Application of Reinforcement Learning Algorithm for Determining the Operational Instructions of the On-Request Method for Optimal Water Distribution and Delivery

Document Type : Research Paper

Authors

1 Ph. D. Candidate, Dept. of Water Structure Engineering, University of Tarbiat Modares

2 Associate Professor, Dept. of Water Structure Engineering, University of Tarbiat Modarres

3 Professor, Electrical Engineering, University of Tehran

Abstract

The on-request system is considered as one of the effective water distribution and delivery systems. It can be applied to currently available irrigation networks but, the main challenge for its application is the extraction and provision of appropriate operational instructions. The main objective followed in the research the development of Fuzzy Sarsa reinforcement Learning (FSL) model for extracting operation al scheduling for the on request irrigation systems. The FSL is to be evaluated in the E1R1 canal of Dez network. Requested discharges are the input of the algorithm and the output comprised of the optimum operational instructions. Water depth and flow performance indicators were made use of for an evaluation of the two performed scenarios. In scenario No. 1, as an exemplary sample, in which turnouts No. 5 and 6 demands increase from 0.1 to 0.2 m3/s while the other turnouts are closed, the minimum values of efficiency and adequacy indicators were recorded as 0.989 and 0.994; and while maximum and average values of water depth deviations being  obtained 8.4% and 7.4%, respectively. Considering the results, FSL can be applied as manual adjustment of the structures available on the present irrigation networks for a determination of the operational instructions.

Keywords

Main Subjects


Burt, C. M. (2011). The Irrigation Sector Shift from Construction to Modernization: What is Required for Success?  8th N.D. Gulhati Memorial Lecture for International Cooperation in Irrigation and Drainage. 7-22.
Clemmens, A. J., Kacerek, T. F., and Grawitz, B., and Schuurmans, W. (1998). Test cases for canal control algorithms. Journal of irrigation and drainage engineering. 124(1), 23-30.
Derhami, V. (2007). Intelligent Agent Based Controller Design for Robot Navigation. Ph. D. dissertation, Tarbiat Modares University, Tehran, Iran. (In Farsi).
Derhami, V., Majd, V. J., and Nili, M. (2008). Fuzzy Sarsa learning and the proof of existence of its stationary points. Asian Journal of Control. 10(5), 535-549.
De Vries, T. and Anwar, A. (2004). Irrigation Scheduling. I: Integer Programming Approach. Journal of Irrigation and Drain Engineering, 130(1), 9-16.
Glorennec, P. Y. and Jouffe, L. (1997). Fuzzy Q-learning fuzzy systems. Proceedings of the Sixth IEEE International Conference on, IEEE.
Haq, Z. U., Anwar, A. A., and Clarke, D. (2008). Evaluation of a genetic algorithm for the irrigation scheduling problem. Journal of Irrigation and Drainage Engineering. 134(6), 737-744.
Kaelbling, L. P., Littman, M. L., and Moore, A. W. (1996). Reinforcement learning: A survey. Arxiv preprint cs/9605103.
Mathur, Y., Sharma, G., and A. Pawde (2009). Optimal Operation Scheduling of Irrigation Canals Using Genetic Algorithm, International Journal of Recent Trends in Engineering, 1(6): 11-15.
Mohseni Movahed, A. and Monem, M. J. (2002). Introducing ICSSDOM model for performance evaluation and optimizing irrigation canals operation, 11th national congress on irrigation and drainage, 16-17 Nov, Tehran, Iran, pp: 95-110. (In Farsi)
Molden, D. J. and Gates, T. K. (1990). Performance measures for evaluation of irrigation-water-delivery systems. Journal of Irrigation and Drainage Engineering. 116(6), 804-823.
Monem, M. J. and Namdarian, R. (2005). Application of simulated annealing (SA) techniques for optimal water distribution in irrigation canals. Irrigation and Drainage. 54(4), 365-373.
Monem, M. J., Najaf, M. R., and Khoshnavaz, S. (2007). Optimal water scheduling in irrigation networks using genetic algorithm. Iran-Water Resources Research, 3(1), 100-110. (In Farsi)
Monem, M. J. and Nouri, M. A. (2010). Application of PSO method for optimal water delivery in irrigation networks, Iranian Journal of lrrigation and drainage, 1(4), 73-82. (In Farsi).
Suryavanshi, A. and Reddy, J. M. (1986). Optimal operation schedule of irrigation distribution systems. Agricultural Water Management. 11(1), 23-30.
Wang, Z., Reddy, J. M., and Feyen, J. (1995). Improved 0–1 programming model for optimal flow scheduling in irrigation canals. Irrigation and Drainage Systems. 9(2), 105-116.