Abstract
Wind speed forecasting is essential for various domains, such as renewable energy generation, aviation, agriculture, and disaster management. However, wind speed is a complex and stochastic phenomenon that exhibits multiple stochastic patterns. Therefore, forecasting methods that can account for the dynamics and uncertainty of wind speed are required. The literature on wind forecasting classifies the time-scale into different categories, such as short-term, medium-term, and long-term. The data used for these categories is usually daily or sub-daily, such as hourly. This implies that high frequency data poses more challenges for the modeling. Machine learning (ML) methods have shown great potential in forecasting wind speed. However, ML methods may not be able to capture the complex and stochastic patterns of time series data, especially when there are multiple seasonal cycles. Therefore, it is often beneficial to use a preprocessing method like time series decomposition before applying ML methods. This article proposes a novel hybrid model that integrates machine learning and time series decomposition for forecasting wind speed. A multivariate seasonal trend decomposition method based on loess (MSTL) is used to preprocess the wind speed data before applying various forecasting methods. MSTL is a generalization of the popular STL method that can split the time series data into a trend component, multiple seasonal components, and a residual component. The seasonal components are considered as deterministic and forecasted using a seasonal naive method that repeats the most recent cycle. For the other non-seasonal components, the neural network autoregression (NNAR) method is employed. The same approach is followed for two common statistical methods: autoregressive integrated moving average and exponential smoothing state space model (ETS). This enables the comparison of the performance of machine learning and statistical forecasting methods based on time series decomposition. The MSTL-NNAR model is also contrasted with the NNAR model without preprocessing to assess the effectiveness of MSTL. The proposed model is applied to two wind speed datasets with different frequencies: daily and hourly. The model is evaluated for both long-term and short-term forecasts by comparing it with other models using various accuracy and bias measures. The results show that the hybrid model, MSTL-NNAR, outperforms all other models in terms of accuracy and bias for both types of data and both time horizons. The results also show that MSTL preprocessing significantly improves the performance of NNAR by reducing its error and bias. The results demonstrate the effectiveness of the hybrid model for forecasting wind speed data that are complex, nonlinear and high-frequency. The model can provide reliable forecasts for different time horizons and different types of data. The model can be useful for various applications, such as wind power generation, weather prediction, and environmental monitoring.
Similar content being viewed by others
References
Ai X, Li S, Xu H (2023) Wind speed prediction model using ensemble empirical mode decomposition, least squares support vector machine and long short-term memory. Front Energy Res 10:1043867
Al Dhaheri K, Woon WL, Aung Z (2017) Wind speed forecasting using statistical and machine learning methods: a case study in the UAE. In: Data analytics for renewable energy integration: informing the generation and distribution of renewable energy: 5th ECML PKDD workshop, DARE 2017, Skopje, Macedonia, September 22, 2017, Revised Selected Papers 5. Springer, pp 107–120
Alhussan AA, El-Kenawy E-SM, Abdelhamid AA, Ibrahim A, Eid MM, Khafaga DS (2023) Wind speed forecasting using optimized bidirectional LSTM based on dipper throated and genetic optimization algorithms. Front Energy Res 11:1172176
Ammar E, Xydis G (2024) Wind speed forecasting using deep learning and preprocessing techniques. Int J Green Energy 21(5):988–1016
Bandara K, Hyndman RJ, Bergmeir C (2021) MSTL: a seasonal-trend decomposition algorithm for time series with multiple seasonal patterns. arXiv preprint arXiv:2107.13462
Birsan M-V, Marin L, Dumitrescu A (2013) Seasonal changes in wind speed in Romania. Rom Rep Phys 65(4):1479–1484
Cao Q, Ewing BT, Thompson MA (2012) Forecasting wind speed with recurrent neural networks. Eur J Oper Res 221(1):148–154
Castillo M, Liang X, Faried SO (2023) Wind speed forecasting using ARMA and boosted regression tree methods: a case study. In: 2023 IEEE Canadian conference on electrical and computer engineering (CCECE). IEEE, pp 136–141
Chang W-Y et al (2014) A literature review of wind forecasting methods. J Power Energy Eng 2(04):161
Chen J, Liu H, Chen C, Duan Z (2022) Wind speed forecasting using multi-scale feature adaptive extraction ensemble model with error regression correction. Expert Syst Appl 207:117358
Cleveland RB, Cleveland WS, McRae JE, Terpenning I (1990) STL: a seasonal-trend decomposition. J Off Stat 6(1):3–73
Duca VE, Fonseca TC, Oliveira FLC (2021) A generalized dynamical model for wind speed forecasting. Renew Sustain Energy Rev 136:110421
Duca VE, Fonseca TC, Oliveira FLC (2023) An overview of non-gaussian state-space models for wind speed data. Energy 266:126436
Elseidi M (2023) Forecasting temperature data with complex seasonality using time series methods. Model Earth Syst Environ 9(2):2553–2567
Elseidi M (2023b) A hybrid facebook prophet-ARIMA framework for forecasting high-frequency temperature data. Model Earth Syst Environ 1–13. https://doi.org/10.1007/s40808-023-01874-4
Fattah J, Ezzine L, Aman Z, El Moussami H, Lachhab A (2018) Forecasting of demand using ARIMA model. Int J Eng Bus Manag 10:1847979018808673
Gupta D, Natarajan N, Berlin M (2022) Short-term wind speed prediction using hybrid machine learning techniques. Environ Sci Pollut Res 29(34):50909–50927
Hanifi S, Liu X, Lin Z, Lotfian S (2020) A critical review of wind power forecasting methods-past, present and future. Energies 13:3764
Huang X, Wang J, Huang B (2021) Two novel hybrid linear and nonlinear models for wind speed forecasting. Energy Convers Manag 238:114162
Hyndman R, Kang Y, Montero-Manso P, Talagala T, Wang E, Yang Y, O’Hara-Wild M et al (2019) tsfeatures: time series feature extraction. R package version, 1(0)
Hyndman RJ, Athanasopoulos G (2018) Forecasting: principles and practice. OTexts
Jain G (2018) Time-series analysis for wind speed forecasting. Malaya J Mat S:55–61
Jørgensen KL, Shaker HR (2020) Wind power forecasting using machine learning: state of the art, trends and challenges. In: 2020 IEEE 8th international conference on smart energy grid engineering (SEGE). IEEE, pp 44–50
Jung J, Broadwater RP (2014) Current status and future advances for wind speed and power forecasting. Renew Sustain Energy Rev 31:762–777
Kong X, Liu X, Shi R, Lee KY (2015) Wind speed prediction using reduced support vector machines with feature selection. Neurocomputing 169:449–456
Kosanoglu F (2022) Wind speed forecasting with a clustering-based deep learning model. Appl Sci 12(24):13031
Lam KC, Oshodi OS (2016) Forecasting construction output: a comparison of artificial neural network and Box–Jenkins model. Eng Constr Archit Manag 23(3):302–322
Lv S-X, Wang L (2022) Deep learning combined wind speed forecasting with hybrid time series decomposition and multi-objective parameter optimization. Appl Energy 311:118674
Maleki A, Nasseri S, Aminabad MS, Hadi M (2018) Comparison of ARIMA and NNAR models for forecasting water treatment plant’s influent characteristics. KSCE J Civ Eng 22:3233–3245
Noman F, Alkawsi G, Alkahtani AA, Al-Shetwi AQ, Tiong SK, Alalwan N, Ekanayake J, Alzahrani AI (2021) Multistep short-term wind speed prediction using nonlinear auto-regressive neural network with exogenous variable selection. Alex Eng J 60(1):1221–1229
Pati N, Gourisaria MK, Das H, Banik D (2023) Wind speed prediction using machine learning techniques. In: 2023 11th international conference on emerging trends in engineering & technology-signal and information processing (ICETET-SIP). IEEE, pp 1–6
Perone G (2021) Comparison of ARIMA, ETS, NNAR, TBATS and hybrid models to forecast the second wave of covid-19 hospitalizations in Italy. Eur J Health Econ 23:1–24
Qian Z, Pei Y, Zareipour H, Chen N (2019) A review and discussion of decomposition-based hybrid models for wind energy forecasting applications. Appl Energy 235:939–953
Roungkvist JS, Enevoldsen P (2020) Timescale classification in wind forecasting: A review of the state-of-the-art. J Forecast 39(5):757–768
Saxena BK, Mishra S, Rao KVS (2022) Forecasting of wind speed by using deep learning for optimal use of the energy produced by wind farms. In: Renewable energy optimization, planning and control: proceedings of ICRTE 2021. Springer, vol 1, pp 91–99
Shamshad B, Khan MZ, Omar Z (2019) Modeling and forecasting weather parameters using ANN-MLP, ARIMA and ETS model: a case study for Lahore, Pakistan. J Appl Stat 5(388):388
Sharma R, Singh D (2018) A review of wind power and wind speed forecasting. J Eng Res Appl 8(7):1–9
Shen X, Kong X, Yu L, Han Y, Gao F, Wu X, Zhang Y (2022) Wind speed forecasting method based on nondominated sorting genetic algorithm and machine learning. In: 2022 IEEE 6th conference on energy internet and energy system integration (EI2). IEEE, pp 2890–2894
Shukla S, Ramaprasad R, Pasari S, Sheoran S (2022) Statistical analysis and forecasting of wind speed. In: 2022 4th international conference on energy, power and environment (ICEPE). IEEE, pp 1–6
Silva ES, Hassani H, Heravi S, Huang X (2019) Forecasting tourism demand with denoised neural networks. Ann Tour Res 74:134–154
Soman SS, Zareipour H, Malik O, Mandal P (2010) A review of wind power and wind speed forecasting methods with different time horizons. In: North American power symposium 2010. IEEE, pp 1–8
Torres JL, Garcia A, De Blas M, De Francisco A (2005) Forecast of hourly average wind speed with ARMA models in Navarre (Spain). Solar Energy 79(1):65–77
Trull O, García-Díaz JC, Peiró-Signes A (2022) Multiple seasonal STL decomposition with discrete-interval moving seasonalities. Appl Math Comput 433:127398
Wang Y, Zhao A, Wei X, Li R (2023) A novel ensemble model based on an advanced optimization algorithm for wind speed forecasting. Energies 16(14):5281
Wu Y-K, Hong J-S (2007) A literature review of wind forecasting technology in the world. In: 2007 IEEE Lausanne Power Tech, pp 504–509
Young I, Zieger S, Babanin AV (2011) Global trends in wind speed and wave height. Science 332(6028):451–455
Zhang GP, Qi M (2005) Neural network forecasting for seasonal and trend time series. Eur J Oper Res 160(2):501–514
Funding
The authors have not disclosed any funding.
Author information
Authors and Affiliations
Contributions
I am the sole author of the paper.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no Conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Elseidi, M. MSTL-NNAR: a new hybrid model of machine learning and time series decomposition for wind speed forecasting. Stoch Environ Res Risk Assess (2024). https://doi.org/10.1007/s00477-024-02701-7
Accepted:
Published:
DOI: https://doi.org/10.1007/s00477-024-02701-7