A Novel Deep Learning Approach for Accurate Offshore Wind Power Forecasting Using the MamKan Network

With the increasing global demand for clean energy, offshore wind power has become a crucial component in the transition to sustainable energy systems. However, predicting offshore wind power output remains a significant challenge due to the highly variable marine environment and complex meteorological conditions. Accurate power forecasting is essential for grid stability and efficient energy dispatch. This paper introduces a novel deep learning model, the MamKan Network (MKN), designed specifically to enhance offshore wind power prediction. The MKN incorporates a Mamba module to capture long-range dependencies in spatiotemporal data and a Kan structure for flexible nonlinear modeling. Evaluation results demonstrate that MKN outperforms traditional machine learning and existing deep learning models in accuracy, robustness, and generalization across complex offshore scenarios. The proposed model offers substantial improvements in prediction accuracy, addressing key challenges in offshore wind power forecasting and providing a scalable solution for real-world energy applications.