A hybrid structure of an extreme learning machine combined with feature selection,signal decomposition and parameter optimization for short-term wind speed forecasting
Restricted accessResearch articleFirst published online January, 2020
A hybrid structure of an extreme learning machine combined with feature selection,signal decomposition and parameter optimization for short-term wind speed forecasting
Influenced by various environmental and meteorological factors, wind speed presents stochastic and unstable characteristics, which makes it difficult to forecast. To enhance the forecasting accuracy, this study contributes to short-term multi-step hybrid wind speed forecasting (WSF) models using wavelet packet decomposition (WPD), feature selection (FS) and an extreme learning machine (ELM) with parameter optimization. In the model, the WPD technique is applied to decompose the empirical wind speed data into different, relatively stable components to reduce the influence of the unstable characteristics of wind speed. A hybrid particle swarm optimization gravitational search algorithm (HPSOGSA) combining conventional PSOGSA with binary PSOGSA (BPSOGSA) is utilized to realize the FS and parameter optimization simultaneously. The PSOGSA is employed to tune the parameter combination of input weights and biases in ELM, while BPSOGSA is exploited to select the most suitable features from the candidate input variables determined by a partial autocorrelation function for reconstruction of the input matrix for ELM. The proposed forecasting strategy carries out multi-step short-term WSF using mean half-hour historical wind speed data collected from a wind farm situated in Anhui, China. To investigate the forecasting results of the hybrid model, a lot of comparisons and analyses are executed. Simulation results illustrate that the proposed WPD-ELM model with FS and parameter optimization can effectively catch the non-linear characteristics hidden in wind speed data and provide satisfactory WSF performance.
AbdoosAA (2016) A new intelligent method based on combination of VMD and ELM for short term wind power forecasting. Neurocomputing203: 111–120.
2.
AghajaniAKazemzadehoREbrahimiA (2016) A novel hybrid approach for predicting wind farm power production based on wavelet transform, hybrid neural networks and imperialist competitive algorithm. Energy Conversion and Management121: 232–240.
3.
AkbariAArjmandiMK (2014) An efficient voice pathology classification scheme based on applying multi-layer linear discriminant analysis to wavelet packet-based features. Biomedical Signal Processing and Control10: 209–223.
4.
CaoZXiaJZhangM, et al. (2015) Optimization of gear blank preforms based on a new R-GPLVM model utilizing GA-ELM. Knowledge-Based Systems83: 66–80.
5.
ChenNQianZNabneyIT, et al. (2014) Wind power forecasts using Gaussian processes and numerical weather prediction. IEEE Transactions on Power Systems29: 656–665.
6.
DoucoureBAgbossouKCardenasA (2016) Time series prediction using artificial wavelet neural network and multi-resolution analysis: application to wind speed data. Renewable Energy92: 202–211.
7.
FengCCuiMHodgeB-M, et al. (2017) A data-driven multi-model methodology with deep feature selection for short-term wind forecasting. Renewable Energy190: 1245–1257.
8.
FigueiredoEMNLudermirTB (2014) Investigating the use of alternative topologies on performance of the PSO-ELM. Neurocomputing127: 4–12.
9.
HuangGBChenL (2008) Enhanced random search based incremental extreme learning machine. Neurocomputing71: 3460–3468.
HuangGBZhouHDingX, et al. (2012) Extreme learning machine for regression and multiclass classification. IEEE Transactions on Systems, Man, and Cybernetics, Part B42: 513–529.
12.
JayaprakasamSRahimSKALeowCY (2015) PSOGSA-Explore: a new hybrid metaheuristic approach for beampattern optimization in collaborative beamforming. Applied Soft Computing30: 229–237.
13.
JiangPWangYWangJZ (2017) Short-term wind speed forecasting using a hybrid model. Energy119: 561–577.
14.
JiangYHuangGQ (2017) Short-term wind speed prediction: hybrid of ensemble empirical mode decomposition, feature selection and error correction. Energy Conversion and Management144: 340–350.
LiangZTLiangJWangC, et al. (2016) Short-term wind power combined forecasting based on error forecast correction. Energy Conversion and Management119: 215–226.
17.
LiuDNiuDWangH, et al. (2014) Short-term wind speed forecasting using wavelet transform and support vector machines optimized by genetic algorithm. Renewable Energy62: 592–597.
18.
LiuHTianH-QPanD-F, et al. (2013) Forecasting models for wind speed using wavelet, wavelet packet, time series and artificial neural networks. Applied Energy107: 191–208.
19.
LiuHTianHQLiY-F (2015). Four wind speed multi-step forecasting models using extreme learning machines and signal decomposing algorithms. Energy Conversion and Management100: 16–22.
20.
LuoMLiCZhangX, et al. (2016) Compound feature selection and parameter optimization of ELM for fault diagnosis of rolling element bearings. ISA Transactions65: 556–566
21.
MengAGeJYinH, et al. (2016) Wind speed forecasting based on wavelet packet decomposition and artificial neural networks trained by crisscross optimization algorithm. Energy Conversion and Management114: 75–88.
22.
MirjaliliSWangGG (2014) Binary optimization using hybrid particle swarm optimization and gravitational search algorithm. Neural Computing and Application25: 1423–1435.
23.
RashediENezamabadi-pourHSaryazdiS (2009) GSA: a gravitational search algorithm. Information Sciences179: 2232–2248.
24.
Salcedo-SanzSPastor-SánchezAPrietoL, et al. (2014) Feature selection in wind speed prediction systems based on a hybrid coral reefs optimization – Extreme learning machine approach. Energy Conversion and Management87: 10–18.
25.
ShunmugeshKPanneerselvamK (2016) Machinability study of carbon fiber reinforced polymer in the longitudinal and transverse direction and optimization of process parameters using PSO-GSA. Engineering Science and Technology, an International Journal19: 1552–1563.
26.
TangYQiWShaQ, et al. (2014) A combination forecast method based on cross entropy theory for wind power and application in power control. Transactions of the Institute of Measurement and Control36: 891–897.
27.
TascikaraogluASanandajiBMPoollaK, et al. (2016) Exploiting sparsity of interconnections in spatio-temporal wind speed forecasting using wavelet transform. Applied Energy165: 735–747.
28.
TascikaraogluAUzunogluM (2014) A review of combined approaches for prediction of short-term wind speed and power. Renewable Sustainable Energy Review34: 243–254.
29.
TorresJLGarcaADe BlasM, et al. (2015) Forecast of hourly average wind speed with ARMA models in Navarre (Spain). Solar Energy79: 65–77.
30.
WangJZXiongSH (2014) A hybrid forecasting model based on outlier detection and fuzzy time series – a case study on Hainan wind farm of China. Energy76: 526–541.
31.
XiaoLYQianFShaoW (2017) Multi-step wind speed forecasting based on a hybrid forecasting architecture and an improved bat algorithm. Energy Conversion and Management143: 410–430.
32.
YanJLiKBaiE-W, et al. (2016) Hybrid probabilistic wind power forecasting using temporally local Gaussian process. IEEE Transactions on Sustainable Energy7: 87–95.
33.
YanJLiKBaiEW, et al. (2016) Time series wind power forecasting based on variant Gaussian Process and TLBO. Neurocomputing189: 135–144.
34.
YuanXChenCYuanY, et al. (2015) Short-term wind power prediction based on LSSVM-GSA model. Energy Conversion and Management101: 393–401.
35.
YuanXTanQLeiX, et al. (2017) Wind power prediction using hybrid autoregressive fractionally integrated moving average and least square support vector machine. Energy129: 122–137.
36.
ZhangCWeiHZhaoJ, et al. (2016) Short-term wind speed forecasting using empirical mode decomposition and feature selection. Renewable Energy96: 727–737.
37.
ZhangCZhouJLiC, et al. (2017) A compound structure of ELM based on feature selection and parameter optimization using hybrid backtracking search algorithm for wind speed forecasting. Energy Conversion and Management143: 360–376.
38.
ZhangJDraxlCHopsonT, et al. (2015) Comparison of numerical weather prediction based deterministic and probabilistic wind resource assessment methods. Applied Energy156: 528–541.
