Fault diagnosis method and fault diagnosis device for power consumption information collection system

Abstract

The invention discloses a fault diagnosis method and device for an electricity consumption information collection system. The method includes the following steps: acquiring network topology data in the electricity consumption information collection system, the network topology data at least including components and components in the electricity consumption information collection system The relevant characteristics of the lines between them; based on the heterogeneous network node representation learning method, the target optimization learning is performed on the network topology data, and the network topology data is mapped to the data distribution in the computable data space, and the learning based on the heterogeneous network node representation is obtained. Results: Based on the preset fault detection and classification model, and integrating the learning results based on heterogeneous network node representation, the fault diagnosis of the power consumption information collection system is carried out. The present invention avoids a large amount of manual work, reduces the cost of system implementation, and improves the adaptability of the system to new data; and in terms of computing system, the related methods designed in this scheme are compatible with the feature modules in the traditional method, which greatly improves the performance of the system. performance.

Description

technical field [0001] The invention relates to the technical field of fault diagnosis, in particular to a method and device for fault diagnosis of an electricity consumption information collection system. Background technique [0002] The electricity consumption information collection system is a system that collects, processes and monitors electricity consumption information of power users in real time, and realizes functions such as automatic collection of electricity consumption information, measurement anomaly detection, and electric energy detection. The electricity consumption information collection system is an important part of the smart grid and also the technical foundation of the smart electricity service link. Its stable and reliable operation is directly related to the development level of the smart grid's "informatization, automation, and interaction". Its physical structure is divided into master station layer, collection layer, monitoring layer and other lay...

AI Technical Summary

Problems solved by technology

The above methods are relatively intuitive, but they lack the knowledge mining of the power consumption information collection system itself, the measurement of the similarity between different nodes in the power consumption information collection system and the learning of the grid topology, and, for large-scale power consumption information Acquisition system structure, the above method is often difficult to apply, and it needs to cooperate with relevant sampling technology to be able to be applied to actual production

Images