Power distribution network fault recovery method based on self-learning mechanism

Abstract

The invention discloses a power distribution network fault recovery method based on a self-learning mechanism. According to the method, anticipated accident simulation is performed according to a riskevaluation result during the normal operation of a power grid; a self-learning database based on an accident plan and a historical fault recovery scheme is built; after a faults occur, fault featuresare extracted, the similarities of the current fault and faults stored in the database are calculated, and are sorted according to the sequence from high similarities to low similarities; and a powersupply recovery task is quickly and reliably realized by utilizing a power supply recovery scheme of a fault which is similar to the current fault and is obtained through matching. According to the method of the invention, a traditional complex and time-consuming online optimization problem is converted into the similarity evaluation problem of finite fault states; and therefore, a real-time calculation amount is greatly reduced while the quality of the fault recovery scheme is ensured, power supply recovery decision speed and scheme performance are improved, and a power supply recovery system is upgraded into an intelligent control system with self-learning, self-perfecting and evolutionary capabilities.

Description

technical field [0001] The invention relates to a distribution network fault recovery method based on a self-learning mechanism, which belongs to the field of power system automation and distribution network fault recovery. Background technique [0002] The distribution network in the power system undertakes the important task of distributing electric energy to thousands of households, which directly affects the power supply reliability and power quality of power users. With the development of social economy and the continuous improvement of living standards, the reliability of distribution network power supply will be improved. As the core function of self-healing control of smart distribution network, power supply restoration is of great significance to improve the reliability of power grid power supply. [0003] The restoration of power supply in the distribution network needs to take into account factors such as power loss load, switching times, load balance, voltage qua...

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is: to overcome the deficiencies of the existing technology, to provide a method that can solve the defects of slow speed and poor performance of the traditional online decision-making method, and can effectively use the processing experience of expected accidents and similar historical faults to propose A distribution network fault recovery method based on self-learning mechanism

Images