Hybrid algorithm to enhance water pump stations efficiency and water distribution networks optimization
Keywords:
Water distribution network, reinforcement learning, CMA-ES algorithm, greedy ascending search algorithm, greedy descending search algorithmAbstract
Designing water distribution networks is a difficult task with many search parameters and restrictions. Evolutionary algorithms have been widely used in this manner to minimize costs while satisfying pressure limits. A new hybrid evolutionary framework with four unique phases is proposed in this research. Reinforcement learning, an efficient artificial technique, was used in the first phase to improve the performance of pump stations. CMA-ES, a strong adaptive meta-heuristic for continuous optimization, was used in the second phase. An upward-greedy search phase to eliminate pressure violations comes next. Lastly, to minimize large pipes, a downward greedy search phase is employed. The hybrid method was applied multiple WDSs case studies in order to evaluate its efficacy. The findings show that on the majority of benchmarks, the new framework performs better than the previously used heuristics in terms of both optimization speed and network cost.
References
Abraham, A. (2005). 129: artificial neural networks. Handbook of measuring system design.
Negm, A., Ma, X., & Aggidis, G. (2024). Deep reinforcement learning challenges and opportunities for urban water systems. Water Research, 253, 121145.
Al-Ansari, N., & Knutsson, S. (2011). Toward prudent management of water resources in Iraq. Journal of Advanced Science and Engineering Research, 2011(1), 53-67.
Al-Ansari, N. (2013). Management of water resources in Iraq: perspectives and prognoses. Engineering, 5(6), 667-684.
Albu-Salih, A. T. (2023). التعلم الآلي التطوري: نماذج تعلم آلي تم تحسينها وتدريبها باستخدام الخوارزمية الجينية.
Ammar Hatem Kamel, S. O. (2013). Study of the effects of water level depression in Euphrates River on the water quality.Journal of Environmental Studies, 22*(4), 45-60.
Barto, A. G. (1997). Reinforcement learning. In Neural systems for control (pp. 7–30)
Keedwell, E., & Khu, S. T. (2005). A hybrid genetic algorithm for the design of water distribution networks. Engineering Applications of Artificial Intelligence, 18(4), 461-472.
Zheng, F., Simpson, A. R., & Zecchin, A. C. (2011). Optimal rehabilitation for large water distribution systems using genetic algorithms. Proc., Australia Water Association (AWA) 2011 OzWater.
Reca, J., & Martínez, J. (2006). Genetic algorithms for the design of looped irrigation water distribution networks. Water resources research, 42(5).
Gupta, I., Gupta, A., & Khanna, P. (1999). Genetic algorithm for optimization of water distribution systems. Environmental Modelling & Software, 14(5), 437-446.
Kulat, M. I. (2017). Optimal Water Allocation Planning Using a Water-Energy-Food Nexus Approach: The Case of Matagorda County, TX (Doctoral dissertation).
Hansen, N., & Auger, A. (2013). Principled design of continuous stochastic search: From theory to practice. In Theory and principled methods for the design of metaheuristics (pp. 145-180). Berlin, Heidelberg: Springer Berlin Heidelberg.
Hansen, N., & Kern, S. (2004, September). Evaluating the CMA evolution strategy on multimodal test functions. In International conference on parallel problem solving from nature (pp. 282-291). Berlin, Heidelberg: Springer Berlin Heidelberg.
Beyer, H. G., & Schwefel, H. P. (2002). Evolution strategies–a comprehensive introduction. Natural computing, 1, 3-52.
Tzanakakis, V. A., Angelakis, A. N., Paranychianakis, N. V., Dialynas, Y. G., & Tchobanoglous, G. (2020). Challenges and opportunities for sustainable management of water resources in the island of Crete, Greece. Water, 12(6), 1538.
Abdelrahmaan, A., & Khalifa, H. (2012). Optimization of drinking water distribution systems using genetic algorithm. Tishreen University Journal for Research and Scientific Studies - Engineering Sciences Series, 34(3), 511-524. Number of pages: 14.
Salmán, H., & Khalifa, A. A. (2020). إيجاد الكلفة التصميمية الأمثل لشبكة الإمداد بمياه الشرب لمدينة جبلة باستخدام الخوارزمية الجينية وخوارزمية البحث المتناغم .Tishreen University Journal for Research and Scientific Studies -Engineering Sciences Series 24(5) 4242.
