Scholarly record
PROGRAMMING TOOLS FOR INFLOWS FORECASTING IN HYDROPOWER RESERVOIRS
Abstract
Within the framework of the iAMP-Hydro EU project, two dedicated work packages address the challenges of inflow and power forecasting for both run-of-river hydropower plants and large hydropower reservoirs. These tasks aim to improve short-term and medium-term operational planning by integrating advanced data-driven techniques into hydrological forecasting chains. Five initial validation sites, three located in Spain and two in Greece, were analyzed using a suite of statistical and machine learning techniques, including ARIMA, LSTM, and Random Forest (RF) models implemented in MATLAB. The first results demonstrated satisfactory forecasting performance for regulated basins, particularly for the fourth and fifth reservoirs of the five-reservoir cascade system along the Aliakmon River in Greece. When extending the workflow to natural inflows and incorporating the first reservoir of the cascade as a new validation site, the modelling framework revealed a significant improvement in simulated inflows, emphasizing the importance of upstream regulation effects in data-driven forecasting. To further strengthen the robustness and reliability of the methodology, a sixth validation site, corresponding to the upstream (first) reservoir, was subsequently integrated into the project s evaluation structure. This paper presents the overall methodological framework, data preprocessing strategies, selected modelling tools, and preliminary forecasting results for the three Greek validation sites: Asomata, Agia Varvara, and Ilarion on the Aliakmon River. The study highlights the potential of statistical and machine learning approaches to support hydropower optimization within interconnected and regulated river systems.
Publication Impact Profile
Publication details
References7
Latif S. D., Ahmed A. N., A review of deep learning and machine learning techniques for hydrological inflow forecasting, Environment, Development and Sustainability, vol. 25, 12189 12216, 2023. DOI: 10.1007/s10668-023-03131-1
Neagoe A., Tica E.-I., Vu?a L.-I., Nedelcu O., Dumitran G.-E., Popa B., Hybrid LSTM-ARIMA Model for Improving Multi-Step Inflow Forecasting in a Reservoir, Water, vol. 17/issue 21, 3051, 2025. DOI: 10.3390/w17213051
Yousefi M., Wang J., H ivik.F., Rajasekharan J., Wierling A.H., Hossein Farahmand H., Arghandeh R., Short-term inflow forecasting in a dam-regulated river in Southwest Norway using causal variational mode decomposition, Scientific Reports, vol. 13, 7016, 2023. DOI: 10.1038/s41598-023-34133-8
Zhao X, Wang H., Bai M., Xu Y., Dong S., Rao H., Ming W., A Comprehensive Review of Methods for Hydrological Forecasting Based on Deep Learning, Water, vol. 16,1407, 2024. DOI: 10.3390/w16101407
Liu C., Xu J., Li X., Yu Z., Wu J., Water resource forecasting with machine learning and deep learning: A scientometric analysis, Artificial Intelligence in Geosciences, vol. 5,100084, 2024. DOI: 10.1016/j.aiig.2024.100084
Singh A.D., Singh A., Optimal Reservoir Operations using Long Short-Term Memory Network, Preprint arXiv:2109.04255, 2021.
Frysali D., Mallios Z., Theodossiou N., Hydrologic modeling of the Aliakmon River in Greece using HEC HMS and open data, Euro-Mediterranean Journal for Environmental Integration, 8:539 555, 2023, DOI: 10.1007/s41207-023-00374-2.
View or Download full articleAccess options
SWS access login
Login as SWS Scientific CommitteeLogin as SWS Scientific PartnerLogin as SWS AuthorAuthors and approved SWS contributors will read and export their own linked papers after identity matching by SWS profile, email and SGEM GlobalID.
For librarian assistance: [email protected]
Purchase Instant Access
- Article can be downloaded after successful payment.
- Article may be used according to SWS library access terms.
- Article cannot be redistributed.