Day-ahead energy production in small hydropower plants: uncertainty-aware forecasts through effective coupling of knowledge and data

K.-K. Drakaki, G.-K. Sakki, I. Tsoukalas, P. Kossieris, and A. Efstratiadis, Day-ahead energy production in small hydropower plants: uncertainty-aware forecasts through effective coupling of knowledge and data, Advances in Geosciences, 56, 155–162, doi:10.5194/adgeo-56-155-2022, 2022.



Motivated by the challenges induced by the so-called Target Model and the associated changes to the current structure of the energy market, we revisit the problem of day-ahead prediction of power production from Small Hydropower Plants (SHPPs) without storage capacity. Using as an example a typical run-of-river SHPP in Western Greece, we test alternative forecasting schemes (from regression-based to machine learning) that take advantage of different levels of information. In this respect, we investigate whether it is preferable to use as predictor the known energy production of previous days, or to predict the day-ahead inflows and next estimate the resulting energy production via simulation. Our analyses indicate that the second approach becomes clearly more advantageous when the expert’s knowledge about the hydrological regime and the technical characteristics of the SHPP is incorporated within the model training procedure. Beyond these, we also focus on the predictive uncertainty that characterize such forecasts, with overarching objective to move beyond the standard, yet risky, point forecasting methods, providing a single expected value of power production. Finally, we discuss the use of the proposed forecasting procedure under uncertainty in the real-world electricity market.

PDF Full text (217 KB)

See also:


The simulation and forecasting models have been developed in the R environment and they are available at:

Our works referenced by this work:

1. A. Efstratiadis, A. Tegos, A. Varveris, and D. Koutsoyiannis, Assessment of environmental flows under limited data availability – Case study of the Acheloos River, Greece, Hydrological Sciences Journal, 59 (3-4), 731–750, doi:10.1080/02626667.2013.804625, 2014.
2. A. Efstratiadis, I. Nalbantis, and D. Koutsoyiannis, Hydrological modelling of temporally-varying catchments: Facets of change and the value of information, Hydrological Sciences Journal, 60 (7-8), 1438–1461, doi:10.1080/02626667.2014.982123, 2015.
3. I. Tsoukalas, A. Efstratiadis, and C. Makropoulos, Stochastic periodic autoregressive to anything (SPARTA): Modelling and simulation of cyclostationary processes with arbitrary marginal distributions, Water Resources Research, 54 (1), 161–185, WRCR23047, doi:10.1002/2017WR021394, 2018.
4. I. Tsoukalas, Modelling and simulation of non-Gaussian stochastic processes for optimization of water-systems under uncertainty, PhD thesis, 339 pages, Department of Water Resources and Environmental Engineering – National Technical University of Athens, December 2018.
5. P. Kossieris, I. Tsoukalas, C. Makropoulos, and D. Savic, Simulating marginal and dependence behaviour of water demand processes at any fine time scale, Water, 11 (5), 885, doi:10.3390/w11050885, 2019.
6. G. Papacharalampous, H. Tyralis, A. Langousis, A. W. Jayawardena, B. Sivakumar, N. Mamassis, A. Montanari, and D. Koutsoyiannis, Probabilistic hydrological post-processing at scale: Why and how to apply machine-learning quantile regression algorithms, Water, doi:10.3390/w11102126, 2019.
7. I. Tsoukalas, P. Kossieris, and C. Makropoulos, Simulation of non-Gaussian correlated random variables, stochastic processes and random fields: Introducing the anySim R-Package for environmental applications and beyond, Water, 12 (6), 1645, doi:10.3390/w12061645, 2020.
8. G.-K. Sakki, I. Tsoukalas, P. Kossieris, and A. Efstratiadis, A dilemma of small hydropower plants: Design with uncertainty or uncertainty within design?, EGU General Assembly 2021, online, EGU21-2398, doi:10.5194/egusphere-egu21-2398, European Geosciences Union, 2021.
9. G.-K. Sakki, I. Tsoukalas, and A. Efstratiadis, A reverse engineering approach across small hydropower plants: a hidden treasure of hydrological data?, Hydrological Sciences Journal, 67 (1), 94–106, doi:10.1080/02626667.2021.2000992, 2022.

Our works that reference this work:

1. V.-E. K. Sarantopoulou, G. J. Tsekouras, A. D. Salis, D. E. Papantonis, V. Riziotis, G. Caralis, K.-K. Drakaki, G.-K. Sakki, A. Efstratiadis, and K. X. Soulis, Optimal operation of a run-of-river small hydropower plant with two hydro-turbines, 2022 7th International Conference on Mathematics and Computers in Sciences and Industry (MCSI), Marathon Beach, Athens, 80–88, doi:10.1109/MCSI55933.2022.00020, 2022.
2. G.-K. Sakki, I. Tsoukalas, P. Kossieris, C. Makropoulos, and A. Efstratiadis, Stochastic simulation-optimisation framework for the design and assessment of renewable energy systems under uncertainty, Renewable and Sustainable Energy Reviews, 168, 112886, doi:10.1016/j.rser.2022.112886, 2022.

Other works that reference this work (this list might be obsolete):

1. Krechowicz, A., M. Krechowicz, and K. Poczeta, Machine learning approaches to predict electricity production from renewable energy sources, Energies, 15(23), 9146, doi:10.3390/en15239146, 2022.
2. Ghobadi, F., and D. Kang, Application of machine learning in water resources management: A systematic literature review, Water, 15(4), 620, doi:10.3390/w15040620, 2023.
3. Chen, B., Y. Long, H. Wei, B. Li, Y. Zhang, W. Deng, and C. Li, A weak-coupling flow-power forecasting method for small hydropower station group, International Journal of Energy Research, 2023, 1214269, doi:10.1155/2023/1214269, 2023.
4. Karakuş, M. O., Impact of climatic factors on the prediction of hydroelectric power generation: A deep CNN-SVR approach, Geocarto International, 38(1), doi:10.1080/10106049.2023.2253203, 2023.
5. #Chauhan, R., N. Batra, S. Goyal, and A. Kaur, Optimizing water resources with IoT and ML: A water management system, Innovations in Machine Learning and IoT for Water Management, A. Kumar, A. Lal Srivastav, A. Kumar Dubey, V. Dutt, N. Vyas (editors), Chapter 4, 94-109, doi:10.4018/979-8-3693-1194-3.ch005, 2024.
6. Sahin, M. E., and M. Ozbay Karakus, Smart hydropower management: utilizing machine learning and deep learning method to enhance dam’s energy generation efficiency, Neural Computing & Applications, doi:10.1007/s00521-024-09613-1, 2024.
7. Lincaru, C., A. Grigorescu, and H. Dincer, Parabolic modeling forecasts of space and time european hydropower production, Processes, 12, 1098, doi:10.3390/pr12061098, 2024.

Tagged under: Hydroinformatics, Renewable energy, Students' works, Water and energy