Method and system for predicting post-fault voltage stability of AC/DC hybrid microgrid based on data driving

• Main Authors: YUE FUCHANG, ZHU LIWEI, LI HONG, SONG JIAKANG, FU XIANGYUN
• Format: Patent
• Language: Chinese; English
• Published: 14.10.2022
• Subjects: CALCULATING; CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTINGELECTRIC POWER; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER; COUNTING; ELECTRICITY; GENERATION; HANDLING RECORD CARRIERS; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS; SYSTEMS FOR STORING ELECTRIC ENERGY

The invention discloses a method and a system for predicting voltage stability after a fault of an AC/DC hybrid micro-grid based on data driving. The method comprises the following steps: firstly, calculating short-time mean square deviation of AC and DC voltages at terminals of an interconnection converter; secondly, determining an initial section according to a mahalanobis distance criterion, and constructing a feature sequence; and finally, a deep learning system is established, the voltage stability after the fault is predicted by using a deep learning network, prediction delay is considered in the optimization design of the deep learning network, and the effectiveness and superiority of the proposed prediction mechanism are verified through simulation. The method is used for predicting the post-fault voltage stability in the island AC/DC hybrid microgrid in time, a coordinated protection and control mechanism is triggered to adjust the voltage in the sub-grid, and the accuracy of predicting the post-faul