Performance Evaluation of Different ANN Models for Medium Term Wind Speed Forecasting

Abstract

Wind power generation is characterized by its variability and uncertainty in the wind speed. Thus, the integration of wind farms to utility grids has several impacts on the optimum power flow, transmission congestion, load dispatch, economic analysis, and electricity market clearing prices. Due to the irregular nature of wind power production, accurate prediction of wind speed poses a major challenge to researchers. Wind speed of a wind farm is affected by conditions of the environment in which the wind farm is built, such as temperature, humidity, dew point, atmospheric pressure and wind direction. In this paper, five ANN techniques namely FFBP, CFBP, PNN, GRNN and KNN are considered to predict the wind speed using MATLAB. The feasibility of the proposed techniques is evaluated using the performance measures such as MSE, MAPE and linear regression and it is observed that GRNN is superior amongst the other methods that are used.

Optimal power flow incorporating wind power and optimally allocated energy storage

“…The basic BP algorithm is a gradient descent one (Lee and Park, 1992), which adjusts the network weights along the steepest descent direction of the error function. Other forecasting techniques such as PNN and GRNN explained in Dhivya et al (2011) are also considered for comparison and analysis.…”

Wavelet neural network–based wind speed forecasting and application of shuffled frog leap algorithm for economic dispatch with prohibited zones incorporating wind power

“…The time series is divided into two folders: one is the training set with 964 samples used for the model's training and the other is the test set that contains the rest, namely, 36 samples, which are used to verify the accuracy during the prediction period. Some of the data in the study by Dhivya et al (2011) are purposely multiplied by a constant (*10, *100 or *1000) to avoid storage of floating point numbers and the same data are considered. Different AI techniques such as feed-forward backpropagation (FFBP), cascade-forward backpropagation (CFBP), PNN, GRNN and k-nearest neighbours (KNN) are applied to the developed model in the author's previous paper (Dhivya et al, 2011) and are given in Table 1.…”

Wavelet Neural Network Based Wind Speed Forecasting and Wind Power Incorporated Economic Dispatch with Losses

“…The variable nature of wind energy also raises challenges in the operation and planning of the power systems, because it is essential to maintain an instantaneous balance between generation and demand at all times. Although considerable strides have been taken in the development of wind power forecasting methodologies over the last year, wind power cannot be scheduled with total accuracy [3]. Two different schools of thought exist w.r.t.…”

“…Generally, some of the forecasting methods applied for wind speed are the neuro fuzzy systems, Artificial Neural Networks (ANN) and Probabilistic Neural Networks (PNN) [4,5]. The models proposed in [3][4][5] register limited ability in achieving non linearity in the time series, thus failing to accurately predict the speed. Therefore, to improve the ANN in terms of accuracy and stability, it has been attempted to combine it with wavelet networks, which have the inherent ability of multi-scale analysis [6].…”

“…[25,26], which adjusts the network weights along the steepest descent direction of error function. The other forecasting techniques, PNN and GRNN, described in [3] are also considered for comparison and analysis. All these methods involve the limitations of obtaining monolithic global models for a time-series [5].…”