Abstract: A method for detecting a topological structure of a grounding grid under extremely cold condition, includes the following steps: in a substation in an extremely cold area, determining a measuring area S on a ground surface of a grounding grid according to the positions of branches and nodes of the grounding grid in a selected area, acquiring dynamic current values of the branches and nodes through a current sensor based on TMR tunnel magnetoresistance, and then indirectly acquiring the magnetic induction intensity of the measuring area S through conversion; calculating moduli of first to third derivatives of magnetic induction intensities; and determining specific positions and laying depths of the branches of the grounding grid according to peak distances between main lobe peaks and side peaks between strong peaks of the moduli. According to the method, the calculation amount is greatly reduced, and the detection method has strong anti-interference.

Abstract: A synchrophasor measurement-based disturbance identification method is described considering different penetration levels of renewable energy. A differential Teager-Kaiser energy operator (dTKEO)-based algorithm is first utilized to improve multiple-disturbances detection accuracy. Then, feature extractions via the integrated additive angular margin (AAM) loss and the long short-term memory (LSTM) network is described. This enables one to deal with intra-class similarity and inter-class variance of disturbances when high penetration renewable energy occurs. With the extracted features, a multi-stage weighted summing (MSWS) loss-based criterion is described for adaptive data window determination and fast disturbance pre-classification. Finally, the re-identification model based on feature similarity is established to identify unknown disturbances, a challenge for existing machine learning algorithms.

Abstract: A synchrophasor measurement-based disturbance identification method is described considering different penetration levels of renewable energy. A differential Teager-Kaiser energy operator (dTKEO)-based algorithm is first utilized to improve multiple-disturbances detection accuracy. Then, feature extractions via the integrated additive angular margin (AAM) loss and the long short-term memory (LSTM) network is described. This enables one to deal with intra-class similarity and inter-class variance of disturbances when high penetration renewable energy occurs. With the extracted features, a multi-stage weighted summing (MSWS) loss-based criterion is described for adaptive data window determination and fast disturbance pre-classification. Finally, the re-identification model based on feature similarity is established to identify unknown disturbances, a challenge for existing machine learning algorithms.