Developing a Local Neurofuzzy Model for Short-Term Wind Power Forecasting

E Faghihnia,N Senu,S Salahshour,A Ahmadian

doi:10.1155/2014/637017

E Faghihnia, N Senu + Show 2 more

Open Access

https://doi.org/10.1155/2014/637017

Copy DOI

Abstract

Large scale integration of wind generation capacity into power systems introduces operational challenges due to wind power uncertainty and variability. Therefore, accurate wind power forecast is important for reliable and economic operation of the power systems. Complexities and nonlinearities exhibited by wind power time series necessitate use of elaborative and sophisticated approaches for wind power forecasting. In this paper, a local neurofuzzy (LNF) approach, trained by the polynomial model tree (POLYMOT) learning algorithm, is proposed for short-term wind power forecasting. The LNF approach is constructed based on the contribution of local polynomial models which can efficiently model wind power generation. Data from Sotavento wind farm in Spain was used to validate the proposed LNF approach. Comparison between performance of the proposed approach and several recently published approaches illustrates capability of the LNF model for accurate wind power forecasting.

Highlights

Being free and environmentally friendly, the wind energy is utilized growingly as a renewable source of energy
Multivariate autoregressive integrated moving average (ARIMA), radial basis function (RBF) neural network, multilayer perceptron (MLP) neural network, and ridgelet neural network ridgelet (RNN), all developed by Amjady et al in [5] for comparison since Amjady et al used the same training and test data for their models
We developed the local linear neurofuzzy (LLNF) model, trained by local linear model tree (LOLIMOT) algorithm, in order to evaluate improvement in local neurofuzzy (LNF) model’s accuracy achieved through polynomial model tree (POLYMOT) learning algorithm

Summary

Introduction

Being free and environmentally friendly, the wind energy is utilized growingly as a renewable source of energy. Many methods have been developed for the wind power and speed forecasting These approaches can be classified into two broad categories, namely, physical methods and time series methods [6]. Physical methods use physical and meteorological information, including description of orography, roughness, obstacles, pressure, and temperature to model wind power and forecast its future values. These approaches perform satisfactorily for long-term prediction of wind power [7]. It has been reported that CI-based approaches can outperform physical and conventional time series models in short-term wind power forecasting. Amjady et al proposed a hybrid neural network model for shortterm wind power forecasting [8].

Local Neurofuzzy Models

Selection of Input Variables

Wind Power Forecasting Results and Discussion

Findings

Conclusion