Fully electrified ships, which is known as the “all-electric ships (AESs)”, have the potentials to bring great economic /environmental benefits. To further improve the energy efficiency of AESs, PV generations are gradually integrated, which introduces uncertainties to the AES operation. However, current researches mostly focus on sizing problem whereas rarely concern the operation. In this perspective, a data-driven robust coordination of generation and demand-side is proposed to properly address the onboard PV generation uncertainties as well as reducing the fuel cost of AESs, which consists of an extreme learning machine (ELM) based PV uncertainty forecasting method and a two-stage operating framework, where the first stage for the worst PV generation case and the second stage targets at the uncertainty realization. A 4-DG AES is implemented into the case study and the simulation results show that the ELM-based method can well characterize the PV uncertainties, and the two-stage operating framework can well accommodate the onboard PV uncertainties. Further analysis also demonstrates the proposed method has enough flexibility when facing working condition variations.

中文翻译：

---

光伏一体化全电动船舶微电网中发电侧和需求侧数据驱动的稳健协调

被称为“全电动船（AES）”的全电气化船舶具有带来巨大经济/环境效益的潜力。为了进一步提高 AES 的能效，光伏发电逐渐集成，这给 AES 运行带来了不确定性。然而，目前的研究主要集中在尺寸问题，而很少涉及操作。从这个角度来看，提出了一种数据驱动的发电和需求侧的稳健协调，以正确解决车载光伏发电的不确定性并降低 AES 的燃料成本，它包括基于极端学习机 (ELM) 的光伏不确定性预测方法和两阶段操作框架，其中第一阶段针对最坏的光伏发电情况，第二阶段针对不确定性实现。案例研究中实施了 4-DG AES，仿真结果表明，基于 ELM 的方法可以很好地表征光伏不确定性，两级运行框架可以很好地适应车载光伏不确定性。进一步的分析还表明，当面临工况变化时，所提出的方法具有足够的灵活性。