Abstract
This paper demonstrates how deep learning can be used to find optimal reservoir operating policies in hydropower river systems. The method that we propose is based on the implicit stochastic optimization (ISO) framework, using direct policy search methods combined with deep neural networks (DNN). The findings from a real-world two-reservoir hydropower system in southern Norway suggest that DNNs can learn how to map input (price, inflow, starting reservoir levels) to the optimal production pattern directly. Due to the speed of evaluating the DNN, this approach is from an operational standpoint computationally inexpensive and may potentially address the long-standing problem of high dimensionality in hydropower optimization. Further on, our method may be used as an input for decision-theoretic planning, suggesting the policy that will give the highest expected profit. The approach also permits for a broader use of pre-trained neural networks in historical reanalysis of production patterns and studies of climate change effects.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Labadie, J.W.: Optimal operation of multi-reservoir systems: state-of-the-art review. J. Water Resour. Plann. Manag., 93 (2004). https://doi.org/10.1061/(ASCE)0733-9496(2004)130:2(93)
Yoo, J.-H.: Maximization of hydropower generation through the application of a linear programming model. J. Hydrol. 376, 182–187. https://doi.org/10.1016/j.jhydrol.2009.07.026
Belsnes, M.M., Wolfgang, O., Follestad, T., Aasgård, E.K.: Applying successive linear programming for stochastic short-term hydropower optimization. Electr. Power Syst. Res. 130, 167–180 (2016)
Moosavian, S.A.A., Ghaffari, A., Salimi, A.: Sequential quadratic programming and analytic hierarchy process for nonlinear multiobjective optimization of a hydropower network. In: Optimal Control Applications and Methods. https://doi.org/10.1002/oca.909
Jothiprakash, V., Arunkumar, R.: Multi-reservoir optimization for hydropower production using NLP technique. KSCE J. Civ. Eng. 18(1), 344–354 (2014)
Allen, B., Bridgeman, R.G.: Dynamic programming in hydropower scheduling. J. Water Resour. Plann. Manag., ASCE. https://doi.org/10.1061/(ASCE)0733-9496(1986)112:3(339)
Zhao, T., Zhao, J., Yang, D.: Improved dynamic programming for hydropower reservoir operation. J. Water Resour. Plann. Manag. 140(3), 365–374 (2012)
Garousi-Nejad, I., Bozorg-Haddad, O., Loáiciga, H.: Modified firefly algorithm for solving multi-reservoir operation in continuous and discrete domains. J. Water Resour. Plann. Manag. 142(9) (2016). https://doi.org/10.1061/(ASCE)WR.1943-5452.0000644
DeRigo, D., Rizzoli, A.E., Soncini-Sessa, R., Weber, E., Zenesi, P.: Neuro-dynamic programming for the efficient management of reservoir networks. In: Proceedings of MODSIM 2001 International Congress on Modelling and Simulation, Vol. 4, pp. 1949–1954. Modelling and Simulation Society of Australia and New Zealand, December 2001. ISBN 0-867405252
Lee, J.H., Labadie, J.W.: Stochastic optimization of multi-reservoir systems via reinforcement learning. Water Resour. Res. 43, W11408 (2007). https://doi.org/10.1029/2006WR005627
Castelletti, A., Galelli, S., Restelli, M., Soncini-Sessa, R.: Tree-based reinforcement learning for optimal water reservoir operation. Water Resour. Res. 46, W09507 (2010). https://doi.org/10.1029/2009WR008898
Loucks, D.P.: Implicit stochastic optimization and simulation. In: Marco, J.B., Harboe, R., Salas, J.D. (eds.) Stochastic Hydrology and its Use in Water Resources Systems Simulation and Optimization. NATO ASI Series (Series E: Applied Sciences), vol. 237. Springer, Dordrecht (1993). https://doi.org/10.1007/978-94-011-1697-8_19
Dariane, A.B., Moradi, A.M.: Comparative analysis of evolving artificial neural network and reinforcement learning in stochastic optimization of multi-reservoir systems. Hydrol. Sci. J. 61(6), 1141–1156 (2016). https://doi.org/10.1080/02626667.2014.986485
Sangiorgio, M., Guariso, G.: NN-based implicit stochastic optimization of multi-reservoir systems management. Water 10, 303 (2018)
Azizipour, M., Ghalenoei, V., Afshar, M.H., Solis, S.S.: Optimal operation of hydropower reservoir systems using weed optimization algorithm. Water Resour. Manag. 30, 3995–4009 (2016). https://doi.org/10.1007/s11269-016-1407-6
Russel, S., Norvig, P.: Artificial Intelligence: A modern Approach, 3rd edn., pp. 131 or 589. Prentice Hall. ISBN 13 978-0-13-604259-4
Keras documentation. https://keras.io/optimizers/
Acknowledgements
This research has been supported by Agder Energi, the Norwegian Research Council (ENERGIX program), and the University of Agder. We also thank Jarand Roeynstrand at Agder Energi for input on an early version of this article.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Matheussen, B.V., Granmo, OC., Sharma, J. (2019). Hydropower Optimization Using Deep Learning. In: Wotawa, F., Friedrich, G., Pill, I., Koitz-Hristov, R., Ali, M. (eds) Advances and Trends in Artificial Intelligence. From Theory to Practice. IEA/AIE 2019. Lecture Notes in Computer Science(), vol 11606. Springer, Cham. https://doi.org/10.1007/978-3-030-22999-3_11
Download citation
DOI: https://doi.org/10.1007/978-3-030-22999-3_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-22998-6
Online ISBN: 978-3-030-22999-3
eBook Packages: Computer ScienceComputer Science (R0)