Abstract
This paper deals with scheduling the operations in systems with storage modeled as a mixed integer nonlinear program (MINLP). Due to time interdependency induced by storage, discrete control, and nonlinear operational conditions, computing even a feasible solution may require an unaffordable computational burden. We exploit a property common to a broad class of these problems to devise a decomposition algorithm related to alternating direction methods, which progressively adjusts the operations to the storage state profile. We also design a deep learning model to predict the continuous storage states to start the algorithm instead of the discrete decisions, as commonly done in the literature. This enables search diversification through a multi-start mechanism and prediction using scaling in the absence of a training set. Numerical experiments on the pump scheduling problem in water networks show the effectiveness of this hybrid learning/decomposition algorithm in computing near-optimal strict-feasible solutions in more reasonable times than other approaches.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Bonvin, G., Demassey, S.: Extended linear formulation of the pump scheduling problem in water distribution networks. In: 9th International Network Optimization Conference, pp. 13–18 (2019)
Bonvin, G., Demassey, S., Lodi, A.: Pump scheduling in drinking water distribution networks with an LP/NLP-based B &B. Optim. Engin. 22, 1275–1313 (2021)
Borovykh, A., Bohte, S., Oosterlee, C.W.: Conditional time series forecasting with convolutional neural networks. preprint: arXiv:1703.04691 (2017)
Demassey, S., Sessa, V., Tavakoli, A.: Strengthening mathematical models for pump scheduling in water distribution. In: 14th International Conference on Applied Energy (2022)
Ding, J.Y., et al.: Accelerating primal solution findings for mixed integer programs based on solution prediction. In: AAAI Conference on Artificial Intelligence, vol. 34, pp. 1452–1459 (2020)
Gal, Y., Ghahramani, Z.: Dropout as a Bayesian approximation: Representing model uncertainty in deep learning. In: 33rd International Conference Machine Learning, vol. 48, pp. 1050–1059 (2016)
Geißler, B., Morsi, A., Schewe, L., Schmidt, M.: Penalty alternating direction methods for mixed-integer optimization: a new view on feasibility pumps. SIAM J. Optim. 27(3), 1611–1636 (2017)
Ghaddar, B., Naoum-Sawaya, J., Kishimoto, A., Taheri, N., Eck, B.: A Lagrangian decomposition approach for the pump scheduling problem in water networks. Eur. J. Oper. Res. 241(2), 490–501 (2015)
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016). http://www.deeplearningbook.org
Gorski, J., Pfeuffer, F., Klamroth, K.: Biconvex sets and optimization with biconvex functions: a survey and extensions. Math. Meth. Oper. Res. 66, 373–407 (2007)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. preprint: arXiv:1412.6980 (2014)
Kleinert, T., Schmidt, M.: Computing feasible points of bilevel problems with a penalty alternating direction method. INFORMS J. Comput. 33, 198–215 (2020)
Kool, W., Van Hoof, H., Welling, M.: Attention, learn to solve routing problems! preprint: arXiv:1803.08475 (2018)
Mackle, G.: Application of genetic algorithms to pump scheduling for water supply. In: International Conference on Genetic Algorithms in Engineering Systems: Innovations and Applications, pp. 400–405 (1995)
Naoum-Sawaya, J., Ghaddar, B., Arandia, E., Eck, B.: Simulation-optimization approaches for water pump scheduling and pipe replacement problems. Eur. J. Oper. Res. 246, 293–306 (2015)
Rockafellar, R.T.: Network Flows and Monotropic Optimization. Athena Scientific, Nashua (1999)
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)
Todini, E., Pilati, S.: A gradient algorithm for the analysis of pipe networks. In: Computer Applications in Water Supply, vol. 1. Research Studies Press Ltd. (1988)
Van Zyl, J.E., Savic, D.A., Walters, G.A.: Operational optimization of water distribution systems using a hybrid genetic algorithm. J. Water Res. Plan. Manage. 130(2), 160–170 (2004)
Wang, Y., Yin, W., Zeng, J.: Global convergence of ADMM in nonconvex Nonsmooth optimization. J. Sci. Comput. 78, 29–63 (2019)
Acknowledgement
This work is supported by the French government, through the 3IA Côte d’Azur Investments in the Future project managed by the National Research Agency (ANR) with the reference number ANR-19-P3IA-0002.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Demassey, S., Sessa, V., Tavakoli, A. (2024). Alternating Direction Method and Deep Learning for Discrete Control with Storage. In: Basu, A., Mahjoub, A.R., Salazar González, J.J. (eds) Combinatorial Optimization. ISCO 2024. Lecture Notes in Computer Science, vol 14594. Springer, Cham. https://doi.org/10.1007/978-3-031-60924-4_7
Download citation
DOI: https://doi.org/10.1007/978-3-031-60924-4_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-60923-7
Online ISBN: 978-3-031-60924-4
eBook Packages: Computer ScienceComputer Science (R0)