Communications in Nonlinear Science and Numerical Simulation
Short-term prediction of wind power using EMD and chaotic theory
Highlights
► A hybrid model for wind power forecasting is suggested. The model is based on EMD, chaotic theory, and grey theory. ► EMD is used to decompose wind farm power into several intrinsic mode function (IMF) components and one residual component. ► The grey forecasting model is used to predict the residual component. ► Grey forecasting or chaotic prediction method is used to predict the IMF components for their different characteristics. ► Prediction results of residual component and all IMF components are aggregated to produce the ultimate prediction.
Introduction
With the large-scale wind power parallel in the power grid, wind power’s intermittent and uncertainty increases the instability of its interconnected power grid. Wind turbine as a complex, non-linear and uncertain systems, its safe and reliable operation will have a direct impact on the stability of interconnected power grid, the load distribution and a reasonable quality of power supply. Timely and accurate prediction of wind power generation, have a significant role for improving overall power system scheduling reasonableness, safety and economy [1], [2], [3], [4], [5], [6], [7].
When wind turbine is running, due to the effects of wind speed, wind direction, pressure, temperature, etc., meteorological data, and wind fields, topography, vegetation, surrounded by obstacles, as well as the wheel hub height, power curve, mechanical drive, control strategy and many other factors of the wind turbine itself, the actual wind power output variation is very complicated and difficult to establish its mathematical model [1], [2], [3], [4], [5], [6], [7].
For obtaining timely the actual output power of wind farm, scheduling reasonable dispatching plan of the power grid, it is very important to accurately predict its output power. In this paper, a wind farm power hybrid prediction model is developed based on empirical mode decomposition, chaotic theory, and grey theory. Using empirical mode decomposition method to subdivide the non-stationary wind farm power time series in low and high frequencies parts, and then analyze the decomposed powers’ characteristics, using largest Lyapunov exponent prediction method or grey prediction to predict each scale, respectively. The selection of prediction method is depending on the dynamic behavior on each scale. Reconstruct these predicted results to obtain the ultimate prediction result.
Section snippets
Empirical mode decomposition
Empirical mode decomposition (EMD) is a nonlinear signal processing method developed by Huang et al [8], [9], [10]. It can decompose a signal into a sum of functions, intrinsic mode functions (IMFs). These IMFs must satisfy two conditions: ① the number of extrema and the number of zero-crossings either are equal or differ at the most by one; ② the mean value of the envelope defined by the local maxima and the local minima is zero at all points.
The detailed decomposition process for a time
Prediction model of wind farm power
For the sake of improving the operating economy and reliability of power systems, accurate forecast of wind farms power is essential. Due to wind farm power is highly nonlinear and non-stationary, it is very difficult to predict accurately. In order to improve prediction accuracy, a hybrid forecasting model based on empirical mode decomposition, chaotic time series and grey theory is presented. The empirical mode decomposition method is used to decompose the wind farm power to several detail
Application and analysis
The hybrid forecasting model described in the previous section is applied to Dongtai wind farm power prediction. The Dongtai wind farm situates in the east of China. The output power of a wind turbine is selected to verify the proposed model. The power data is 10 min a sampling point, choose 710 points to analysis.
The actual wind turbine output power time series have certain random volatility, it is necessary to be de-noised. Wavelet method is used to eliminate its noise. The de-noised wind
Conclusion
It is difficult to find an appropriate model to predict wind farm power due to the fact that the power is highly complex and non-linear. In this paper, a hybrid prediction model using empirical mode decomposition, largest Lyapunov exponent prediction method, and grey theory is constructed. The empirical mode decomposition method is used to decompose the wind farm power into several intrinsic mode function components and one residual component. This can reduce the non-stationary of the power
Acknowledgement
This work is supported by the National Basic Research Program (973 Program) (No. 2007CB210304) and China Postdoctoral Science Foundation funded project (No. 20090460273).
References (18)
Short-term prediction of the power production from wind farms
J Wind Eng Ind Aerodyn
(1999)- et al.
Improvements in wind speed forecasts for wind power prediction purposes using Kalman filtering
J Wind Eng Ind Aerodyn
(2008) - et al.
Comparison of two new short-term wind-power forecasting systems
Renew Energy
(2009) - et al.
A novel hybrid EMD-based drift denoising method for a dynamically tuned gyroscope
Measurement
(2009) - et al.
Forecasting crude oil price with an EMD-based neural network ensemble learning paradigm
Energy Econ
(2008) - et al.
Determining Lyapunov exponents from a time series
Phys D Nonlinear Phenom
(1985) - et al.
Grey system theory-based models in time series prediction
Expert Sys Appl
(2010) Practical method for determining the minimum embedding dimension of a scalar time series
Phys D Nonlinear Phenom
(1997)- et al.
Short-term prediction of wind farm power: A data mining approach
IEEE Trans Energy Convers
(2009)