Exploration of AI-Oriented Power System Dynamic Simulations

Artificial Intelligence (AI) is playing a more and more important role in power system analysis and control. It is foreseeable that the accuracy and efficiency of future power system dynamic analysis will be greatly improved by the interaction of the deduction-based simulator and the inductionbased AI. While some commercial software already supports AI applications to a certain extent, the way in which power system transient simulators interact with AI remains unclear. In this paper, a general design of an AI-oriented power system dynamic simulator is proposed based on the illustration of the interaction mechanism between dynamic simulations and AI. With the support of a flexible application programming interface, the simulator has rapid simulation speed, intrusive parameter accessibility, non-intrusive function usability, and neural network supportability. A prototype of this design is implemented and made public based on our previously realized simulator. Tests of this AI-oriented simulator are carried out under four scenarios, which proves that the design and implementation of the simulator are reasonable, AI-friendly, and highly efficient.