TY - JOUR
T1 - Application of artificial intelligence techniques for modeling, optimizing, and controlling desalination systems powered by renewable energy resources
AU - Sayed, Enas Taha
AU - Olabi, A. G.
AU - Elsaid, Khaled
AU - Al Radi, Muaz
AU - Semeraro, Concetta
AU - Doranehgard, Mohammad Hossein
AU - Eltayeb, Mohamed Elrayah
AU - Abdelkareem, Mohammad Ali
N1 - Publisher Copyright:
© 2023 Elsevier Ltd
PY - 2023/8/10
Y1 - 2023/8/10
N2 - Utilizing various renewable energy resources (RERs) for powering desalination plants is an encouraging choice, specifically in arid and remote areas where conventional resources are unavailable or costly. Various RERs were used to derive desalination systems such as solar, wind, geothermal, etc. Reverse osmosis, multi-stage flash, and multi-effect distillation are the most used desalination technologies in connection with various RES. Some RES/desalination technologies combinations could be cost-efficient and reliable if appropriately designed. However, the unpredictable load demands and the intermittency nature of the RERs make designing such systems difficult. Various integrated scenarios are proposed in such systems, such as PV combinations with wind, battery energy storage systems, fuel cells, electrolyzers, etc. As a result, determining the optimum configuration using traditional methods is difficult. Implementing intelligent techniques that can integrate all working and design parameters involved in the various possible scenarios is critical for finding the optimal operating conditions. This work discusses and summarizes various artificial intelligence (AI) techniques to enhance RES-powered desalination systems. The implementation of various forecasting models, optimization algorithms, and control systems in designing and operating RER-powered desalination systems was analyzed. Finally, future research recommendations for further improving the current technology were included.
AB - Utilizing various renewable energy resources (RERs) for powering desalination plants is an encouraging choice, specifically in arid and remote areas where conventional resources are unavailable or costly. Various RERs were used to derive desalination systems such as solar, wind, geothermal, etc. Reverse osmosis, multi-stage flash, and multi-effect distillation are the most used desalination technologies in connection with various RES. Some RES/desalination technologies combinations could be cost-efficient and reliable if appropriately designed. However, the unpredictable load demands and the intermittency nature of the RERs make designing such systems difficult. Various integrated scenarios are proposed in such systems, such as PV combinations with wind, battery energy storage systems, fuel cells, electrolyzers, etc. As a result, determining the optimum configuration using traditional methods is difficult. Implementing intelligent techniques that can integrate all working and design parameters involved in the various possible scenarios is critical for finding the optimal operating conditions. This work discusses and summarizes various artificial intelligence (AI) techniques to enhance RES-powered desalination systems. The implementation of various forecasting models, optimization algorithms, and control systems in designing and operating RER-powered desalination systems was analyzed. Finally, future research recommendations for further improving the current technology were included.
KW - Artificial intelligence
KW - Artificial neural networks
KW - Control
KW - Desalination
KW - Modeling
KW - Optimization
KW - Renewable energy
UR - http://www.scopus.com/inward/record.url?scp=85162204725&partnerID=8YFLogxK
U2 - 10.1016/j.jclepro.2023.137486
DO - 10.1016/j.jclepro.2023.137486
M3 - Article
AN - SCOPUS:85162204725
SN - 0959-6526
VL - 413
JO - Journal of Cleaner Production
JF - Journal of Cleaner Production
M1 - 137486
ER -
