Wind Farm Cluster Research Articles

Power prediction of a wind farm cluster based on spatiotemporal correlations

Accurate power prediction of wind farm clusters is important for safe and economic operation of power systems with high wind power penetration. Current superposition and statistical scaling methods used in wind power prediction systems do not fully consider the relationships among wind farms in a cluster, thereby leading to insufficient power prediction accuracies. To improve the power prediction accuracy of wind farm clusters, a new method based on spatiotemporal correlations is proposed herein. First, three correlation coefficients are used to represent spatiotemporal correlation characteristics of wind farms in a wind cluster. The Shapley value method is used to weight these coefficients, and a standard wind farm is found by combining the nominal capacities of the wind farms. Then, considering the spatiotemporal factors that affect wind power generation, a characteristic matrix of the wind farm cluster is constructed, and the key characteristics are extracted using a convolutional neural network (CNN). Considering the time series characteristics of wind power generation, a long and short term memory (LSTM) neural network is used to establish the mapping relationship between key characteristics and power generation, and power prediction of a wind farm cluster is performed. Finally, by utilizing the actual operating data of wind farm clusters in North China as an example, feasibility and effectiveness of the proposed method are verified. The proposed system provides a new high-precision method for future wind farm cluster power predictions.

Study on harmonic interaction between paralleled STATCOMs with cascaded H‐bridge topology in wind farm clusters

Study on harmonic interaction between paralleled STATCOMs with cascaded H‐bridge topology in wind farm clusters

Short-Term Wind Power Prediction for Wind Farm Clusters Based on SFFS Feature Selection and BLSTM Deep Learning

Wind power prediction (WPP) of wind farm clusters is important to the safe operation and economic dispatch of the power system, but it faces two challenges: (1) The dimensions of the input parameters for WPP of wind farm clusters are very high so that the input parameters contain irrelevant or redundant features; (2) it is difficult to build a holistic WPP model with high-dimensional input parameters for wind farm clusters. To overcome these challenges, a novel short-term WPP model for wind farm clusters, based on sequential floating forward selection (SFFS) feature selection and bidirectional long short-term memory (BLSTM) deep learning, is proposed in this paper. First, more than 300,000 input features of the wind farm cluster are constructed. Second, the SFFS method is applied to sort the high-dimensional features and analyze the rule that the forecasting accuracy changes with the number of features to obtain the optimal number of features and feature sets. Finally, based on the results of feature selection, BLSTM is applied to build a WPP model for wind farm clusters with a combination of feature selection and deep learning. This case study shows that (1) SFFS is an effective method for selecting the core features for WPP of wind farm clusters; (2) BLSTM shows not only higher WPP accuracy than long short-term memory and backpropagation neural network but also outstanding performance in terms of reducing the phase errors of WPP.

Adaptive Extended Kalman Filter Based Dynamic Equivalent Method of PMSG Wind Farm Cluster

In order to reduce the dimension of wind farm model and improve the simulation efficiency under the premise of ensuring the accuracy, this article proposes a dynamic equivalent method for permanent magnet synchronous generator (PMSG) based wind farm cluster utilizing the adaptive extended Kalman filters. Combining the dynamic model of PMSG, the equivalent wind turbine parameters that need to be identified are incorporated into the extended state variables, and an online parameters identification method based on extended Kalman filter (EKF) theory is put forward. To eliminate the influence of random noise on the accuracy of identification, the adaptive technology is introduced into EKF to estimate the process and measurement noise covariance in real time through the Sage–Husa estimator. Thus, a wind farm cluster equivalent model is obtained. Finally, the effectiveness and robustness of the proposed method are verified by time-domain simulation and frequency-domain simulation in IEEE 39-bus system.

Research on voltage control strategy optimization of wind farm cluster

With the continuous expansion of the grid-connected scale of wind farms, the problem of the stability of the grid-connected point voltage of wind farm cluster has become increasingly prominent. However, the current reactive voltage control strategy of wind farm cluster has less research on the optimization of the internal node voltage and grid loss of wind farms, and the problem of the reduction of wind turbine life caused by the full reactive power of doubly-fed wind turbines needs further research. In view of the above problems, this paper proposes a wind farm cluster reactive voltage hierarchical control strategy based on the reactive power margin of doubly-fed wind turbines. The strategy improves the traditional artificial fish algorithm and realizes the reactive voltage control of wind farm cluster. As a result, the node and network loss have reached a certain degree of optimization.

M2GSNet: Multi-Modal Multi-Task Graph Spatiotemporal Network for Ultra-Short-Term Wind Farm Cluster Power Prediction

Ultra-short-term wind power prediction is of great importance for the integration of renewable energy. It is the foundation of probabilistic prediction and even a slight increase in the prediction accuracy can exert significant improvement for the safe and economic operation of power systems. However, due to the complex spatiotemporal relationship and the intrinsic characteristic of nonlinear, randomness and intermittence, the prediction of regional wind farm clusters and each wind farm’s power is still a challenge. In this paper, a framework based on graph neural network and numerical weather prediction (NWP) is proposed for the ultra-short-term wind power prediction. First, the adjacent matrix of wind farms, which are regarded as the vertexes of a graph, is defined based on geographical distance. Second, two graph neural networks are designed to extract the spatiotemporal feature of historical wind power and NWP information separately. Then, these features are fused based on multi-modal learning. Third, to enhance the efficiency of prediction method, a multi-task learning method is adopted to extract the common feature of the regional wind farm cluster and it can output the prediction of each wind farm at the same time. The cases of a wind farm cluster located in Northeast China verified that the accuracy of a regional wind farm cluster power prediction is improved, and the time consumption increases slowly when the number of wind farms grows. The results indicate that this method has great potential to be used in large-scale wind farm clusters.

A Model for the Spectrum of the Lateral Velocity Component from Mesoscale to Microscale and Its Application to Wind-Direction Variation

A model for the spectrum of the lateral velocity component $$S_v(f)$$ is developed for a frequency range from about 0.2 $$\hbox {day}^{-1}$$ to the turbulence inertial subrange, with the intent of improving the calculation of flow meandering over areas the size of offshore wind farms and clusters. These sizes can correspond to a temporal scale of several hours, much larger than the validity limit of typical boundary-layer models, such as the Kaimal model, or the Mikkelsen–Tchen model. The development of the model is based on observations from one site and verified with observations from another site up to a height of 241 m. The model describes three ranges: (1) the mesoscale from $$0.2\ \hbox {day}^{-1}$$ to about $$10^{-3}\ \hbox {Hz}$$ where a mesoscale spectral model from Larsen et al. (2013: QJR Meteorol Soc 139: 685–700) is used; (2) the spectral gap where the normalized v spectrum, $$fS_v(f)$$ , can be approximated to be a constant; (3) the high-frequency range where a boundary-layer model is used. In order to demonstrate a general applicability of the lateral velocity spectrum model to reproduce the statistics of wind-direction variability, models for both horizontal velocity components, u and v, are used through an inverse Fourier transform technique to produce time series of both components, which in theory could have been the ensemble for calculating the corresponding spectra. The ensemble is then used to calculate directional statistics, which in turn are compared with corresponding statistics from the measured time series. We demonstrate the relevance of the constructed spectral models for calculating meandering effects for large wind farms and wind-farm clusters.

Wind Power Prediction for Wind Farm Clusters Based on the Multifeature Similarity Matching Method

Regional wind power prediction (WPP) is conducive to achieving scientific dispatch of the power system as well as improving its reliability. Data mining based on a large number of samples is an effective way to improve the accuracy of WPP. A new regional power forecasting method in the context of data mining is proposed in the article. First, a previously described regional WPP method, single feature similarity matching (SFSM) method, is analyzed and a new multifeature similarity matching (MFSM) method is proposed. Second, the optimization and analysis processes of four key parameters in the MFSM method are proposed and the impact of each key parameter on prediction error and the applicability of the method under different regional scales is analyzed. Finally, the new method and the optimization and analysis processes are verified by wind farm clusters, composed of 52 wind farms in northeast China, and the new method is compared with the conventional method, such as additive method, statistical up-scaling method, and the SFSM method. The results show that the improved MFSM method is superior to the conventional prediction method, whereby the root mean square error (RMSE) of 0 to 2 h is reduced by 3.65% and the RMSE of 0 to 4 h is reduced by 1.56%. The new method has been proved to be an effective WPP method for wind farm clusters and has potential industrial application prospects.

Development of Wind Energy in India and a Stratagem for Analyzing Performance of Wind Farm Clusters

Development of Wind Energy in India and a Stratagem for Analyzing Performance of Wind Farm Clusters

Two‐tier combined active and reactive power controls for VSC–HVDC‐connected large‐scale wind farm cluster based on ADMM

To reduce the voltage fluctuations inside the wind farm cluster (WFC), a combined active and reactive power control schemes based on model predictive control is proposed. The aims of the proposed control scheme are to maintain the collector bus and wind turbine (WT) terminal voltages within the feasible range. With the size of WFC increasing, conventional centralised optimal control may no longer be suitable for a large-scale WFC due to the high computation burden of the WFC central controller. To improve the calculation efficiency and protect information privacy, a two-tier control structure with alternating direction method of multipliers (ADMMs) algorithm is used to solve the large-scale optimisation problem in distributed/hierarchical manner. In the upper-tier distributed control, the active and reactive power outputs of the WFs are coordinated to enhance the voltage control performance. In the lower-tier control, an ADMM-based hierarchical control is developed to minimise the voltage deviation of the WT terminals. Case studies demonstrate the efficacy of the proposed two-tier combined active and reactive power controls.

Offshore wind farm wake recovery: Airborne measurements and its representation in engineering models

AbstractWe present an analysis of wind measurements from a series of airborne campaigns conducted to sample the wakes from two North Sea wind farm clusters, with the aim of determining the dependence of the downstream wind speed recovery on the atmospheric stability. The consequences of the stability dependence of wake length on the expected annual energy yield of wind farms in the North Sea are assessed by an engineering model. Wakes are found to extend for significantly longer downstream distances (>50 km) in stable conditions than in neutral and unstable conditions ( 15 km). The parameters of one common engineering model are modified to reproduce the observed wake decay at downstream distances 30 km. More significant effects on the energy yield are expected for wind farms separated by distances 30 km, which is generally the case in the North Sea, but additional data would be required to validate the suggested parameter modifications within the engineering model. A case study is accordingly performed to show reductions in the farm efficiency downstream of a wind farm. These results emphasize not only the importance of understanding the impact of atmospheric stability on offshore wind farms but also the need to update the representation of wakes in current industry models to properly include wake‐induced energy losses, especially in large offshore clusters.

Improved Deep Mixture Density Network for Regional Wind Power Probabilistic Forecasting

Unsteady motion of the atmosphere incurs nonlinear and spatiotemporally coupled uncertainties in the wind power prediction (WPP) of multiple wind farms. This brings both opportunities and challenges to wind power probabilistic forecasting (WPPF) of a wind farm cluster or region, particularly when wind power is highly penetrated within the power system. This paper proposes an Improved Deep Mixture Density Network (IDMDN) for short-term WPPF of multiple wind farms and the entire region. In this respect, a deep multi-to-multi (m2m) mapping Neural Network model, which adopts the beta kernel as the mixture component to avoid the density leakage problem, is established to produce probabilistic forecasts in an end-to-end manner. A novel modified activation function and several general training procedures are then introduced to overcome the unstable behavior and NaN (Not a Number) loss issues of the beta kernel function. Verification of IDMDN is based on an open-source dataset collected from seven wind farms, and comparison results show that the proposed model improves the WPPF performance at both wind farm and regional levels. Furthermore, a laconic and accurate probabilistic expression of predicted power at each time step is produced by the proposed model.

Cluster wakes impact on a far-distant offshore wind farm's power

Abstract. Our aim with this paper was the analysis of the influence of offshore cluster wakes on the power of a far-distant wind farm. We measured cluster wakes with long-range Doppler light detection and ranging (lidar) and satellite synthetic aperture radar (SAR) in different atmospheric stabilities and analysed their impact on the 400 MW offshore wind farm Global Tech I in the German North Sea using supervisory control and data acquisition (SCADA) power data. Our results showed clear wind speed deficits that can be related to the wakes of wind farm clusters up to 55 km upstream in stable and weakly unstable stratified boundary layers resulting in a clear reduction in power production. We discussed the influence of cluster wakes on the power production of a far-distant wind farm, cluster wake characteristics and methods for cluster wake monitoring. In conclusion, we proved the existence of wake shadowing effects with resulting power losses up to 55 km downstream and encouraged further investigations on far-reaching wake shadowing effects for optimized areal planning and reduced uncertainties in offshore wind power resource assessment.

Distributed Optimal Voltage Control for VSC-HVDC Connected Large-Scale Wind Farm Cluster Based on Analytical Target Cascading Method

This article proposes an analytical target cascading (ATC) based distributed optimal voltage control (DOVC) scheme for the voltage-source-converter high-voltage-direct-current (VSC-HVDC) connected large-scale wind farm cluster (WFC). The aims are to minimize the voltage fluctuations of the point of connection (POC), collector buses, and wind turbine (WT) terminal buses inside the WFC while regulating the bus voltages close to the rated voltage and smooth the reactive power outputs of the WTs. With the DOVC scheme, the large-scale strongly coupled sensitivity-based voltage optimization problem is decomposed and solved in the WFC voltage-source-converter (WFCVSC) controller and sub-wind farm controllers in parallel. The DOVC scheme considers the $N-1$ principle to improve the reliability, and distributes computation burden to several controllers to achieve better scalability of the WFC. The optimization subproblems are solved with local constraints and local measurements while guaranteeing the optimality of the primal optimization problem. A WFC with 5 wind farms and each wind farm consisting of 20 WTs is used to validate the proposed DOVC scheme.

An improved coordination method of multi-terminal MMC-HVDC system suitable for wind farm clusters integration

With the continuous expansion of wind farm clusters, the multi-terminal modular multilevel converter based high voltage direct current (MMC-HVDC) transmission has been employed for wind power delivery. To improve the control flexibility, dynamic voltage adjustment speed and rationality of power allocation, various coordination control methods have been recently investigated in multi-terminal MMC-HVDC transmission system. An attempt is made in this paper to contribute to the optimization of coordination control in the multi-terminal MMC-HVDC system connected to wind farms. Based on the analysis of DC voltage, power deviation and droop coefficient, an improved droop control strategy with adjustable coefficients is first proposed and thereby applied to multi-terminal MMC-HVDC transmission system with wind farm clusters. Arguably, the droop coefficient correction should be an effective method for optimizing power allocation and reducing DC voltage deviation between the receiving converters. In addition, a lag compensator is introduced to improve the response speed of the inner loop controller when the improved droop control is adopted. Furthermore, the influence of droop coefficients on the stability of the control system is discussed, and the dynamic response of the improved control system is also analyzed under the different droop and time coefficients, which can provide guidelines for the control optimization of multi-terminal MMC-HVDC system. Finally, a model of a five-terminal MMC-HVDC transmission system is built based on the RT-LAB simulator, and the simulation results show that the proposed method can not only optimize the voltage control and power allocation, but also improve the system response speed.

Development of a High-Resolution Wind Forecast System Based on the WRF Model and a Hybrid Kalman-Bayesian Filter

Regional microscale meteorological models have become a critical tool for wind farm production forecasting due to their capacity for resolving local flow dynamics. The high demand for reliable forecasting tools in the energy industry is the motivation for the development of an integrated system that combines the Weather Research and Forecasting (WRF) atmospheric model with an optimization obtained by the conjunction of a Kalman filter and a Bayesian model. This study focuses on the development and validation of this combined system in a very dense wind farm cluster located in Galicia (Northwest of Spain). A period of one year is simulated at 333 m horizontal resolution, with a daily operational forecasting set-up. The Kalman-Bayesian filter was tested both directly on wind speed and on the U-V (zonal and meridional) components for nowcasting periods from 10 min to 6 h periods, all of them with important applications in the wind industry. The results are quite promising, as the main statistical error indices are significantly improved in a 6 h forecasting horizon and even more in shorter horizon cases. The Mean Annual Error (MAE) for 1 h nowcasting horizon is 1.03 m/s for wind speed and 12.16 ° for wind direction. Moreover, the successful utilization of the integrated system in test cases with different characteristics demonstrates the potential utility that this tool may have for a variety of applications in wind farm operations and energy markets.

Investigating the Wind Power Smoothing Effect Using Set Pair Analysis

This study explores the smoothing effect on the uncertainty of the wind power fluctuations that affect a power system at points of common coupling. Set pair analysis is applied to evaluate the similarity between the power fluctuations of a single wind turbine and those of all aggregated wind turbines, based on which a quantitative index describing the wind power smoothing effect is proposed. The smoothing effect characteristics of a wind farm cluster are investigated for different numbers of wind turbines, different wind speeds, different seasons, and multiple sampling intervals. A significant smoothing effect is usually observed at a shorter sampling interval and a higher wind speed, and the smoothing effect index increases with an increase in the numbers of wind turbines and farms. Additionally, the correlation between the smoothing effect of aggregated wind farms and the forecast accuracy for the corresponding aggregated power output is examined. The experimental results indicate that the wind power forecast accuracy varies with the smoothing effect index, which is influenced by the number of wind farms. Furthermore, the aggregated output from a wind farm cluster with a higher smoothing effect index exhibits better forecasting performance than that from a single wind farm, showing that the trend of the wind power series becomes smoother due to the smoothing effect, thus enabling one-step-ahead wind power forecasting with higher accuracy.

Bi-level decentralized active and reactive power control for large-scale wind farm cluster

This paper proposes a bi-level decentralized active and reactive power control (DARPC) for the large-scale wind farm cluster (WFC) composed of several wind farms. The WFC tracks the active power reference from the transmission system operator (TSO) while controlling the bus voltage of the point of connection (POC), and maintaining the wind turbine (WT) terminal voltages stable in each wind farm. In the upper level, a distributed active and reactive power control scheme based on the consensus protocol is designed for the WFC, which can achieve fair active and reactive power sharing among multiple wind farms, and generates active and reactive power references for each wind farm. In the lower level, a centralized control scheme based on Model Predictive Control (MPC) is proposed, which can effectively regulates active and reactive power outputs of all WTs within the wind farm. The proposed centralized control scheme can maintain WTs terminal voltage close to the rated voltage while tracking the power reference from the upper level control. The DARPC can effectively reduce the computation burden of the WFC controller by distributing the computation and monitoring tasks to several wind farm controllers. Moreover, the communication cost is reduced. A WFC with 8 wind farms and totally 128 WTs was used to validate the proposed DARPC scheme.

Distributed Voltage Control Based on ADMM for Large-Scale Wind Farm Cluster Connected to VSC-HVDC

A distributed voltage control (DVC) scheme based on the alternating direction method of multipliers (ADMM) is proposed for the large-scale wind farm cluster (WFC) connected to a voltage source converter-high voltage direct current system. The proposed scheme coordinates the reactive power output among several wind farms, and wind turbines (WTs) within each wind farm. This keeps the collector bus voltage of each wind farm and WT terminal voltages within the feasible range, and minimizes active power losses. First, a distributed reactive power control scheme based on the consensus ADMM is designed for the WFC, which can achieve fair reactive power sharing among wind farms with the optimal reactive power utilization ratio, to regulate the collector bus voltage close to the rated voltage. Second, a decentralized reactive power control scheme based on the standard ADMM is designed for each wind farm, which can effectively regulate reactive power outputs of all WTs within the wind farm. The ADMM algorithm is used to reduce the calculation burden of the wind farm controller. Moreover, the proposed decentralized control scheme coordinates the voltage regulation and economical operation. The DVC is able to effectively reduce the computation burden of the WFC and wind farm controllers, and the communication cost is reduced. A WFC with eight wind farms was used to validate the proposed DVC scheme.

Calculating Wind Variability Costs with Considering Ramping Costs of Conventional Power Plants

Due to the variability of the wind power, conventional power plants are required to ramp more frequently to mitigate the imbalance of generation and supply, which increase the total cost of power systems. The increase of the cost is termed the “variability cost” of wind power. Generally, it includes the additional ramping cost, reserve cost and fuel cost of conventional plants. In this paper, we propose an alternative scenario construction method to calculate the “variability cost” of wind power from the viewpoint of the power system schedule. Firstly, in the alternative scenario, a new energy proxy with zero wind variability costs is constructed. Then, a unit commitment optimization model considering ramping costs is developed. The operation costs of power systems under two scenarios (alternative one and real one) are calculated and the difference between two costs is the variability cost. Furthermore, we apply the proposed method to calculate the variability costs of the wind farm cluster. The simulations show that the variability cost increases with higher penetration and higher variability of wind power. Meanwhile, it is found that the variability cost of the wind farm cluster as a whole is lower than the sum of variability costs of each wind farm.