Yongqian Liu

A Hybrid Forecasting Method for Wind Power Ramp Based on Orthogonal Test and Support Vector Machine (OT-SVM)

In an electric power system with a high penetration of wind power, incoming power ramps pose a serious threat to the power system. To adopt suitable response strategies for wind power ramps, it is important to predict them accurately and in a timely manner. Since power ramps are caused by various factors, their occurrence has irregular characteristics and vary by location, bringing great difficulty in forecasting. To solve this problem, a hybrid forecasting model termed as orthogonal test and support vector machine (OT-SVM) was developed in this paper, which combines an orthogonal test (OT) with a support vector machine (SVM). A novel factor analysis method was established based on the theory of the OT, and applied to determine the optimal inputs of a SVM. The effectiveness of OT-SVM was tested with three wind farms in China, while comparing the results with other related methods. The results show that the proposed OT-SVM has the highest accuracy covering different input numbers and time resolutions. In addition, a novel evaluation index mean accuracy index was proposed, considering both the missed ramps and false ramps, which can be used as a supplementary index for critical success index.

Clustering methods of wind turbines and its application in short-term wind power forecasts

Commonly used wind power forecasts methods choose only one representative wind turbine to forecast the output power of the entire wind farm; however, this approach may reduce the forecasting accuracy. If each wind turbine in a wind farm is forecasted individually, this considerably increases the computational cost, especially for a large wind farm. In this work, a compromise approach is developed where the turbines in the wind farm are clustered and a forecast made for each cluster. Three clustering methods are evaluated: K-means; a self-organizing map (SOM); and spectral clustering (SC). At first, wind turbines in a wind farm are clustered into several groups by identifying similar characteristics of wind speed and output power. Sihouette coefficient and Hopkins statistics indices are adopted to determine the optimal cluster number which is an important parameter in cluster analysis. Next, forecasting models of the selected representative wind turbines for each cluster based on correlation analysis are established separately. A comparative study of the forecast effect is carried to determine the most effective clustering method. Results show that the short-term wind power forecasting on the basis of SOM and SC clustering are effective to forecast the output power of the entire wind farm with better accuracy, respectively, 1.67% and 1.43% than the forecasts using a single wind speed or power to represent the wind farm. Both Hopkins statistics and Sihouette coefficient are effective in choosing the optimal number of clusters. In addition, SOM with its higher forecast accuracy and SC with more efficient calculation when applied into wind power forecasts can provide guidance for the operating and dispatching of wind power. The emphasis of the paper is on the clustering methods and its effect applied in wind power forecasts but not the forecasting algorithms.

Novel Cost Model for Balancing Wind Power Forecasting Uncertainty

The intermittency of wind generation creates nonlinear uncertainties in wind power forecasting (WPF). Thus, additional operating costs can be incurred for balancing these forecasting deviations. Normally, large wind power penetration requires accurate quantification of the uncertainty-induced costs. This paper defines this type of costs as wind power uncertainty incremental cost (WPUIC) and wind power uncertainty dispatch cost (WPUDC), and it then formulates a general methodology for deriving them based on probabilistic forecasting of wind power. WPUIC quantifies the incremental cost induced from balancing the uncertainties of wind power generation. WPUDC is a balancing cost function with a quadratic form considering diverse external conditions. Besides, the risk probability (RP) of not meeting the scheduled obligation is also modelled. Above models are established based on a newly developed probabilistic forecasting model, varying variance relevance vector machine (VVRVM). Demonstration results show that the VVRVM and RP provide accurate representation of WPF uncertainties and corresponding risk, and thus they can better support and validate the modelling of WPUDC and WPUIC. The proposed cost models have the potential to easily extend traditional dispatches to a new low-carbon system with a high penetration of renewables.

Adaptabilities of three mainstream short-term wind power forecasting methods

Variability and intermittency of wind is the main challenge for making a reliable wind power forecasting (WPF). Meteorological and topological complexities make it even harder to fit any forecasting algorithm to one particular case. This paper presents the comparison of three short term WPF models based on three wind farms in China with different terrains and climates. The sensitivity effects of training samples on forecasting performance are investigated in terms of sample size, sample quality, and sample time scale. Then, their adaptabilities and modeling efficiency are also discussed under different seasonal and topographic conditions. Results show that (1) radial basis function (RBF) and support vector machine (SVM) generally have higher prediction accuracy than that of genetic algorithm back propagation (GA-BP), but different models show advantages in different seasons and terrains. (2) WPF taking a month as the training time interval can increase the accuracy of short-term WPF. (3) The change of sample number for the GA-BP and RBF is less sensitive than that of the SVM. (4) GA-BP forecasting accuracy is equally sensitive to all size of training samples. RBF and SVM have different sensibility to different size of training samples. This study can quantitatively provide reference for choosing the appropriate WPF model and further optimization for specific engineering cases, based on better understanding of algorithm theory and its adaptability. In this way, WPF users can select the suitable algorithm for different terrains and climates to achieve reliable prediction for market clearing, efficient pricing, dispatching, etc.

Numerical weather prediction wind correction methods and its impact on computational fluid dynamics based wind power forecasting

Numerical weather prediction (NWP) of wind speed (WS) is an important input to wind power forecasting (WPF), which its accuracy will limit the WPF performance. This paper proposes three NWP correcting methods based on the multiple linear regression, a radial basis function neural network, and an Elman neural network. The proposed correction methods exhibit small sample learning and efficient computational ability. So, they are in favour of forecasting the performance of planned large-scale wind farms. To this end, a physical WPF model based on computational fluid dynamics is used to demonstrate the impact of improving the NWP WS data based forecasting. A certain wind farm located in China is selected as the case study, and the measured and NWP WS forecasts before and after correction are taken as inputs to the WPF model. Results show that all three correction methods improve the precision of the NWP WS forecasts, with the nonlinear correction models performing a little better than the linear one. Compared with the original NWP, the three corrected NWP WS have higher annual, single point, and short-term prediction accuracy. As expected, the accuracy of wind power forecasting will increase with the accuracy of the input NWP WS forecast. Moreover, the WS correction enhances the consistency of error variation trends between input WS and output wind power. The proposed WS correction methods greatly improve the accuracy of both original NWP WS and the WPF derived from them.

Optimal power dispatch in wind farm with life extension of wind turbine blades as target

The importance of optimal dispatch in wind farm has been increasingly prominent for large-scale wind farms. The blades are integral parts of wind turbines, which have much influence on the wind turbine life. This paper analyzes the force on the wind turbine blades in different conditions and determines the relationship between the wind turbine blades damage value and different operating conditions and the relationship between the wind turbine blades damage value and life of wind turbine blades. With life extension of wind turbine blades as the optimization objective, the optimal dispatch model is established by Dijkstras algorithm. It is verified that this optimal dispatch model is reliable in the wind farm operation.

Impact of atmospheric stability on wind turbine wake velocity distribution

With the up-scaling of wind farms, wake effect has become a major factor which restricts wind power generation. Accurate simulation of the wind turbine wake velocity decay is of great significance to improve the current situation. Against the limitation of the neutral atmospheric hypothesis in wake simulation, the impact of atmospheric stability is taken into consideration in this paper. Establish the geometric models of single wind turbine, use different Monin-Obuhkov length values to represent diverse atmospheric stability classifications, carry on flow numerical simulation with RANS method. And then obtain wind speed distributions under stable, neural and unstable atmospheric stabilities. Extract the wind speed on hub height behind rotor, and do research on the wake velocity recovery conditions under various atmosphere status. Results show that wake velocity curves under different M-O length take on a variety of distribution characters. The average wind speed in wake area from high to low in order is unstable, neutral and stable atmosphere status. The more stable the atmosphere status, the slower the wake recovery rate. But for any selected atmosphere status, the wake speed in 30 times diameter length behind rotor can all recover to 90% of the inflow wind.

Wind Turbine Wake Vertical Distributions Considering Different Inflow Shear Indices

Wind shear inflow conditions with different indices lead to different wind speed distributions in wind turbine wakes, which further affects the power output of downstream turbines. In this study we focus on wind turbine wake considering different inflow shear indices. The three-dimensional numerical simulation, based on the full NREL 5 MW wind turbine model, was implemented with the RNG k-epsilon turbulence model and solved by pressure-based implicit solver. Distributions of wind speed in the wake regions under uniform inflow and different wind shear inflow conditions were calculated. The results show that wind speed in the wake region increases with the height, especially in the cases with larger wind shear indices, which is different from the result of the simulation under uniform inflow condition. In addition, a part of the rotor of downstream turbine would be outside the wake region when the wind shear index is large enough. The calculated velocity deficit around the upper boundary of wake region would be larger than the actual value, if we ignores the influence of wind shear.

Numerical Simulation of Wake Interference Effects on the Downstream Wind Turbine

In wind farms, the performance of downstream wind turbines is significantly affected by the upstream turbine wakes. In this study, we focus on the wake interactions of two horizontal-axis wind turbines, and the separation distance has been investigated using a Reynolds-averaged Navier-Stokes (RANS) framework. Three models for two in-line turbines arranged with different separation distances have been established using Full Rotor Modelling (FPM) approach. And the flow field in the wake region were analysed to help explain the wake interference effects. The simulation results show that the wake effects depend on the relative positions of wind turbines to a great extent. The wake lateral width increases by almost 31% (at 1D downstream the second wind turbine) caused by the wake interference effects of the first turbine. Additionally, wake effects of upstream wind turbines are not always negative, and they are beneficial for the wake recovery of the downstream turbines under certain circumstances.