Alternating-current transformer substation reactive voltage control method based on deep neural network

• Main Authors: XU SIXUAN, ZHAO FEIFEI, HAN XINGNING, QI WANCHUN, GE YI, SUN FANGYUAN, HUANG JUNHUI, CAI HUI, WANG QUANQUAN, ZHANG WENJIA, LIU ZHANNING, SUN WENTAO, XU XINXIN, XIE ZHENJIAN, PENG ZHUYI, DIAO RUISHENG
• Format: Patent
• Language: Chinese; English
• Published: 13.12.2022
• 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; PHYSICS; SYSTEMS FOR STORING ELECTRIC ENERGY

The invention discloses an AC transformer substation reactive voltage control method based on a deep neural network, and the method comprises the steps: obtaining the real-time SCADA measurement information of a power grid in a controlled region; according to the measurement information, judging whether the alternating-current transformer substation in the controlled area has a voltage power line crossing problem or not; if yes, determining all feasible control strategies according to the existing problems, inputting substation operation data in the measurement information as input values into a pre-constructed and trained deep neural network model corresponding to the feasible control strategies, and outputting AC substation bus voltage amplitudes corresponding to the feasible control strategies; determining AC transformer substation bus voltage and power factors corresponding to each feasible control strategy; and determining an optimal control strategy according to a safety evaluation result. The method ef