Enhancing Short-Term Wind Power Forecasting through Multiresolution Analysis and Echo State Networks

Hugo Gouveia,Ronaldo De Aquino,Aida Ferreira

doi:10.3390/en11040824

Abstract

This article suggests the application of multiresolution analysis by Wavelet Transform—WT and Echo State Networks—ESN for the development of tools capable of providing wind speed and power generation forecasting. The models were developed to forecast the hourly mean wind speeds, which are applied to the wind turbine’s power curve to obtain wind power forecasts with horizons ranging from 1 to 24 h ahead, for three different locations of the Brazilian Northeast. The average improvement of Normalized Mean Absolute Error—NMAE for the first six, twelve, eighteen and twenty-four hourly power generation forecasts obtained by using the models proposed in this article were 70.87%, 71.99%, 67.77% and 58.52%, respectively. These results of improvements in relation to the Persistence Model—PM are among the best published results to date for wind power forecasting. The adopted methodology was adequate, assuring statistically reliable forecasts. When comparing the performance of fully-connected feedforward Artificial Neural Networks—ANN and ESN, it was observed that both are powerful time series forecasting tools, but the ESN proved to be more suited for wind power forecasting.

Highlights

Nowadays, wind energy is one of the most successful sources of renewable energy used around the world
The incentive policies adopted by several countries are among the drivers for using wind power, since they guarantee the purchase of energy produced by wind farms even if the price of energy is not competitive
Similar patterns and results were observed for all forecasting horizons and analyzed wind speed series

Summary

Introduction

Wind energy is one of the most successful sources of renewable energy used around the world. The incentive policies adopted by several countries are among the drivers for using wind power, since they guarantee the purchase of energy produced by wind farms even if the price of energy is not competitive. Other countries adopted incentive policies, as in the case of Brazil, with the creation of the Incentive Program for Alternative Sources of Electric. Since wind generation is an intermittent source of generation, the use of models or techniques capable of predicting the energy produced by these type of sources is essential for an adequate wind power integration into electrical power systems. The higher the penetration level of wind generation, the greater the need for forecasting tools of this type of generation, in order to maximize the integration between the generation from conventional sources (which is planned and programmed) and the forecast

Methods

Results

Discussion

Conclusion