Performance analysis of wind-hydrogen energy storage system using composite objective optimization proactive scheduling strategy coordinated with wind power prediction

The large-scale deployment of wind energy encounters challenges like randomness, intermittency and fluctuation. Integrating energy storage systems and effective scheduling strategy can mitigate these issues. This paper proposes a composite objective optimization proactive scheduling strategy (COOPSS) integrated with ultra-shortterm wind power prediction (WPP) to enhance the performance of the wind-hydrogen energy storage system (WHESS). The COOPSS model includes four key components: a WPP module, a scheduling strategy, objective functions and parameter optimization. WPP provides projected output, while discrepancies between actual and planned outputs are addressed through a dynamic scheduling strategy to regulate the charge and discharge of the Hydrogen Energy Storage System (HESS). A composite objective function quantifies output accuracy, system fluctuation, and equipment health, with parameter optimization algorithms (Dynamic Information-driven Bayesian Optimization and Sparrow Search Algorithm) refining scheduling parameters. This approach reduces the deviation from the ideal state SoC by 59.4 % compared to real-time scheduling strategies and enhancing fluctuation suppression by 6 % (0.90 MW vs. 0.85 MW). Moreover, compared to wind power without HESS, COOPSS improves power accuracy by 13.9% (19.76 MW vs. 17.02 MW). Furthermore, WPP accuracy is shown to influence optimization direction, with higher accuracy improving long-term scheduling and state management. COOPSS effectively reduces energy waste and enhances grid stability.