Short-term wind power prediction based on extreme learning machine with error correction

Zhi Li,Yongning Zhao,Jingxin Jin,Jingzhu Teng,Xuri Song,Lin Ye

doi:10.1186/s41601-016-0016-y

Abstract

Large-scale integration of wind generation brings great challenges to the secure operation of the power systems due to the intermittence nature of wind. The fluctuation of the wind generation has a great impact on the unit commitment. Thus accurate wind power forecasting plays a key role in dealing with the challenges of power system operation under uncertainties in an economical and technical way. In this paper, a combined approach based on Extreme Learning Machine (ELM) and an error correction model is proposed to predict wind power in the short-term time scale. Firstly an ELM is utilized to forecast the short-term wind power. Then the ultra-short-term wind power forecasting is acquired based on processing the short-term forecasting error by persistence method. For short-term forecasting, the Extreme Learning Machine (ELM) doesn’t perform well. The overall NRMSE (Normalized Root Mean Square Error) of forecasting results for 66 days is 21.09 %. For the ultra-short term forecasting after error correction, most of forecasting errors lie in the interval of [−10 MW, 10 MW]. The error distribution is concentrated and almost unbiased. The overall NRMSE is 5.76 %. The ultra-short-term wind power forecasting accuracy is further improved by using error correction in terms of normalized root mean squared error (NRMSE).

Highlights

Large-scale integration of wind generation brings great challenges to the secure operation of the power systems due to the intermittence nature of wind
The combined approach can improve the forecasting accuracy by 5–10 % compared to single statistics [15]
With 3 hidden nodes, the Extreme Learning Machine (ELM) has the best performance of 21.09 % in terms of normalized root mean squared error (NRMSE)

Summary

Introduction

Large-scale integration of wind generation brings great challenges to the secure operation of the power systems due to the intermittence nature of wind. Accurate wind power forecasting plays a key role in dealing with the challenges of power system operation under uncertainties in an economical and technical way. The large-scale integration of wind power is challenging power grids operation and management [1]. In order to schedule the spinning reserve capacity and manage the grid operation, persistence approach was commonly used to predict changes of the wind power production in the ultra-short-term [3, 4]. The basic statistical approach includes the time-series analysis and neural networks, such as Box-Jenkins ARMA (p, q) models, where p represents most recent wind speeds and q represents most recent forecasting errors [8]. Neural network (NN) models have been widely applied in a variety

Methods

Results

Conclusion