Solving the ordinary differential equations that govern the power system is an indispensable part in transient stability analysis. However, the traditionally applied methods either carry a significant computational burden, require model simplifications, or use overly conservative surrogate models. Neural networks can circumvent these limitations but are faced with high demands on the used datasets. Furthermore, they are agnostic to the underlying governing equations. Physics-informed neural network tackle this problem and we explore their advantages and challenges in this paper. We illustrate the findings on the Kundur two-area system and highlight possible pathways forward in developing this method further.
翻译:解决支配电力系统的普通差异方程式是短暂稳定分析的一个不可或缺的部分,然而,传统应用的方法要么具有重大的计算负担,需要简化模型,要么使用过于保守的替代模型。神经网络可以绕过这些限制,但面对对已使用数据集的高度要求。此外,它们对基本治理方程式具有不可知性。物理知情神经网络解决这一问题,我们在本文件中探讨其优势和挑战。我们举例说明关于昆都尔两地区系统的调查结果,并着重指出进一步发展这一方法的可能途径。