Multivariable control strategy for variable speed, variable pitch wind turbines

Reliable and powerful control strategies are needed for wind energy conversion systems to achieve maximum performance. A new control strategy for a variable speed, variable pitch wind turbine is proposed in this paper for the above-rated power operating condition. This multivariable control strategy is realized by combining a nonlinear dynamic state feedback torque control strategy with a linear control strategy for blade pitch angle. A comparison with existing strategies, PID and LQG controllers, is performed. The proposed approach results in better power regulation. The new control strategy has been validated using an aeroelastic wind turbine simulator developed by NREL for a high turbulence wind condition.     

Effect of direction on wind speed estimation in complex terrain using neural networks

A method of estimating the annual average wind speed at a selected site using neural networks is presented. The method proposed uses only a few measurements taken at the selected site in a short time period and data collected at nearby fixed stations.The neural network used in this study is a multilayer perceptron with one hidden layer of 15 neurons, trained by the Bayesian regularization algorithm. The number of inputs that must be used in the neural network was analyzed in detail, and results suggest that only wind speed and direction data for a single station are required. In sites of complex terrain, direction is a very important input that can cause a decrease of 23% in root mean square (RMS).The results obtained by simulating the annual average wind speed at the selected site based on data from nearby stations are satisfactory, with errors below 2%.     

Research on wind turbine rotor models using NACA profiles

In this study, rotation rates and power coefficients of miniature wind turbine rotor models manufactured using NACA profiles were investigated. For this purpose, miniature rotor models with 310 mm diameter were made from “Balsa” wood. When all properties of rotor models were taken into account, a total of 180 various combinations were obtained. Each combination was coded with rotor form code. These model rotors were tested in a wind tunnel measurement system. Rotation rates for each rotor form were determined based on wind speed. Power coefficient values were calculated using power and tip speed rates of wind. Rotor models produced a rotation rate up to 3077 rpm, with a power coefficient rate up to 0.425. Rotor models manufactured by using NACA 4412 profiles with 0 grade twisting angle, 5 grade blade angle, double blades had the highest rotation rate, while those manufactured by using NACA 4415 profiles with 0 grade twisting angle, 18 grade blade angle, 4 blades had the highest power coefficient.     

A classification mechanism for determining average wind speed and power in several regions of Turkey using artificial neural networks

In this paper, average wind speed and wind power values are estimated using artificial neural networks (ANNs) in seven regions of Turkey. To start with, a network has been set up, and trained with the data set obtained from several stations—each station gather data from five different heights—from each region, one randomly selected height value of a station has been used as test data. Wind data readings corresponding to the last 50 years of relevant regions were obtained from the Turkish State Meteorological Service (TSMS). The software has been developed under Matlab 6.0. In the input layer, longitude, latitude, altitude, and height are used, while wind speeds and related power values correspond to output layer. Then we have used the networks to make predictions for varying heights, which are not incorporated to the system at the training stage. The network has successfully predicted the required output values for the test data and the mean error levels for regions differed between 3% and 6%. We believe that using ANNs average wind speed and wind power of a region can be predicted provided with lesser amount of sampling data, that the sampling mechanism is reliable and adequate.     

Low wind speed turbines and wind power potential in Minnesota, USA

Wind power development in Minnesota largely has been focused in the “windy” southwestern part of the state. This research evaluates the additional power that potentially could be generated via low wind speed turbines, particularly for areas of the state where there has been comparatively little wind energy investment. Data consist of 3 years (2002–2004) of wind speed measurements at 70–75 m above ground level, at four sites representing the range of wind speed regimes (Classes 2–5) found in Minnesota. Power estimates use three configurations of the General Electric 1.5-MW series turbine that vary in rotor diameter and in cut-in, cut-out, and rated speeds. Results show that lower cut-in, cut-out, and rated speeds, and especially the larger rotor diameters, yield increases of 15–30% in wind power potential at these sites. Gains are largest at low wind speed (Class 2) sites and during the summer months at all four sites. Total annual wind power at each site shows some year-to-year variability, with peaks at some sites partially compensating for lulls at others. Such compensation does not occur equally in all years: when large-scale atmospheric circulation patterns are strong (e.g., 2002), the four sites show similar patterns of above- and below-average wind power, somewhat reducing the ability of geographic dispersion to mitigate the effects of wind speed variability.     

相同叶尖速比不同转速的垂直轴风力机气动性能分析

在不考虑连杆、转轴及叶尖损失的简化模型基础上,利用Fluent软件采用雷诺平均Navier-Stokes方程与k-ωSST湍流模型对直叶片垂直轴风力机进行了数值模拟.对比了相同叶尖速比λ=4,叶轮半径r分别为1 m和2 m的垂直轴风力机的气动性能.结果表明,在来流风速V∞和叶尖速比λ相同的情况下,不同半径的垂直轴风力机具有十分相似的翼型表面压力分布,对应位置处的升、阻力系数相差不大.     

The application of artificial neural networks to mapping of wind speed profile for energy application in Nigeria

Modelling and prediction of wind speed are essential prerequisites in the sitting and sizing of wind power applications. The profile of wind speed in Nigeria is modelled using artificial neural network (ANN). The ANN model consists of 3-layered, feed-forward, back-propagation network with different configurations, designed using the Neural Toolbox for MATLAB. The monthly mean daily wind speed data monitored at 10 m above ground level for a period of 20 years (1983–2003) for 28 ground stations operated by the Nigeria Meteorological Services (NIMET) were used as training (18 stations) and testing (10 stations) dataset. The geographical parameters (latitude, longitude and altitude) and the month of the year were used as input data, while the monthly mean wind speed was used as the output of the network. The optimum network architecture with minimum Mean Absolute Percentage Error (MAPE) of 8.9% and correlation coefficient (r) between the predicted and the measured wind speed values of 0.9380 was obtained. The predicted monthly wind speed ranged from 0.9–13.1 m/s with an annual mean of 4.7 m/s. The model predicted wind speed values are given in the form of monthly maps, which can be easily used for assessment of wind energy potential for different locations within Nigeria.     

Application of artificial neural networks for the wind speed prediction of target station using reference stations data

In this study, artificial neural networks (ANNs) were applied to predict the mean monthly wind speed of any target station using the mean monthly wind speeds of neighboring stations which are indicated as reference stations. Hourly wind speed data, collected by the Turkish State Meteorological Service (TSMS) at 8 measuring stations located in the eastern Mediterranean region of Turkey were used. The long-term wind data, containing hourly wind speeds, directions and related information, cover the period between 1992 and 2001. These data were divided into two sections. According to the correlation coefficients, reference and target stations were defined. The mean monthly wind speeds of reference stations were used and also corresponding months were specified in the input layer of the network. On the other hand, the mean monthly wind speed of the target station was utilized in the output layer of the network. Resilient propagation (RP) learning algorithm was applied in the present simulation. The hidden layers and output layer of the network consist of logistic sigmoid transfer function (logsig) and linear transfer function (purelin) as an activation function. Finally, the values determined by ANN model were compared with the actual data. The maximum mean absolute percentage error was found to be 14.13% for Antakya meteorological station and the best result was found to be 4.49% for Mersin meteorological station.     

Power curve tracking in the presence of a tip speed constraint

This paper considers the problem of power regulation for a variable speed wind turbine in the presence of a blade tip speed constraint, for example to limit noise emissions. The main contribution of the paper is the formulation of a policy for the regulation of the machine in the transition region between the classical regions II and III that accommodates the tip speed constraint, and the derivation of associated wind schedules for the rotor speed, blade pitch and aerodynamic torque. To exemplify the possible use of such wind schedules in the design of control laws, model-based controllers are formulated in this paper that are capable of performing power curve tracking throughout all wind speeds, in contrast with commonly adopted approaches that use switching controllers to cover the various operating regimes of the machine. The proposed regulation policies and control laws are demonstrated in a high fidelity simulation environment for a representative 3 MW machine.     

Transient analysis of variable-speed wind turbines at wind speed disturbances and a pitch control malfunction

As wind power generation undergoes rapid growth, new technical challenges emerge: dynamic stability and power quality. The influence of wind speed disturbances and a pitch control malfunction on the quality of the energy injected into the electric grid is studied for variable-speed wind turbines with different power-electronic converter topologies. Additionally, a new control strategy is proposed for the variable-speed operation of wind turbines with permanent magnet synchronous generators. The performance of disturbance attenuation and system robustness is ascertained. Simulation results are presented and conclusions are duly drawn.     

On comparing three artificial neural networks for wind speed forecasting

Wind speed forecasting is critical for wind energy conversion systems since it greatly influences the issues such as the scheduling of a power system, and the dynamic control of the wind turbine. In this paper, we present a comprehensive comparison study on the application of different artificial neural networks in 1-h-ahead wind speed forecasting. Three types of typical neural networks, namely, adaptive linear element, back propagation, and radial basis function, are investigated. The wind data used are the hourly mean wind speed collected at two observation sites in North Dakota. The performance is evaluated based on three metrics, namely, mean absolute error, root mean square error, and mean absolute percentage error. The results show that even for the same wind dataset, no single neural network model outperforms others universally in terms of all evaluation metrics. Moreover, the selection of the type of neural networks for best performance is also dependent upon the data sources. Among the optimal models obtained, the relative difference in terms of one particular evaluation metric can be as much as 20%. This indicates the need of generating a single robust and reliable forecast by applying a post-processing method.     

On the energy output estimation of wind turbines

During the operation of the German test field for small Wind Energy Conversion Systems (WECS) on the island of Pellworm five wind turbines were tested following recommendations of the International Energy Agency (IEA) expert group. Possible errors in the estimation of a tested wind turbine's total energy output at a potential installation site are investigated. Different wind speed frequency distributions (the measured one, the Rayleigh and the two-parameter Weibull distribution) are used to calculate the total energy output. The differences between the various distributions are mostly below 10 per cent. An improvement of the energy output estimate by a Weibull-instead of a Rayleigh distribution was not found. It is also shown that the use of the recommended 10 min averages or any other average overestimates the WECS' efficiency, up to 14 per cent on average depending on turbulence intensity. Wind power instead of wind speed is the appropriate parameter for power performance testing. Spectra of wind power and electrical power output show three areas of different correlation. A resistance length for wind turbines is shown to be dependent on the WECS operation status.     

Transfer learning for short-term wind speed prediction with deep neural networks

As a type of clean and renewable energy source, wind power is widely used. However, owing to the uncertainty of wind speed, it is essential to build an accurate forecasting model for large-scale wind power penetration. Numerical weather prediction (NWP) and data-driven modeling are two typical paradigms. NWP is usually unavailable or spatially insufficient. Data-driven modeling is an effective candidate. As to some newly-built wind farms, sufficient historical data is not available for training an accurate model, while some older wind farms may have long-term wind speed records. A question arises regarding whether the prediction model trained by data coming from older farms is also effective for a newly-built farm. In this paper, we propose an interesting trial of transferring the information obtained from data-rich farms to a newly-built farm. It is well known that deep learning can extract a high-level representation of raw data. We introduce deep neural networks, trained by data from data-rich farms, to extract wind speed patterns, and then finely tune the mapping with data coming from newly-built farms. In this way, the trained network transfers information from one farm to another. The experimental results show that prediction errors are significantly reduced using the proposed technique.     

Direct calculation of wind turbine tip loss

The usual method to account for a finite number of blades in blade element calculations of wind turbine performance is through a tip loss factor. Most analyses use the tip loss approximation due to Prandtl which is easily and cheaply calculated but is known to be inaccurate at low tip speed ratio. We develop three methods for the direct calculation of the tip loss. The first is the computationally expensive calculation of the velocities induced by the helicoidal wake which requires the evaluation of infinite sums of products of Bessel functions. The second uses the asymptotic evaluation of those sums by Kawada. The third uses the approximation due to Okulov which avoids the sums altogether. These methods are compared to the tip loss determined independently and exactly for an ideal three-bladed rotor at tip speed ratios between zero and 15. Kawada's asymptotic approximation and Okulov's equations are preferable to the Prandtl factor at all tip speed ratios, with the Okulov equations being generally more accurate. In particular the tip loss factor exceeds unity near the axis of rotation by a large amount at all tip speed ratios, which Prandtl's factor cannot reproduce. Neither the Kawada nor the Okulov equations impose a large computational burden on a blade element program.     

Assessment of wind characteristics and wind turbine characteristics in Taiwan

Wind characteristics and wind turbine characteristics in Taiwan have been thoughtfully analyzed based on a long-term measured data source (1961–1999) of hourly mean wind speed at 25 meteorological stations across Taiwan. A two-stage procedure for estimating wind resource is proposed. The yearly wind speed distribution and wind power density for the entire Taiwan is firstly evaluated to provide annually spatial mean information of wind energy potential. A mathematical formulation using a two-parameter Weibull wind speed distribution is further established to estimate the wind energy generated by an ideal turbine and the monthly actual wind energy generated by a wind turbine operated at cubic relation of power between cut-in and rated wind speed and constant power between rated and cut-out wind speed. Three types of wind turbine characteristics (the availability factor, the capacity factor and the wind turbine efficiency) are emphasized. The monthly wind characteristics and monthly wind turbine characteristics for four meteorological stations with high winds are investigated and compared with each other as well. The results show the general availability of wind energy potential across Taiwan.     

Short term wind speed forecasting for wind turbine applications using linear prediction method

In this paper a new method, based on linear prediction, is proposed for wind speed forecasting. The method utilizes the ‘linear prediction’ method in conjunction with ‘filtering’ of the wind speed waveform. The filtering eliminates the undesired parts of the frequency spectrum (i.e. smoothing) of the measured wind speed which is less effective in an application, for example, in a wind energy conversion system. The linear prediction method is intuitively explained with some easy to follow case studies to clarify the complex underlying mathematics. For verification purposes, the proposed method is compared with real wind speed data based on experimental results. The results show the effectiveness of the linear prediction method.     

A novel online training neural network-based algorithm for wind speed estimation and adaptive control of PMSG wind turbine system for maximum power extraction

In this paper, an adaptive control scheme for maximum power point tracking of stand-alone PMSG wind turbine systems (WTS) is presented. A novel procedure to estimate the wind speed is derived. To achieve this, a neural network identifier (NNI) is designed in order to approximate the mechanical torque of the WTS. With this information, the wind speed is calculated based on the optimal mechanical torque point. The NNI approximates in real-time the mechanical torque signal and it does not need off-line training to get its optimal parameter values. In this way, it can really approximates any mechanical torque value with good accuracy. In order to regulate the rotor speed to the optimal speed value, a block-backstepping controller is derived. Uniform asymptotic stability of the tracking error origin is proved using Lyapunov arguments. Numerical simulations and comparisons with a standard passivity based controller are made in order to show the good performance of the proposed adaptive scheme.     

Performance analysis of the airfoil-slat arrangements for hydro and wind turbine applications

Standard airfoils historically used for wind and hydrokinetic turbines had maximum lift coefficients of around 1.3 at stall angles of attack, which is about 12°. At these conditions, the minimum flow velocities to generate electric power were about 7 m/s and 2 m/s for the wind turbine and the hydrokinetic turbine cases, respectively. In this study, NACA4412-NACA6411 slat–airfoil arrangement was chosen for these two cases in order to investigate the potential performance improvements. Aerodynamic performances of these cases were both numerically and experimentally investigated. The 2D and 3D numerical analysis software were used and the optimum geometric and flow conditions leading to the maximum power coefficient or the maximum lift to drag ratio were obtained. The maximum lift to drag ratio of 24.16 was obtained at the optimum geometric and flow parameters. The maximum power coefficient of 0.506 and the maximum torque were determined at the tip speed ratios of 5.5 and 4.0 respectively. The experimental work conducted in a towing tank gave the power coefficient to be 0.47 which is about %7 lower than the numerical results obtained. Hence, there is reasonable agreement between numerical end experimental values. It may be concluded that slat-hydrofoil or airfoil arrangements may be applied in the design of wind and hydrokinetic turbines for electrical power generation in lower wind velocities (3–4 m/s) and current velocities (about 1 m/s).     

Wind speed prediction in the mountainous region of India using an artificial neural network model

Measured wind speed data are not available for most sites in the mountainous regions of India. The objective of present study is to predict wind speeds for 11 locations in the Western Himalayan Indian state of Himachal Pradesh to identify possible wind energy applications. An artificial neural network (ANN) model is used to predict wind speeds using measured wind data of Hamirpur location for training and testing. Temperature, air pressure, solar radiation and altitude are taken as inputs for the ANN model to predict daily mean wind speeds. Mean absolute percentage error (MAPE) and correlation coefficient between the predicted and measured wind speeds are found to be 4.55% and 0.98 respectively. Predicted wind speeds are found to range from 1.27 to 3.78 m/s for Bilaspur, Chamba, Kangra, Kinnaur, Kullu, Keylong, Mandi, Shimla, Sirmaur, Solan and Una locations. A micro-wind turbine is used to assess the wind power generated at these locations which is found to vary from 773.61 W to 5329.76 W which is suitable for small lighting applications. Model is validated by predicting wind speeds for Gurgaon city for which measured data are available with MAPE 6.489% and correlation coefficient 0.99 showing high prediction accuracy of the developed ANN Model.