For being the world’s largest low voltage direct current (LVDC) microgrid (MG) in space, the power generation and distribution systems aboard the International Space Station (ISS) employ a hierarchical assortment of electric power sources, energy storage, control devices, power electronics, and loads operating cooperatively at multifarious system dispositions and multi-stage configurations. At the early phase of design, for such time-critical systems, the trade-off between reliability and convergence rate of device modeling, varying accuracy requirements of control flows, and especially the implementation for real-time performance have brought new challenges and problems for testing and validation of the MG. One of the solutions presented by this paper is to use the hardware-in-the-loop (HIL) emulation, where the MG is emulated using the field-programmable gate array (FPGA) hardware platform. In parallel with the emulation effort, comprehensive modeling solutions for both large-scale photovoltaic (PV) solar array wings (SAWs) and nonlinear behavior model (NBM) of insulated-gate bipolar transistors (IGBTs) have been utilized based on machine learning (ML) concepts of artificial neural network (ANN) and recurrent neural network (RNN). Both system-level (validated by Matlab/Simulink) and device-level (validated by SaberRD) transient simulations are carried out, and the results exhibit high accuracy and fidelity of the models and significant improvements in execution speed and hardware resource consumption.

中文翻译：

---

国际空间站 LVDC 微电网的实时机器学习辅助硬件在环电热仿真


作为世界上最大的太空低压直流 (LVDC) 微电网 (MG)，国际空间站 (ISS) 上的发电和配电系统采用了分层分类的电源、储能、控制设备、电力电子设备，以及在多种系统配置和多级配置下协同运行的负载。在设计的早期阶段，对于这种时间关键的系统，器件建模的可靠性和收敛速度之间的权衡、控制流的不同精度要求，特别是实时性能的实现，给系统设计带来了新的挑战和问题。 MG 的测试和验证。本文提出的解决方案之一是使用硬件在环（HIL）仿真，其中使用现场可编程门阵列（FPGA）硬件平台对MG进行仿真。在进行仿真工作的同时，还利用了基于机器学习 (ML) 的大规模光伏 (PV) 太阳能电池阵列翼 (SAW) 和绝缘栅双极晶体管 (IGBT) 非线性行为模型 (NBM) 的综合建模解决方案）人工神经网络（ANN）和循环神经网络（RNN）的概念。进行了系统级（经Matlab/Simulink验证）和器件级（经SaberRD验证）瞬态仿真，结果显示模型的高精度和保真度，以及执行速度和硬件资源消耗的显着改善。