An agent-based distribution network fault location method and system

Abstract

The invention discloses a fault locating method for a power distribution network based on an intelligent agent, and the method comprises the steps: initializing the start position of the intelligent agent in the power distribution network when the power distribution network has a fault; enabling the intelligent agent to move in the power distribution network, and obtaining the feature vector of each new position when the intelligent agent moves to one new position each time; determining how the intelligent agent processes the feature vector of the current position and a feature vector of a storage part in the intelligent agent according to the feature vector of the current position and the feature vector of the storage part in the intelligent agent through employing a decision making tablein the intelligent agent; enabling the intelligent agent to traverse each position in the power distribution network, and taking the position corresponding to the feature vector stored in the intelligent agent as a fault position after the intelligent agent traverses all positions.

Description

technical field [0001] The invention relates to the field of electric power technology, in particular to an intelligent agent-based distribution network fault location method and system. Background technique [0002] The distribution network is an important part of the power system. With the rapid development of the smart grid, a large number of uncertain connections of distributed power sources make the fault information of the distribution network more and more complicated, and the accurate and rapid analysis of the fault becomes more and more difficult. In order to ensure the highly intelligent operation of the distribution network, real-time monitoring of feeder operation data, timely warning of abnormal conditions, and rapid fault location and processing are required. Therefore, the distribution network is usually equipped with devices such as line fault indicators and feeder terminals, and these devices are used to record the operation of the distribution network. In ...

AI Technical Summary

Problems solved by technology

[0003] When using various machine learning models for fault location and judgment, the machine learning model used must first be trained. Training the machine training model requires a large amount of data. If only the data generated by the monitoring terminal of a distribution network is used, the training data will Insufficient amount, and the data output by the monitoring terminals of different power distribution networks have different characteristics. If the data belonging to different distribution network monitoring terminals are mixed for training the same model, it is easy to cause deviations in the training results.

On the other hand, in the existing technology, the fault location point corresponds to the monitoring terminal position. When the machine learning model has errors and produces multiple fault point results, a new machine learning model is required for further screening.

Images