peak current. In this scheme, the machine side converter (MSC) controller adjusts the electromagnetic power according to the power transmitted to the grid by the grid side converter (GSC). Meanwhile, it converts the unbalanced power on the dc-link into the rotor kinetic energy, avoiding the dc-link overvoltage. The GSC controller can not only ensure that the three-phase inverter currents are in the maximum safe range that the converters can bear, but also provide reactive power support for the grid. Furthermore, the fluctuations on dc bus voltage and output power can be eliminated effectively by using the GSC controller. The feasibility of the proposed scheme and the superiority over the traditional control schemes have been verified by simulations under different types of unbalanced voltage.

Wind speed forecasting using a new multi-factor fusion and multi-resolution ensemble model with real-time decomposition and adaptive error correction

The chaos and non-stability of the wind pose challenges for obtaining reliable wind speed forecasting. Accurate and reliable wind speed forecasting is critical to the efficient and safe operation of wind power systems. In the study, a new hybrid multi-factor fusion and multi-resolution ensemble model is proposed for forecasting wind speed. The proposed hybrid forecasting model adopts real-time data decomposition and adaptive multiple error correction strategies and it consists of three phases. In stage I, the low-resolution and high-resolution data obtained by the averaging method and the Staked Auto-Encoder (SAE) feature extraction method, respectively. The data are used by Bidirectional Long Short-Term Memory (BiLSTM) for multi-step forecasting. The forecasting results are reasonably ensemble by Non-dominated Sorting Genetic Algorithm III (NSGA-III) to complete the multi-resolution ensemble phase. In stage II, Ljung-Box Q-Test (LBQ-test) is utilized to detect predictable components in the forecasting results. And Auto-Regression Moving Averaging (ARMA) completes adaptive multiple error corrections. In stage III, Multi-universe Optimization (MVO) is used to ensemble the wind speed forecasting results of multiple positions. At this point, the multi-position data fusion phase is completed. Wind speed data from Xinjiang, China are carried out to validate the efficiency of the proposed model. Experimental analysis shows: The performance of the proposed hybrid model is superior to other comparative models. The MAE error of 3-step wind speed forecasting from the four sets of experiments is only 0.4614 m/s, 0.4482 m/s, 0.6755 m/s, and 0.2912 m/s, respectively.

Research on Modeling of Wind-solar Hybrid Microgrid and Control Strategy of Maximum Power Load

As an important form of receiving renewable energy, microgrids can be a useful supplement to large grids, which can solve the power supply problem of residents in remote mountainous areas, pastoral areas, and islands. Modeling and simulation of energy management for microgrid operation characteristics with wind and solar storage have important practical significance. In this paper, mathematical models of photovoltaic cells and wind power systems are established, simulation models are constructed, and their respective characteristics are simulated and analyzed to verify the correctness of the mathematical models. A simulation model of maximum power point tracking for wind and solar power systems was established based on the respective shortcomings and limitations of independent operation of wind power systems and photovoltaic systems. According to the simulation results, it can be seen that the maximum power control technology used in this system can achieve maximum power tracking for wind power generation systems and photovoltaic power generation systems. The simulation results verify the correctness of the system and the feasibility of the control strategy.

Hardware-in-the-Loop and Field Validation of a Rotor-Side Subsynchronous Damping Controller for a Series Compensated DFIG System

In the past decade, several subsynchronous control interaction (SSCI) incidents have been reported in various large-scale grid-interfaced doubly-fed induction generator (DFIG) based wind farms. The subsynchronous oscillation caused by the SSCI endangers the safe and reliable operation of wind power systems. The DFIG's converter controls play a crucial role in such interactions; therefore, several SSCI mitigation schemes have been reported, which modify the DFIG's converter controls to stabilize the subsynchronous oscillation caused by the SSCI. However, the effectiveness of such converter control modifications has not been verified through laboratory or field experiments. This paper considers a practical rotor-side subsynchronous damping controller (RSDC) and fills the gap by first validating the RSDC's performance through controller hardware-in-the-loop (CHIL) simulations, and then implementing it in a real-world DFIG connected to a series compensated line. The RSDC fundamentally reshapes the effective impedance of the DFIG to stabilize the subsynchronous oscillation. The CHIL simulations, as well as the field tests, successfully validated the RSDC's ability to suppress the SSCI. The results enhanced the practical confidence of the SSCI mitigation strategy based on RSC's converter control modification.

Finite-time function projective synchronization control method for chaotic wind power systems

Wind power is a rapidly growing renewable energy source that plays an increasingly important role in power systems. However, its dynamic behaviors are complex because of the instability of wind speed, strong coupling, highly nonlinear subsystems, and mass grid connections. Chaotic oscillation is one of the most typical complex dynamic behaviors of wind power systems. This behavior can seriously influence the stable operation of wind power systems and cause great harm. This study proposed a control method for finite-time function projective synchronization on the basis of the chaos synchronization principle and finite-time theory for wind power systems. Wind power systems with or without uncertain parameters were considered. First, we built a high-dimensional wind power system and analyzed its chaotic behaviors. Lyapunov exponents were derived to prove the existence of chaos and bifurcation. Second, we aimed to increase the robustness of the controller by adding parameter observers to the controller. The result helped solve the problem of unknown parameters. If a wind power system comprises unknown parameters, the unknown parameters can be defined as the system's states. An unknown parameter observer was designed to realize the identification of unknown parameters. Third, we proposed a control method for finite-time function projective synchronization. Finite-time stability theory and function projective synchronization theory were used to construct the controller. These theories can ensure the quick synchronization of a chaotic wind power system with a stable wind power system in finite time. Finally, the mathematical proof of the stability theorem was derived, and a corresponding numerical simulation was performed to validate the chaos control method for wind power systems.

Optimal and stable energetic operation of wind power systems at variable wind speed

In the present paper we analyse the stable and optimal operation of wind power systems, WPS, composed of wind turbines, TV, coupled with synchronous generators with permanent magnets (SGPM), high power SGPM in the Dobrogea area, 4MW turbines manufactured at General Electric. Based on the experimental data, the wind turbine models MM-WT and the MM-SGPM permanent magnet synchronous generator are determined. Using these mathematical models, simulations are made of rapid variations in wind speed over time and the conditions for stable and energy-efficient EEA operation are highlighted. It mainly analyses the evolutions in time of power and speed from the generator, in direct connection with the change in wind speed over time. At the end of the paper is given a power calculation algorithm at SGPM, based on wind velocity measurements and VUM, ω, so that the operation is stable and energy optimal.

Forecasting Wind Speed using Artificial Neural Networks – A Case Study of a Potential Location of Saudi Arabia

The growing concerns regarding the depletion of oil/gas reserves and global warming have made it inevitable to seek energy from wind and other renewable energy resources. Forecasting wind speed is a challenging topic and has important applications in the design and operation of wind power systems, particularly grid connected renewable energy systems, and where forecasting wind speed helps in manipulating the load on the grid. Modern machine learning techniques including neural networks have been widely used for this purpose. As per literature, various models for estimating the hourly wind speed one hour ahead and the hourly wind speed data profile one day ahead have been developed. This paper proposes the use of Artificial Intelligence methods (AI) which are most suitable for the prediction and have provided best results in many situations. AI method involves nonlinear (or linear) and highly complex statistical relationships between input and output data, such as neural networks, fuzzy logic methods, Knearest Neighbors algorithm (KNN) and Support Vector Machine (SVM). AI methods are promising alternatives for predicting wind speed and understanding the wind behavior for a particular region. In the present study (as a case-study), hourly average wind speed data of 13 years (1970-1982) of Qaisumah, Saudi Arabia has been used to evaluate the performance of ANN model. This data has been used for training the neural network. ANN is trained multiple times with different number of hidden neurons to forecast accurate wind speed. The efficiency of proposed model is validated by predicting wind speed of the Qaisumah region with the measured data. Mean Square Error (MSE) and mean absolute percentage error (MAPE values) for proposed model are found to be 0.0912 and 6.65% respectively.

Implementation of module-based wind power system with pitch angle control

AbstractThis paper presents a module approach for lab-scale wind power systems (WPS). The system is designed into functional modules. These modules can be used independently or in other projects. It is also convenient to handle and set up them on a small table in classrooms and labs. Hence, they are very useful for training and research. In addition, operation on both aerodynamic side and generator side is developed in this research. Many papers on wind system simulators focus only on aerodynamic system with pitch angle control or generator system with optimal control. Thus, the operation of WPS in 2 regions, which requires coordination of aerodynamic and generator sides, is not explained and demonstrated in previous study. Many case studies are conducted to demonstrate the capability of the module-based WPS. The system is capable of speed control, optimal power control and pitch angle control. As illustrated in experimental results, these control strategies can efficiently cooperate under operation in 2 ...