Wind Power Generation Forecasting Using Least Squares Support Vector Machine Combined with Ensemble Empirical Mode Decomposition, Principal Component Analysis and a Bat Algorithm

Abstract

Abstract:Regarding the non-stationary and stochastic nature of wind power, wind power generation forecasting plays an essential role in improving the stability and security of the power system when large-scale wind farms are integrated into the whole power grid. Accurate wind power forecasting can make an enormous contribution to the alleviation of the negative impacts on the power system. This study proposes a hybrid wind power generation forecasting model to enhance prediction performance. Ensemble empirical mode decomposition (EEMD) was applied to decompose the original wind power generation series into different sub-series with various frequencies. Principal component analysis (PCA) was employed to reduce the number of inputs without lowering the forecasting accuracy through identifying the variables deemed as significant that maintain most of the comprehensive variability present in the data set. A least squares support vector machine (LSSVM) model with the pertinent parameters being optimized by bat algorithm (BA) was established to forecast those sub-series extracted from EEMD. The forecasting performances of diverse models were compared, and the findings indicated that there was no accuracy loss when only PCA-selected inputs were utilized. Moreover, the simulation results and grey relational analysis reveal, overall, that the proposed model outperforms the other single or hybrid models.

Year Ahead Demand Forecast of City Natural Gas Using Seasonal Time Series Methods

“…In our study, theṘ 2 value of the time series decomposition, Holt-Winters and ARIMA are 0.915, 0.846 and 0.956, respectively. Wu and Peng introduced a wind power generation forecasting model and they compared their result with the ARIMA method [60]. They found 38.57% MAPE with ARIMA forecasting whereas we achieved a three times lower MAPE.…”

Spatial and Temporal Wind Power Forecasting by Case-Based Reasoning Using Big-Data

“…In particular, in [12] PCA is integrated in a statistical wind-forecasting algorithm in order to reduce the cardinality of a time delay-matrix, simplifying the solution of the time regression problem. According to the same principle, in [13] a PCA-based technique is employed to reduce the cardinality of the training set of a neural network aimed at improving the wind forecasting accuracy of a mesoscale model, while in [14] the same technique is employed to select the most suitable inputs for a semi-physical forecasting method. Moreover, in [15] a method based on PLSR is adopted in an ensemble-forecasting framework to determine the weighting factors to assign in combining the output of multiple forecast algorithms.…”

A Naive Bayesian Wind Power Interval Prediction Approach Based on Rough Set Attribute Reduction and Weight Optimization

“…This domain can be accurately divided into the equivalence classes of the relational D according to the classified U/C 1 information; |U| is the number of elements Energies 2017, 10,1903 4 of 15 in a domain. γ C 1 (D) represents the proportion of objects that can be accurately assigned to the decision class U/C under the condition attribute C 1 , and describes the extent to which the conditional attribute C 1 supports the decision attribute D.…”

“…The main focus of these methods is to reduce the point forecast errors of wind power by introducing new models. In [10], the original wind power data are decomposed by Ensemble Empirical Mode Decomposition (EEMD) and the decomposition sequences that are reduced by the principal component analysis are predicted by the least squares support vector machine. However, prediction errors cannot be fully eliminated, even if the best forecasting tools are adopted [11].…”