Voltage sag reason recognition method based on EM algorithm and gradient boosting tree

Abstract

The invention discloses a voltage sag reason recognition method based on an EM algorithm and a gradient boosting tree, and aims at solving problems that voltage sags having same kind and different kinds of sag characteristics cannot be classified accurately, data characteristics are hard to extract, and the like. On the basis of voltage sag waveform data and complemented by power grid fault data,thunder data and meteorological data, the per-unit value of power grid secondary voltage is accurately extracted through the EM algorithm, the characteristic of the waveform data in a statistical sense is extracted on the basis of the per-unit value, a gradient boosting tree model is trained in single-phase and three-phase data waveforms through certain training sample data, voltage sag reason recognition is achieved, and a voltage sag caused by a system side fault and a voltage sag caused by a user side heavy user load starting are clearly distinguished.

Description

technical field [0001] The invention relates to a voltage sag cause identification method based on an EM algorithm and a gradient boosting tree, and belongs to the field of power system power quality. Background technique [0002] Voltage sag refers to an event in which the root mean square value of the voltage drops rapidly and does not last long, and its typical duration is 10ms to 1min cycle. The phenomenon of voltage sag can usually be described by voltage sag amplitude and duration. The sag amplitude is defined as the ratio of the effective value of the voltage during the sag to the rated value, and the duration refers to the time from the occurrence to the end of the sag. These two characteristic quantities representing voltage sag have a great influence on load operation. The International Electrotechnical Commission (IEC) defines the voltage sag amplitude as falling to 90% to 1% of the rated value; the Institute of Electrical and Electronics Engineers (IEEE) define...

AI Technical Summary

Problems solved by technology

Existing technologies either store a large number of voltage sag waveforms in the database and match them in a cumbersome and time-consuming manner, which consumes a lot of computing and time resources, or use explicit rules to judge and need to continuously add rules

In the identification process of voltage sag sources, intuitive feature extraction based on voltage effective value and duration often has difficulties such as large granularity, inability to accurately classify, and data feature extraction.

Images