Abstract
The poor performance of surface irrigation water distribution systems in terms of reliability, sufficiency, and timely delivery makes researchers develop and employ new methods to reduce its consequent challenges, including environmental, energy, and groundwater withdrawal issues. In this regard, many model-based control systems have been considered to automate canal structures. Artificial intelligence, as model-free systems, has recently gained researchers’ attraction to be employed for canal control purposes. In this research, the Reinforcement Learning (RL) methods with critic-only architecture, Fuzzy SARSA Learning (FSL) and Fuzzy Q Learning (FQL) that use a scalar reward/penalty to adapt system parameters online were developed and introduced to control irrigation canals. The main difference between the mentioned methods lies in the mathematical guarantees regarding FSL convergence and FQL divergence observation. Applications of these two methods to a case study canal allows assessing their performance and convergence in this context using standard performance indicators.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Alamiyan-Harandi, F., Derhami, V., & Jamshidi, F. (2018). A new framework for mobile robot trajectory tracking using depth data and learning algorithms. Journal of Intelligent & Fuzzy Systems, 34(6), 3969–3982.
Amein, M. (1968). An implicit method for numerical flood routing. Water Resources Research, 4(4), 719–726.
Amein, M., and Fang, C. S. (1970). Implicit flood routing in natural channels. Journal of the Hydraulics Division.
Arauz, T., Maestre, J. M., Tian, X., & Guan, G. (2020). Design of PI controllers for irrigation canals based on linear matrix inequalities. Water, 12(3), 855.
Barkhordari, S., & Shahdany, S. M. H. (2021). Developing a smart operating system for fairly distribution of irrigation water, based on social, economic, and environmental considerations. Agricultural Water Management, 250, 106833.
Brittain, M., & Wei, P. (2019). Autonomous air traffic controller: A deep multi-agent reinforcement learning approach. arXiv preprint arXiv:1905.01303.
Carlucho, I., De Paula, M., Villar, S. A., & Acosta, G. G. (2017). Incremental Q-learning strategy for adaptive PID control of mobile robots. Expert Systems with Applications, 80, 183–199.
Chu, T., Chinchali, S., & Katti, S. (2020). Multi-agent reinforcement learning for networked system control. In Proceedings of International Conference on Learning Representations.
Clemmens, A. J., Kacerek, T. F., Grawitz, B., & Schuurmans, W. (1998). Test cases for canal control algorithms. Journal of Irrigation and Drainage Engineering, 124(1), 23–30.
Derhami, V., Majd, V. J., & Ahmadabadi, M. N. (2010). Exploration and exploitation balance management in fuzzy reinforcement learning. Fuzzy Sets and Systems, 161(4), 578–595.
Fatemeh, O., Hesam, G., & Shahverdi, K. (2020). Comparing fuzzy SARSA learning (FSL) and ant colony optimization (ACO) algorithms in water delivery scheduling under water shortage conditions. Irrigation and Drainage Engineering, 146(9), 04020028.
Fread, D., & Harbaugh, T. (1971). Open-channel profiles by Newton’s iteration technique. Journal of Hydrology, 13, 70–80.
Glorennec, P. Y., & Jouffe, L. (1997) Fuzzy Q-learning. In Proceedings of 6th International Fuzzy Systems Conference (pp. 659–662). IEEE.
Harandi, F. A., & Derhami, V. (2016). A reinforcement learning algorithm for adjusting antecedent parameters and weights of fuzzy rules in a fuzzy classifier. Journal of Intelligent & Fuzzy Systems, 30(4), 2339–2347.
Henderson, F. M. (1966). Open channel flow.
Hernández, J., and Merkley, G. (2011a). Canal structure automation rules using an accuracy-based learning classifier system, a genetic algorithm, and a hydraulic simulation model. I: Design. Journal of irrigation and drainage engineering, 137(1).
Hernández, J., & Merkley, G. (2011b). Canal structure automation rules using an accuracy-based learning classifier system, a genetic algorithm, and a hydraulic simulation model. I: Result. Journal of Irrigation and Drainage Engineering, 137(5).
Kempka, M., Wydmuch, M., Runc, G., Toczek, J., & Jaśkowski, W. (2016). Vizdoom: A doom-based ai research platform for visual reinforcement learning. In 2016 IEEE Conference on Computational Intelligence and Games (CIG) (pp. 1–8). IEEE.
Khiabani, M. Y., Shahdan, S. M. H., Hassani, Y., & Maestre, J. M. (2021). Introducing an economic agricultural water distribution in a hyper-arid region: A case study in Iran. Journal of Hydroinformatics, 23(3), 548–566.
Liu, Y., Yang, T., Zhao, R.-H., Li, Y.-B., Zhao, W.-J., & Ma, X.-Y. (2018). Irrigation canal system delivery scheduling based on a particle swarm optimization algorithm. Water, 10(9), 1281.
Manz , D. H. (1990). Use of the ICSS model for prediction of conveyance system operational characteristics. In Transactions of the Fourteenth International Congress on Irrigation and Drainage (ICID) (1–18). Rio de Janerio, Brazil.
Mao, H., Alizadeh, M., Menache, I., & Kandula, S. (2016) Resource management with deep reinforcement learning. In Proceedings of the 15th ACM Workshop on Hot Topics in Networks (pp. 50–56).
Molden, D. J., & Gates, T. K. (1990). Performance measures for evaluation of irrigation-water-delivery systems. Journal of Irrigation and Drainage Engineering, 116(6), 804–823.
Pretorius, A., Cameron, S., Van Biljon, E., Makkink, T., Mawjee, S., Plessis, J. d., Shock, J., Laterre, A., & Beguir, K. (2020). A game-theoretic analysis of networked system control for common-pool resource management using multi-agent reinforcement learning. arXiv preprint arXiv:2010.07777.
Ren, T., Niu, J., Cui, J., Ouyang, Z., & Liu, X. (2021). An application of multi-objective reinforcement learning for efficient model-free control of canals deployed with IoT networks. Journal of Network and Computer Applications, 182, 103049.
Savari, H., Monem, M., & Shahverdi, K. (2016). Comparing the performance of FSL and traditional operation methods for on-request water delivery in the Aghili Network, Iran. Journal of Irrigation and Drainage Engineering, 142(11), 04016055.
Shahverdi, K., Maestre, J., Alamiyan-Harandi, F., & Tian, X. (2020). Generalizing fuzzy SARSA learning for real-time operation of irrigation canals. Water, 12(9), 2407.
Shahverdi, K., amp; Maestre, J. M. (2022). Gray wolf optimization for scheduling irrigation water. Journal of Irrigation and Drainage Engineering, 148(7), 04022020.
Shahverdi, K., & Monem, M. J. (2012). Construction and evaluation of the bival automatic control system for irrigation canals in a laboratory flume. Irrigation and Drainage, 61(2), 201–207.
Shahverdi, K., & Monem, M. J. (2015). Application of reinforcement learning algorithm for automation of canal structures. Irrigation and Drainage, 64(1), 77–84.
Shahverdi, K., Monem, M. J., & Nili, M. (2016). Fuzzy SARSA learning of operational instructions to schedule water distribution and delivery. Irrigation and Drainage, 65(3), 276–284.
Strelkoff, T. (1969). One-dimensional equations of open-channel flow. Journal of the Hydraulics Division.
Sugeno, M., & Takagi, T. (1983). Multi-dimensional fuzzy reasoning. Fuzzy Sets and Systems, 9(1–3), 313–325.
Sutton, R. S., & Barto, A. G. (1998). Reinforcement learning: An introduction, MIT Press Cambridge.
Wang, L.-X. (1999). A course in fuzzy systems. Prentice-Hall Press.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this chapter
Cite this chapter
Shahverdi, K., Alamiyan-Harandi, F., Maestre, J.M. (2022). Fuzzy Reinforcement Learning for Canal Control. In: Bozorg-Haddad, O., Zolghadr-Asli, B. (eds) Computational Intelligence for Water and Environmental Sciences. Studies in Computational Intelligence, vol 1043. Springer, Singapore. https://doi.org/10.1007/978-981-19-2519-1_15
Download citation
DOI: https://doi.org/10.1007/978-981-19-2519-1_15
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-2518-4
Online ISBN: 978-981-19-2519-1
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)