Modelos híbrido e ensemble para previsão de geração de energia eólica
uma revisão sistemática
DOI:
https://doi.org/10.14488/1676-1901.v26i2.5634Palavras-chave:
Methodi Ordinatio 2.0, Previsão eólica, Híbrido, EnsembleResumo
A previsão da geração eólica é essencial para auxílio nas tomadas de decisões vinculadas a uso de fontes energéticas mais poluentes e/ou mais custosas. Este estudo realizou uma revisão de literatura sobre os métodos híbridos e ensemble para previsão de geração de energia eólica utilizando o Methodi Ordinatio 2.0. Foram selecionados 31 artigos no portfólio, em que avaliou-se a utilização de: pré-processamento, métodos de previsão e métrica de desempenho. Os artigos do portfólio demonstram uma preferência pelo pré-processamento dos dados, principalmente através dos métodos Empirical Mode Decomposition (EMD) e Variational Mode Decomposition (VMD) e suas variantes. Algo similar ocorreu com os métodos de previsão, em que foi encontrado uma variedade alta entre os métodos identificados. Já as métricas de desempenho, por mais que também haja uma variedade considerável, todos artigos possuíam a Mean Absolute Error (MAE) ou Root Mean Squared Error (RMSE). Dos artigos 70,97% são provenientes da China, e 29,03% do portfólio total provém da revista Energy.
Downloads
Referências
AI, C. et al. Chaotic time series wind power interval prediction based on quadratic decomposition and intelligent optimization algorithm. Chaos, Solitons and Fractals, v. 177, 114222, 2023.
ASLAM, M. KIM, J.-S. JUNG, J. Multi-step ahead wind power forecasting based on dual-attention mechanism. Energy Reports, v. 9, p. 239-251, 2023.
CASCIARO, G. et al. Novel strategies of Ensemble Model Output Statistics (EMOS) for calibrating wind speed/power forecasts. Energy Conversion and Management, v. 271, 116297, 2022.
CHANG, Y. et al. A Hybrid Model for Long-Term Wind Power Forecasting Utilizing NWP Subsequence Correction and Multi-Scale Deep Learning Regression Methods. IEEE TRANSACTIONS ON SUSTAINABLE ENERGY, vol. 15, 1, 2024.
DAI, J. FU, L. A wind speed forecasting model using nonlinear auto-regressive model optimized by the hybrid chaos-cloud salp swarm algorithm. Energy, v. 298, 131332, 2024.
DONADIO, L. FANG, J. PORTÉ-AGEL, F. Numerical Weather Prediction and Artificial Neural Network Coupling for Wind Energy Forecast. Energies, v. 14, 338, 2021.
GAO, Y. et al. Multi-step wind speed prediction based on LSSVM combined with ESMD and fractional-order beetle swarm optimization. Energy Reports, v. 9, p. 6114-6134, 2023.
HANIFI, S. et al. Offshore wind power forecasting based on WPD and optimised deep learning methods. Renewable Energy, v. 218, 119241, 2023.
HOU, G. et al. A novel wind power deterministic and interval prediction framework based on the critic weight method, improved northern goshawk optimization, and kernel density estimation. Renewable Energy, v. 222, 119863, 2024.
HOU, G. WANG, J. FAN, Y. Wind power forecasting method of large-scale wind turbine clusters based on DBSCAN clustering and an enhanced hunter-prey optimization algorithm. Energy Conversion and Management, v. 307, 118341, 2024.
JUNG, C. SCHINDLER, D. Comprehensive validation of 68 wind speed models highlights the benefits of ensemble approaches. Energy Conversion and Management, v. 286, 117012, 2023.
KARIJADI, I. et al. Wind power forecasting based on hybrid CEEMDAN-EWT deep learning method. Renewable Energy, v. 218, 119357, 2023.
LI, G. et al. Hybrid forecasting system considering the influence of seasonal factors under energy sustainable development goals. Measurement, v. 211, 112607, 2023.
LIU, X. et al. A Bayesian Deep Learning-based Wind Power Prediction Model Considering the Whole Process of Blade Icing and De-icing. IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, v. 20, p 1-11, 2024.
MENG, A. et al. An adaptive distribution-matched recurrent network for wind power prediction using time-series distribution period division. Energy, v. 299, 131383, 2024.
MIRZA, A. F. et al. Quantile-transformed multi-attention residual framework (QT-MARF) for medium-term PV and wind power prediction. Renewable Energy, v. 220, 119604, 2024.
MORETTIN, P. A.; TOLOI, C. M. C. Modelos de suavização exponencial. Análise de Séries Temporais: Modelos lineares univariados. São Paulo: Edgard Blucher, 2018.
OLIVEIRA, M. S. de. Et al. Integrated data envelopment analysis, multi-criteria decision making, and cluster analysis methods: Trends and perspectives. Decision Analytics Journal, v. 8, 100271, 2023.
PAGANI, R.N. KOVALESKI, J.L. RESENDE, L.M. Methodi Ordinatio: a proposed methodology to select and rank relevant scientific papers encompassing the impact factor, number of citation, and year of publication. Scientometrics, v.105, p. 2109-2135, 2015.
PAGANI, R.N. et al. Methodi Ordinatio 2.0: revisited under statistical estimation, and presenting FInder and RankIn. Quality & Quantity, v. 57, p. 4563-4602, 2023.
PELLEGRINI, F. R.; FOGLIATTO, F. S. Passos para Implantação de Sistemas de Previsão de Demanda - Técnicas e Estudo de Caso. Produção, 11, 1, 2001.
QIAN, Z. et al. A review and discussion of decomposition-based hybrid models for wind energy forecasting applications. Applied Energy, v. 235, p. 939-953, 2019.
RIBEIRO, M. H. D. M. Variational mode decomposition and bagging extreme learning machine with multi-objective optimization for wind power forecasting. Applied Intelligence, v. 54, p. 3119-3134, 2024.
SHI, X. WANG, J. ZHANG, B. A fuzzy time series forecasting model with both accuracy and interpretability is used to forecast wind power. Applied Energy, v. 335, 122015, 2024.
SOUSA, A. R. D. S. et al. ANÁLISE DE SÉRIES TEMPORAIS. Porto Alegre: SAGAH, 2021.
XIONG, J. et al. A dual-scale deep learning model based on ELM-BiLSTM and improved reptile search algorithm for wind power prediction. Energy, v. 266, 126419, 2023.
YUZGEC, U. DOKUR, E. BALCIC, M. A novel hybrid model based on Empirical Mode Decomposition and Echo State Network for wind power forecasting. Energy, v. 300, 131546, 2024.
WANG, H. et al. A novel multi-layer stacking ensemble wind power prediction model under Tensorflow deep learning framework considering feature enhancement and data hierarchy processing. Energy, v. 286, 129409, 2024.
WANG, J. et al. A novel wind power prediction model improved with feature enhancement and autoregressive error compensation. Journal of Cleaner Production, v. 420, 138386, 2023.
Wang, J. TANG, T. D. JIANG, W. Y. A deterministic and probabilistic hybrid model for wind power forecasting based improved feature screening and optimal Gaussian mixed kernel function. Expert Systems with Applications, v. 251, 123965, 2024.
WU, Z. et al. Explainable temporal dependence in multi-step wind power forecast via decomposition based chain echo state networks. Energy, v. 270, 126906, 2023.
YANG, W. et al. Hybrid wind energy forecasting and analysis system based on divide and conquer scheme: A case study in China. Journal of Cleaner Production, v. 222, p. 942-959, 2019.
ZHANG, D. et al. A novel spatio-temporal wind speed forecasting method based on the microscale meteorological model and a hybrid deep learning model. Energy, v. 288, 129823, 2024.
ZHANG, Y. et al. Ensemble optimization approach based on hybrid mode decomposition and intelligent technology for wind power prediction system. Energy, v. 292, 130492, 2024.
ZHENG, J. et al. A hybrid framework for forecasting power generation of multiple renewable energy sources. Renewable and Sustainable Energy Reviews, v. 172, 110346, 2023.
Publicado
Como Citar
Edição
Seção
Licença
Copyright (c) 2026 Revista Produção Online
Este trabalho está licenciado sob uma licença Creative Commons Attribution 4.0 International License.
A Revista se reserva no direito de efetuar, no artigo publicado, alterações de ordem normativa, ortográfica e gramatical, com vistas a manter o padrão culto da língua, respeitando, porém, o estilo dos autores.
A obra publicada é de inteira responsabilidade do(s) autor(es), cabendo à Revista Produção Online apenas a avaliação da obra, na qualidade de veículo de publicação científica. A Revista Produção Online não se responsabiliza por eventuais violações à Lei nº 9.610/1998, Lei de Direito Autoral.
A revista Produção Online permite que o autor detenha o copyright dos artigos aceitos para publicação, sem restrições.
Esta obra está licenciada sob uma Licença Creative Commons.
