Design of an Offshore Hybrid Energy System with Intelligent Dispatch: Dynamic Cooperative Optimization of Wave Energy and Backup Sources

Abstract

To address the challenges of intermittency and grid integration associated with wave energy, this study aims to enhance its dispatchability and economic viability. We propose a novel design and optimization framework for an offshore hybrid energy system, centered around a dynamic cooperative optimization strategy based on Deep Reinforcement Learning (DRL). The system integrates a Wave Energy Converter (WEC) with a hybrid backup system composed of Battery Energy Storage (BESS) and a hydrogen-based system (P2H-FC). A DRL agent, built upon the Deep Deterministic Policy Gradient (DDPG) algorithm, was trained to make real-time scheduling decisions. The framework was validated through a case study using a full year of data from two typical sites in the East China Sea. The results demonstrate the superior performance of the proposed Intelligent Dispatch Strategy (IDS), achieving a dispatch accuracy of over 96% and reducing the wave power curtailment rate to 2.1%. Compared to a Rule-Based Control (RBC) strategy, the IDS increased annual economic revenue by 12.4% and decreased the Levelized Cost of Energy (LCOE) by 17.3%. This research provides a new paradigm for the intelligent and sustainable operation of offshore renewable energy systems, confirming that advanced AI-driven scheduling can significantly enhance the grid-friendliness and profitability of wave energy, paving the way for its large-scale application.