Wind energy, one of the greatest progressing renewable energy sources, becomes more significant for sustainable development and environmental protection. Its intermittent nature makes accurate and reliable predictions very challenging. Currently, hybrid models are extensively employed for wind speed forecasting and have been established to perform superior to traditional single forecast models. Hence, in this paper, a hybrid multi-step wind speed forecasting framework that combines the features of Wavelet Transform (WT), Long Short Term Memory (LSTM), and Support Vector Regression (SVR) is proposed. The prediction accuracy of the model is enhanced by denoising the dataset using wavelet transforms, which decomposes the data into low and high-frequency sub-series. The low-frequency sub-series is forecasted using LSTM network, and the high-frequency sub-series using SVR. Each forecasting outcomes are summed up to get the final forecasting results. The simulation results reveal that the forecast accuracy has significantly improved for the proposed wavelet-based hybrid model.
AwadMKhannaR (2015) Support vector regression. In: PepperJWeissSHaukeP (eds.) Efficient Learning Machines. Berkeley, CA: Apress. pp. 67–80.
2.
BasakiDPalSPatranabisDC (2007) Support vector regression. Neural Information Processing—Letters and Reviews, 11(10): 203–224.
3.
BayerFMKozakeviciusAJCintraRJ (2019) An iterative wavelet threshold for signal denoising. Signal Processing162: 10–20.
4.
Ben TaiebSBontempiGAtiyaAF, et al. (2012) A review and comparison of strategies for multi-step ahead time series forecasting based on the NN5 forecasting competition. Expert Systems with Applications39(8): 7067–7083.
5.
CaiHJiaXFengJ, et al. (2020) Gaussian process regression for numerical wind speed prediction enhancement. Renewable Energy146: 2112–2123.
6.
ChenMRZengGQLuKD, et al. (2019) A two-layer nonlinear combination method for short-term wind speed prediction based on ELM, ENN and LSTM. IEEE Internet of Things Journal6(4): 6997–7010.
7.
ChuJYuanLWangW, et al. (2019) Short-term wind speed prediction based on deep learning. In: IOP Conference Series: Earth and Environmental Science233: 052007.
8.
DautovÇPÖzerdemMS (2018) Introduction to wavelets and their applications in signal denoising. Bitlis Eren University Journal of Science & Technology8(1): 1–10.
9.
DhimanHSAnandPDebD (2019) Wavelet transform and variants of SVR with application in wind forecasting. In DebDipankarBalasValentina E.DeyRajeeb (eds): Innovations in Infrastructure. Springer: Singapore, pp. 501–511.
10.
DuJLiuYYuY, et al. (2017) A prediction of precipitation data based on support vector machine and particle swarm optimization (PSO-SVM) algorithms. Algorithms10(2): 57.
11.
DuanXLiQWangR, et al. (2015) An error-revision-based method for very short-term wind speed prediction using wavelet transform and support vector machine. In: 2015 international conference on control, automation and information sciences (ICCAIS), Changshu, China, pp. 197–202. IEEE.
12.
DupréADrobinskiPAlonzoB, et al. (2020) Sub-hourly forecasting of wind speed and wind Energy. Renewable Energy145: 2373–2379.
13.
GoodfellowIBengioYCourvilleA (2016) Deep Learning. Cambridge: The MIT Press publisher.
14.
HochreiterSSchmidhuberJ (1997) Long short-term memory. Neural Computation9(8): 1735–1780.
15.
HouCHanHLiuZ, et al. (2019) A wind direction forecasting method based on Z_score normalization and long short term memory. In: 2019 IEEE 3rd international conference on green energy and applications (ICGEA), Taiyuan, China, pp. 172–176. IEEE.
16.
HusseinSChandraRSharmaA (2016). Multi-step-ahead chaotic time series prediction using coevolutionary recurrent neural networks. In: 2016 IEEE congress on evolutionary computation (CEC), Vancouver, BC, pp. 3084–3091. IEEE.
17.
JaseenaKUKovoorBC (2019) Deep learning based multi-step short term wind speed forecasts with LSTM. In: Proceedings of the second international conference on data science, E-learning and information systems, Dubai, UAE, p. 7. ACM.
18.
KakarekoGJungSVanliOA (2020) Hurricane risk analysis of the residential structures located in Florida. Sustainable and Resilient Infrastructure5(6): 395–409.
19.
KhandelwalIAdhikariRVermaG (2015) Time series forecasting using hybrid ARIMA and ANN models based on DWT decomposition. Procedia Computer Science48: 173–179.
20.
KocatepeAUlakMBKakarekoG, et al. (2019) Measuring the accessibility of critical facilities in the presence of hurricane-related roadway closures and an approach for predicting future roadway disruptions. Natural Hazards95(3): 615–635.
21.
KushwahVWadhvaniRKushwahAK (2020) Trend-based time series data clustering for wind speed forecasting. Wind Engineering, First Published online 21 July. Available at: https://doi.org/10.1177/0309524X20941180
22.
LabatiRDGenoveseAPiuriV, et al. (2018) A decision support system for wind power production. IEEE Transactions on Systems, Man, and Cybernetics: Systems50(1): 290–304.
23.
LiangSNguyenLJinF (2018) A multi-variable stacked long-short term memory network for wind speed forecasting. In: 2018 IEEE international conference on big data (big data), Seattle, WA, USA, pp. 4561–4564. IEEE.
24.
LiuHChenCLvX, et al. (2019). Deterministic wind energy forecasting: A review of intelligent predictors and auxiliary methods. Energy Conversion and Management195: 328–345.
25.
LiuZJiangPZhangL, et al. (2020). A combined forecasting model for time series: Application to short-term wind speed forecasting. Applied Energy259: 114137.
26.
LiuHMiXLiY (2018). Smart multi-step deep learning model for wind speed forecasting based on variational mode decomposition, singular spectrum analysis, LSTM network and ELM. Energy Conversion and Management159: 54–64.
27.
LiuJZioE (2017) SVM hyperparameters tuning for recursive multi-step-ahead prediction. Neural Computing and Applications28(12): 3749–3763.
28.
MasumSLiuYChivertonJ (2018) Multi-step time series forecasting of electric load using machine learning models. In: International conference on artificial intelligence and soft computing, pp. 148–159. Cham: Springer.
29.
MishraSVanliOAKakarekoG, et al. (2019) Preventive maintenance of wood-framed buildings for hurricane preparedness. Structural Safety76: 28–39.
30.
NielsenMA (2015) Neural Networks and Deep Learning. vol. 25. San Francisco, CA: Determination press publisher.
31.
NiyaCZhengQXiao-fengM (2011) A hybrid model for short-term wind speed forecasting based on wavelet and support vector machine. In: IET conference on renewable power generation (RPG 2011). Edinburgh, UK.
32.
NouraniVTajbakhshADMolajouA (2019) Data mining based on wavelet and decision tree for rainfall-runoff simulation. Hydrology Research50(1): 75–84.
33.
NuryAHHasanKAlamMJB (2017) Comparative study of wavelet-ARIMA and wavelet-ANN models for temperature time series data in northeastern Bangladesh. Journal of King Saud University-Science29(1): 47–61.
34.
ShaoHWeiHDengX, et al. 2016. Short-term wind speed forecasting using wavelet transformation and AdaBoosting neural networks in Yunnan wind farm. IET Renewable Power Generation11(4): 374–381.
35.
ShiZLiangHDinavahiV (2018) Wavelet neural network based multi objective interval prediction for short-term wind speed. IEEE Access6: 63352–63365.
36.
Siami-NaminiSTavakoliNNaminAS (2018) A comparison of ARIMA and LSTM in forecasting time series. In: 2018 17th IEEE international conference on machine learning and applications (ICMLA), Orlando, USA, pp. 1394–1401. IEEE.
37.
SinghPJoshiSDPatneyRK, et al. 2017. The Fourier decomposition method for nonlinear and non-stationary time series analysis. Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences473(2199): 20160871.
38.
SmolaAJSchölkopfB. (2004) A tutorial on support vector regression. Statistics and Computing14(3): 199–222.
39.
SuYWangSXiaoZ, et al. (2018) An ultra-short-term wind power forecasting approach based on wind speed decomposition, wind direction and elman neural networks. In: 2018 2nd IEEE conference on energy internet and energy system integration (EI2), Beijing, China, pp. 1–9. IEEE.
40.
WangCZhangHMaP. (2020) Wind power forecasting based on singular spectrum analysis and a new hybrid Laguerre neural network. Applied Energy259: 114139.
41.
WangJZWangY (2017) A novel wind speed forecasting model for wind farms of Northwest China. International Journal of Green Energy14(5): 463–478.
42.
WuYKSuPEWuTY, et al. (2018). Probabilistic wind-power forecasting using weather ensemble models. IEEE Transactions on Industry Applications54(6): 5609–5620.
43.
YousefiMHooshyarDYousefiM, et al. (2015) An artificial neural network hybrid with wavelet transform for short-term wind speed forecasting: A preliminary case study. In: 2015 international conference on science in information technology (ICSITech), Yogyakarta, Indonesia, pp. 95–99. IEEE.
44.
YuCLiYZhangM (2017) An improved wavelet transform using singular spectrum analysis for wind speed forecasting based on Elman neural network. Energy Conversion and Management148: 895–904.
45.
ZhangKGençayRandYazganME. (2017) Application of wavelet decomposition in time-series forecasting. Economics Letters158: 41–46.
46.
ZhaoZWangXLZhangYG, et al. (2017) Wind speed prediction based on wavelet analysis and time series method. In: 2017 International conference on wavelet analysis and pattern recognition (ICWAPR), Ningbo, China, pp. 23–27. IEEE.
