Analysis of Ensembles Applied to Time Series Forecasting of Hydroelectric Dams
Resumo
Context: Dams are essential for electricity generation in Brazil. Given the countrys vast territorial extent, it is crucial to optimize the use of its energy sources, particularly the hydrological potential of rivers. Problem: Flow forecasting in river basins is critical for the safety and efficiency of operations. Underestimation errors can increase the risk of dam overflow and failure, while overestimations compromise water storage, affecting supply and power generation during dry periods. Solution: This study proposes a dynamic selection method of machine learning models to achieve more accurate and stable flow forecasts. IS Theory: The research is based on Dynamic Capabilities Theory, emphasizing the ability for internal reconfiguration to address complex issues such as time series forecasting. Method: Data were initially normalized and temporally adjusted to ensure consistency. A diverse set of base models was selected based on their intrinsic characteristics, then integrated into a dynamic ensemble framework. Performance was evaluated using MAPE and RMSE metrics, allowing comparative analysis between the proposed dynamic ensemble and traditional deep learning models. Results: The dynamic selection approach showed significant improvements, achieving errors of 23.88 (MAPE) and 852.97 (RMSE), outperforming traditional and deep learning models. Contributions and Impact in the IS Field: This work demonstrates that dynamic model selection is a superior and promising approach compared to isolated model use, offering a significant advancement for flow forecasting in dam systems and contributing to more efficient water resource management in the Brazilian context.
Palavras-chave:
Time series forecast, Ensembles, Dynamic selection
Referências
Dihia Boulegane, Albert Bifet, and Giyyarpuram Madhusudan. 2019. Arbitrated Dynamic Ensemble with Abstaining for Time-Series Forecasting on Data Streams. In 2019 IEEE International Conference on Big Data (Big Data). 1040–1045. DOI: 10.1109/BigData47090.2019.9005541
Zezhou Chen and Irena Koprinska. 2020. Ensemble Methods for Solar Power Forecasting. In 2020 International Joint Conference on Neural Networks (IJCNN). 1–8. DOI: 10.1109/IJCNN48605.2020.9206713
Douglas Vieira Do Nascimento, Rafael Teixeira Sousa, Diogo Fernandes Costa Silva, Daniel Do Prado Pagotto, Clarimar José Coelho, and Arlindo Rodrigues Galvão Filho. 2023. Live Birth Forecasting in Brazillian Health Regions with Tree-based Machine Learning Models. In 2023 IEEE 36th International Symposium on Computer-Based Medical Systems (CBMS). 85–90. DOI: 10.1109/CBMS58004.2023.00197
Empresa de Pesquisa Energética (EPE). 2024. Matriz Energética e Elétrica. [link] Accessed: November 2024.
Hansika Hewamalage, Christoph Bergmeir, and Kasun Bandara. 2021. Recurrent Neural Networks for Time Series Forecasting: Current status and future directions. International Journal of Forecasting 37, 1 (2021), 388–427. DOI: 10.1016/j.ijforecast.2020.06.008
Rob J. Hyndman and George Athanasopoulos. 2018. Forecasting: Principles and Practice (2nd ed.). OTexts. Available at [link].
Haseeb Javed, Hafiz Abdul Muqeet, Amirhossein Danesh, Atiq Ur Rehman, Tahir Javed, and Amine Bermak. 2024. Impact of AI and Dynamic Ensemble Techniques in Enhancing Healthcare Services: Opportunities and Ethical Challenges. IEEE Access 12 (2024), 141064–141087. DOI: 10.1109/ACCESS.2024.3443812
Bryan Lim and Stefan Zohren. 2021. Time-series forecasting with deep learning: a survey. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences 379, 2194 (2021), 20200209. DOI: 10.1098/rsta.2020.0209 arXiv: [link]
Diego de Souza Martins, Heder Soares Bernardino, and Luciana Conceição Dias Campos. 2024. Short-term Forecasting of the Wind Power Generation of Brazilian Power Stations Using an LSTM Model. In Proceedings of the 20th Brazilian Symposium on Information Systems (Juiz de Fora, Brazil) (SBSI ’24). Association for Computing Machinery, New York, NY, USA, Article 21, 9 pages. DOI: 10.1145/3658271.3658292
Kasun Mendis, Manjusri Wickramasinghe, and Pasindu Marasinghe. 2024. Multivariate Time Series Forecasting: A Review. In Proceedings of the 2024 2nd Asia Conference on Computer Vision, Image Processing and Pattern Recognition (Xiamen, China) (CVIPPR ’24). Association for Computing Machinery, New York, NY, USA, Article 58, 9 pages. DOI: 10.1145/3663976.3664241
Marcos Alberto Mochinski, Jean Paul Barddal, and Fabrício Enembreck. 2020. Improving Multiple Time Series Forecasting with Data Stream Mining Algorithms. In 2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC). 1060–1067. DOI: 10.1109/SMC42975.2020.9283059
Thiago J. M. Moura, George D. C. Cavalcanti, and Luiz S. Oliveira. 2021. On the Evaluation of Competence Measures for Time Series Forecasting. In 2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC). 1527–1532. DOI: 10.1109/SMC52423.2021.9659086
Oksana Mulesa, Anatoliy Batyuk, Fedir Geche, Olena Melnyk, Mykola Palinchak, and Tamara Radivilova. 2021. Information technology for time series forecasting based on the evolutionary method of the forecasting scheme synthesis. In 2021 IEEE 16th International Conference on Computer Sciences and Information Technologies (CSIT), Vol. 2. 258–261. DOI: 10.1109/CSIT52700.2021.9648639
Bencharef Omar, Bousbaa Zineb, Aida Cortés Jofré, and Daniel González Cortés. 2018. A Comparative Study of Machine Learning Algorithms for Financial Data Prediction. In 2018 International Symposium on Advanced Electrical and Communication Technologies (ISAECT). 1–5. DOI: 10.1109/ISAECT.2018.8618774
Zuokun Ouyang, Philippe Ravier, and Meryem Jabloun. 2022. Are Deep Learning Models Practically Good as Promised? A Strategic Comparison of Deep Learning Models for Time Series Forecasting. In 2022 30th European Signal Processing Conference (EUSIPCO). 1477–1481. DOI: 10.23919/EUSIPCO55093.2022.9909926
Yi Peng, He Kang, and Yanan Chen. 2021. A Research on Stock Index Prediction Based on Multiple Linear Regression and ELM Neural Network. In 2021 6th International Conference on Intelligent Computing and Signal Processing (ICSP). 254–259. DOI: 10.1109/ICSP51882.2021.9408840
Eraylson G. Silva, Paulo S. G. De Mattos Neto, and George D. C. Cavalcanti. 2021. A Dynamic Predictor Selection Method Based on Recent Temporal Windows for Time Series Forecasting. IEEE Access 9 (2021), 108466–108479. DOI: 10.1109/ACCESS.2021.3101741
Taiane Silva Barbosa and Artur Henrique Kronbauer. 2019. Panorama of Researches Related to the Application of Virtual Reality in the Health Area in SVR. In 2019 21st Symposium on Virtual and Augmented Reality (SVR). 69–76. DOI: 10.1109/SVR.2019.00027
Simran and Jaspreet Singh. 2023. A Comprehensive Survey of PSO-ACO Optimization and Swarm Intelligence in Healthcare: Implications for Medical Image Analysis and Disease Surveillance. In 2023 3rd Asian Conference on Innovation in Technology (ASIANCON). 1–6. DOI: 10.1109/ASIANCON58793.2023.10270025
Nuno Verdelho Trindade, Pedro Leitão, Daniel Gonçalves, Sérgio Oliveira, and Alfredo Ferreira. 2023. Immersive Situated Analysis of Dams’ Behavior. In 2023 International Conference on Graphics and Interaction (ICGI). 1–8. DOI: 10.1109/ICGI60907.2023.10452725
Hubert Truchan, Christian Kalfar, and Zahra Ahmadi. 2024. LTBoost: Boosted Hybrids of Ensemble Linear and Gradient Algorithms for the Long-term Time Series Forecasting. In Proceedings of the 33rd ACM International Conference on Information and Knowledge Management (Boise, ID, USA) (CIKM ’24). Association for Computing Machinery, New York, NY, USA, 2271–2281. DOI: 10.1145/3627673.3679527
Zheng Wang, Irena Koprinska, Alicia Troncoso, and Francisco Martínez-Álvarez. 2018. Static and Dynamic Ensembles of Neural Networks for Solar Power Forecasting. In 2018 International Joint Conference on Neural Networks (IJCNN). 1–8. DOI: 10.1109/IJCNN.2018.8489231
Dong Wu, Xinyi Lin, Shivam Gupta, and Arpan Kumar Kar. 2024. Big Data Analytics Capability,Dynamic Capability, and Firm Performance: The Moderating Effect of IT–Business Strategic Alignment. IEEE Transactions on Engineering Management 71 (2024), 11638–11651. DOI: 10.1109/TEM.2024.3429648
Songting Xing and Yuansheng Lou. 2019. Hydrological time series forecast by ARIMA+PSO-RBF combined model based on wavelet transform. In 2019 IEEE 3rd Information Technology, Networking, Electronic and Automation Control Conference (ITNEC). 1711–1715. DOI: 10.1109/ITNEC.2019.8729367
Shuhan Zhong, Sizhe Song,Weipeng Zhuo, Guanyao Li, Yang Liu, and S.-H. Gary Chan. 2024. A Multi-Scale Decomposition MLP-Mixer for Time Series Analysis. Proc. VLDB Endow. 17, 7 (May 2024), 1723–1736. DOI: 10.14778/3654621.3654637
Zezhou Chen and Irena Koprinska. 2020. Ensemble Methods for Solar Power Forecasting. In 2020 International Joint Conference on Neural Networks (IJCNN). 1–8. DOI: 10.1109/IJCNN48605.2020.9206713
Douglas Vieira Do Nascimento, Rafael Teixeira Sousa, Diogo Fernandes Costa Silva, Daniel Do Prado Pagotto, Clarimar José Coelho, and Arlindo Rodrigues Galvão Filho. 2023. Live Birth Forecasting in Brazillian Health Regions with Tree-based Machine Learning Models. In 2023 IEEE 36th International Symposium on Computer-Based Medical Systems (CBMS). 85–90. DOI: 10.1109/CBMS58004.2023.00197
Empresa de Pesquisa Energética (EPE). 2024. Matriz Energética e Elétrica. [link] Accessed: November 2024.
Hansika Hewamalage, Christoph Bergmeir, and Kasun Bandara. 2021. Recurrent Neural Networks for Time Series Forecasting: Current status and future directions. International Journal of Forecasting 37, 1 (2021), 388–427. DOI: 10.1016/j.ijforecast.2020.06.008
Rob J. Hyndman and George Athanasopoulos. 2018. Forecasting: Principles and Practice (2nd ed.). OTexts. Available at [link].
Haseeb Javed, Hafiz Abdul Muqeet, Amirhossein Danesh, Atiq Ur Rehman, Tahir Javed, and Amine Bermak. 2024. Impact of AI and Dynamic Ensemble Techniques in Enhancing Healthcare Services: Opportunities and Ethical Challenges. IEEE Access 12 (2024), 141064–141087. DOI: 10.1109/ACCESS.2024.3443812
Bryan Lim and Stefan Zohren. 2021. Time-series forecasting with deep learning: a survey. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences 379, 2194 (2021), 20200209. DOI: 10.1098/rsta.2020.0209 arXiv: [link]
Diego de Souza Martins, Heder Soares Bernardino, and Luciana Conceição Dias Campos. 2024. Short-term Forecasting of the Wind Power Generation of Brazilian Power Stations Using an LSTM Model. In Proceedings of the 20th Brazilian Symposium on Information Systems (Juiz de Fora, Brazil) (SBSI ’24). Association for Computing Machinery, New York, NY, USA, Article 21, 9 pages. DOI: 10.1145/3658271.3658292
Kasun Mendis, Manjusri Wickramasinghe, and Pasindu Marasinghe. 2024. Multivariate Time Series Forecasting: A Review. In Proceedings of the 2024 2nd Asia Conference on Computer Vision, Image Processing and Pattern Recognition (Xiamen, China) (CVIPPR ’24). Association for Computing Machinery, New York, NY, USA, Article 58, 9 pages. DOI: 10.1145/3663976.3664241
Marcos Alberto Mochinski, Jean Paul Barddal, and Fabrício Enembreck. 2020. Improving Multiple Time Series Forecasting with Data Stream Mining Algorithms. In 2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC). 1060–1067. DOI: 10.1109/SMC42975.2020.9283059
Thiago J. M. Moura, George D. C. Cavalcanti, and Luiz S. Oliveira. 2021. On the Evaluation of Competence Measures for Time Series Forecasting. In 2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC). 1527–1532. DOI: 10.1109/SMC52423.2021.9659086
Oksana Mulesa, Anatoliy Batyuk, Fedir Geche, Olena Melnyk, Mykola Palinchak, and Tamara Radivilova. 2021. Information technology for time series forecasting based on the evolutionary method of the forecasting scheme synthesis. In 2021 IEEE 16th International Conference on Computer Sciences and Information Technologies (CSIT), Vol. 2. 258–261. DOI: 10.1109/CSIT52700.2021.9648639
Bencharef Omar, Bousbaa Zineb, Aida Cortés Jofré, and Daniel González Cortés. 2018. A Comparative Study of Machine Learning Algorithms for Financial Data Prediction. In 2018 International Symposium on Advanced Electrical and Communication Technologies (ISAECT). 1–5. DOI: 10.1109/ISAECT.2018.8618774
Zuokun Ouyang, Philippe Ravier, and Meryem Jabloun. 2022. Are Deep Learning Models Practically Good as Promised? A Strategic Comparison of Deep Learning Models for Time Series Forecasting. In 2022 30th European Signal Processing Conference (EUSIPCO). 1477–1481. DOI: 10.23919/EUSIPCO55093.2022.9909926
Yi Peng, He Kang, and Yanan Chen. 2021. A Research on Stock Index Prediction Based on Multiple Linear Regression and ELM Neural Network. In 2021 6th International Conference on Intelligent Computing and Signal Processing (ICSP). 254–259. DOI: 10.1109/ICSP51882.2021.9408840
Eraylson G. Silva, Paulo S. G. De Mattos Neto, and George D. C. Cavalcanti. 2021. A Dynamic Predictor Selection Method Based on Recent Temporal Windows for Time Series Forecasting. IEEE Access 9 (2021), 108466–108479. DOI: 10.1109/ACCESS.2021.3101741
Taiane Silva Barbosa and Artur Henrique Kronbauer. 2019. Panorama of Researches Related to the Application of Virtual Reality in the Health Area in SVR. In 2019 21st Symposium on Virtual and Augmented Reality (SVR). 69–76. DOI: 10.1109/SVR.2019.00027
Simran and Jaspreet Singh. 2023. A Comprehensive Survey of PSO-ACO Optimization and Swarm Intelligence in Healthcare: Implications for Medical Image Analysis and Disease Surveillance. In 2023 3rd Asian Conference on Innovation in Technology (ASIANCON). 1–6. DOI: 10.1109/ASIANCON58793.2023.10270025
Nuno Verdelho Trindade, Pedro Leitão, Daniel Gonçalves, Sérgio Oliveira, and Alfredo Ferreira. 2023. Immersive Situated Analysis of Dams’ Behavior. In 2023 International Conference on Graphics and Interaction (ICGI). 1–8. DOI: 10.1109/ICGI60907.2023.10452725
Hubert Truchan, Christian Kalfar, and Zahra Ahmadi. 2024. LTBoost: Boosted Hybrids of Ensemble Linear and Gradient Algorithms for the Long-term Time Series Forecasting. In Proceedings of the 33rd ACM International Conference on Information and Knowledge Management (Boise, ID, USA) (CIKM ’24). Association for Computing Machinery, New York, NY, USA, 2271–2281. DOI: 10.1145/3627673.3679527
Zheng Wang, Irena Koprinska, Alicia Troncoso, and Francisco Martínez-Álvarez. 2018. Static and Dynamic Ensembles of Neural Networks for Solar Power Forecasting. In 2018 International Joint Conference on Neural Networks (IJCNN). 1–8. DOI: 10.1109/IJCNN.2018.8489231
Dong Wu, Xinyi Lin, Shivam Gupta, and Arpan Kumar Kar. 2024. Big Data Analytics Capability,Dynamic Capability, and Firm Performance: The Moderating Effect of IT–Business Strategic Alignment. IEEE Transactions on Engineering Management 71 (2024), 11638–11651. DOI: 10.1109/TEM.2024.3429648
Songting Xing and Yuansheng Lou. 2019. Hydrological time series forecast by ARIMA+PSO-RBF combined model based on wavelet transform. In 2019 IEEE 3rd Information Technology, Networking, Electronic and Automation Control Conference (ITNEC). 1711–1715. DOI: 10.1109/ITNEC.2019.8729367
Shuhan Zhong, Sizhe Song,Weipeng Zhuo, Guanyao Li, Yang Liu, and S.-H. Gary Chan. 2024. A Multi-Scale Decomposition MLP-Mixer for Time Series Analysis. Proc. VLDB Endow. 17, 7 (May 2024), 1723–1736. DOI: 10.14778/3654621.3654637
Publicado
19/05/2025
Como Citar
CAVALCANTI, Jheymesson Apolinário; FAGUNDES, Roberta Andrade de Araújo.
Analysis of Ensembles Applied to Time Series Forecasting of Hydroelectric Dams. In: SIMPÓSIO BRASILEIRO DE SISTEMAS DE INFORMAÇÃO (SBSI), 21. , 2025, Recife/PE.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 182-190.
DOI: https://doi.org/10.5753/sbsi.2025.246412.
