<p>Addressing hunger and ensuring access to energy and freshwater are critical priorities in today's world, and achieving these goals sustainably is essential. Renewable energy sources offer a promising solution to these challenges. This study employs meta-heuristic algorithms to determine the optimal placement of wind turbines within a wind farm alongside techno-economic feasibility assessments using real-time wind speed data from an offshore facility. The study applied Archimedes Optimization Algorithm (AOA), Particle Swarm Optimization (PSO), Differential Evolution (DE), and Genetic Algorithm (GA) across two scenarios: case 1, which assumes constant wind speed, and case 2, which utilizes real-time data. The findings indicate that AOA yields a levelized cost of energy of $0.5146/kWh in case 1 and $0.63496/kWh in case 2. Moreover, AOA significantly reduces wake loss by 17.6%, 8.15%, and 10.13% compared to PSO, DE, and GA in case 1, respectively. In case 2, the reductions are even more pronounced, with AOA achieving a 58.47%, 13.26%, and 40.03% improvement over PSO, DE, and GA. Furthermore, the annual energy production estimates for the wind farm using AOA are notably higher, reaching 164,662.1 MWh in case 1 and 167,934.88 MWh in case 2, outperforming the other algorithms.</p> Graphical abstract <p></p>