Online fault positioning method for power distribution network containing distributed power supply

Abstract

The invention discloses an online fault positioning method for a power distribution network containing a distributed power supply. The method comprises the following steps: constructing a topologicalstructure of a power distribution network system, and labeling nodes and branches; acquiring historical fault data including physical characteristics, spatial characteristics and label characteristicsaccording to different power distribution network position faults; performing data preprocessing and feature extraction on different types of data; constructing an LSTM neural network model, and training historical data by using the model to obtain proper network parameters; and acquiring real-time fault data on line, preprocessing the real-time fault data, sending the preprocessed real-time fault data into the model to obtain a corresponding fault position result, and updating the neural network model by using the group of data. The method provided by the invention is efficient and accuratein positioning, low in configuration cost and high in error-tolerant rate of fault data, and can overcome instability of a power distribution network caused by access of a distributed power supply.

Description

technical field [0001] The invention belongs to the field of application of big data and neural networks in distribution networks, and relates to an online fault location method for distribution networks containing distributed power sources based on data and long-short-term memory neural networks (LSTM). Background technique [0002] With the popularization and development of electricity, people's dependence on electricity is increasing, and the requirements for reliable power transmission are also getting higher and higher. At the same time, the power grid also needs to take into account the reduction of interruption time and operating costs. As an important part of the power system, the distribution network is mainly connected to the user side, and has the characteristics of wide geographical distribution, various types of equipment, complex connections, and changeable operation modes. When a fault occurs in the distribution network, the power grid needs to determine the f...

AI Technical Summary

Problems solved by technology

The traditional distribution network fault location method is to visually identify the fault on the line, send a pulse signal to the line, and analyze the reflected wave, or identify the circuit interruption through the power failure management system. These fault location methods cannot be compared with large amounts of data. And change the structure of the distribution network to adapt

Images