Method and system for visually sensing power grid situation

• Main Authors: CHEN YONG, FENG JING, WANG ZHONGLI, LI QINGZHI, YANG HONGYING, DU SAN'EN, FENG YIXIAN, XIAO XIANGTAO, YANG XUETAO, XIE JIAZHENG, LIU KAIXIN, LIU DAOWEI, ZHAO GAOSHANG, GAO SHEN
• Format: Patent
• Language: Chinese; English
• Published: 19.09.2023
• 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; ELECTRIC DIGITAL DATA PROCESSING; ELECTRICITY; GENERATION; MEASURING; MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES; PHYSICS; SYSTEMS FOR STORING ELECTRIC ENERGY; TESTING

The invention provides a method and a system for visually sensing a power grid situation. The method comprises the following steps of: acquiring an equipment operation signal of a power system by adopting a phasor measurement device, and de-noising the equipment operation signal to obtain an effective operation signal; based on a preset LSTM network, performing feature extraction on the effective operation signal to obtain a predicted operation signal; and according to the prediction operation signal and a preset power grid situation evaluation index, carrying out visual identification on the power grid situation by adopting an SVDD algorithm, and outputting a power grid situation prediction result. According to the method and system, for a large amount of abnormal data existing in the power system, data noise is removed through wavelet analysis, an SVDD algorithm is introduced on the basis of an LSTM network to monitor all operation indexes of the power system, and the situation of a power grid is sensed and