A data-driven method for judging loop closure conditions of distribution network

Abstract

A data-driven method for judging loop closing conditions of a distribution network, the method preprocesses open-loop operation data, so that the processed open-loop operation data is the operation data under closed-loop operation; and then the processed load of each node is used as The input value of the neural network is processed, and the voltage difference of each node is used as the output value of the neural network. Appropriate neural network parameters are obtained through a large amount of training, and the performance of the neural network is tested by applying the test set to evaluate the generalization ability of the neural network model; then The trained neural network model is used to predict the power flow when the loop is closed and the loop closure current is calculated; according to the maximum steady-state current and the RMS value of the maximum inrush current at the head end of the feeder after loop closure, it is determined whether the loop network can be closed.

Description

technical field [0001] The invention relates to a data-driven method for judging loop closing conditions of a power distribution network, which belongs to the technical field of power distribution and consumption. Background technique [0002] When the distribution network is overloaded or faulted, the loop closure operation can ensure uninterrupted power supply to users. When loop closure, the power flow in the loop will be redistributed, and loop closure current will be generated. If the inrush current or steady-state current is too large, it may be Cause the feeder switch to trip, but reduce the reliability of the user's power supply. Therefore, it is necessary to judge whether the closed loop network can be closed. [0003] The power flow calculation when the distribution network is closed is an important means to verify whether the distribution network can be closed under the closed loop condition. When the voltage, load and network parameters are known, by establishin...

AI Technical Summary

Problems solved by technology

In the loop-closing equivalent model, the current passing through the tie switch is just the loop-closing current, and the outgoing current of each feeder is the superimposition of the load current before the loop-closing and the loop-closing current, and the loop-closing nodes are not considered The power flow will change, which may lead to a large deviation between the current of the feeder line and the actual value after the loop is closed. In addition, the line parameters of the distribution network are still roughly calculated based on basic information such as line path and length. Whether the network parameters are accurate or not It will have an impact on the power flow calculation of the distribution network closure, so the power flow calculation model still has certain limitations

Images