A review on GA-NN based control strategies for floating solar-ocean hybrid energy platforms

Floating solar-ocean hybrid platforms offer a promising solution to meet the growing energy needs of coastal and island regions through sustainable sources. However, their control remains a major challenge due to the complex, nonlinear dynamics caused by waves, wind, and fluctuating solar irradiance. Conventional control methods often lack the adaptability required for such environments, limiting their effectiveness. To address this gap, this study proposes a Genetic Algorithm-Tuned Neural Network (GA-NN) control framework aimed at enhancing stability, energy efficiency, and real-time adaptability in floating hybrid platforms. The methodology involves a three-layer neural network optimized using genetic algorithms, which continuously adjust network parameters in response to environmental inputs such as wave height, wind speed, solar irradiance, and platform inclination. Simulations conducted in MATLAB/Simulink demonstrate that the GA-NN system outperforms traditional PID controllers, achieving up to 35% improvement in platform stability and higher energy tracking accuracy under varying sea states. These findings highlight the potential of intelligent control systems in enabling autonomous, resilient, and efficient operation of next-generation marine renewable energy infrastructures.