Abstract
Learning Automata (LA) is a powerful approach for solving complex, non-linear and stochastic optimisation problems. However, existing solutions struggle with high-dimensional problems due to slow convergence, arguably caused by the global nature of feedback. In this paper we introduce a novel Learning Automata (LA) scheme to attack this challenge. The scheme is based on a parallel form of Local Contribution Sampling (LCS), which means that the LA receive individually directed feedback, designed to speed up convergence. Furthermore, our scheme is highly decentralized, allowing parallel execution on GPU architectures. To demonstrate the power of our scheme, the LA LCS is applied to hydropower production optimisation, involving several particularly challenging optimisation scenarios. The experimental results show that LA LCS is able to quickly find optimal solutions for a wide range of problem configurations. Our results also demonstrate that local directed feedback provides significantly faster convergence than global feedback. These results lead us to conclude that LA LCS holds great promise for solving complex, non-linear and stochastic optimisation problems, opening up for improved performance in a number of real-world applications.
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
Notes
- 1.
Tail-water: water downstream from the turbine is called tail-water.
References
Thathachar, M.A.L., Sastry, P.S.: Varieties of learning automata: an overview. IEEE Trans. Syst. Man Cybern. Part B (Cybern.) 32(6), 711–722 (2002)
Archibald, T.W., McKinnon, K.I.M., Thomas, L.C.: An aggregate stochastic dynamic programming model of multireservoir systems. Water Resour. Res. 33(2), 333–340 (1997)
Azizipour, M., Ghalenoei, V., Afshar, M.H., Solis, S.S.: Optimal operation of hydropower reservoir systems using weed optimization algorithm. Water Resour. Manag. 30(11), 3995–4009 (2016)
Arnold, E., Tatjewski, P., Wołochowicz, P.: Two methods for large-scale nonlinear optimization and their comparison on a case study of hydropower optimization. J. Optim. Theory Appl. 81, 221–248 (1994)
Crawley, P.D., Dandy, G.C.: Optimal operation of multiple-reservoir system. J. Water Resour. Plan. Manage. 119(1), 1–17 (1993)
Pereira, M.V.F.: Optimal stochastic operations scheduling of large hydroelectric systems. Int. J. Electr. Power Energy Syst. 11(3), 161–169 (1989)
Pereira, M.V.F., Pinto, L.M.V.G.: Stochastic optimization of a multireservoir hydroelectric system: a decomposition approach. Water Resour. Res. 21(6), 779–792 (1985)
Bellman, R.: Dynamic Programming, vol. 1, no. 2, p. 3. Princeton University Press, Princeton (1957)
Granmo, O.-C., Bouhmala, N.: Solving the satisfiability problem using finite learning automata. IJCSA 4(3), 15–29 (2007)
Oommen, B.J., de St Croix, E.V.: Graph partitioning using learning automata. IEEE Trans. Comput. 45(2), 195–208 (1996)
Granmo, O.-C., Oommen, B.J.: Solving stochastic nonlinear resource allocation problems using a hierarchy of twofold resource allocation automata. IEEE Trans. Comput. 59(4), 545–560 (2010)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Fidje, J.T., Haraldseid, C.K., Granmo, OC., Goodwin, M., Matheussen, B.V. (2017). A Learning Automata Local Contribution Sampling Applied to Hydropower Production Optimisation. In: Bramer, M., Petridis, M. (eds) Artificial Intelligence XXXIV. SGAI 2017. Lecture Notes in Computer Science(), vol 10630. Springer, Cham. https://doi.org/10.1007/978-3-319-71078-5_15
Download citation
DOI: https://doi.org/10.1007/978-3-319-71078-5_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-71077-8
Online ISBN: 978-3-319-71078-5
eBook Packages: Computer ScienceComputer Science (R0)