Artificial Intelligence-Based Optimization of Renewable-Powered RO Desalination for Reduced Grid Dependence

Water scarcity and the growing demand for sustainable energy solutions have driven the need for renewable-powered desalination. This study evaluates three scenarios for reverse osmosis (RO) desalination powered by photovoltaic (PV), wind turbine (WT), and hybrid PV–WT systems, aiming to minimize the levelized costs of electricity (LCOE) and water (LCOW) while reducing grid dependence. The city studied is Zahedan, Iran, which has high potential in renewable energy. A multi-objective optimization approach using the Non-dominated Sorting Genetic Algorithm II (NSGA-II), a popular evolutionary algorithm, is employed to determine the optimal number of PV panels and wind turbines. The results show that the hybrid system outperforms single-source configurations, supplying 34.79 MWh of electricity and 34.19 m3 of desalinated water, while achieving the lowest LCOE (2.73 cent/kWh−1) and LCOW (35.33 cent/m−3). The hybrid scenario covers 65.49% of the electricity demand and 58.54% of the water demand, significantly reducing reliance on the grid compared to the PV and WT scenarios. Additionally, it ensures greater energy stability by leveraging the complementary nature of PV and WT. These findings highlight the techno-economic feasibility of hybrid renewable-powered desalination as a cost-effective and sustainable solution. Future research should focus on integrating energy storage to further enhance efficiency and minimize grid dependency.