A Fault Trace Method for Power Dispatch Automation System Based on Information Difference Graph Model

Abstract

The embodiment of the present invention proposes a fault tracing method for electric power dispatching automation system based on the information difference graph model, including: selecting historical data before and after the alarm of the electric power dispatching automation system, and obtaining the clustering center through the k-means algorithm, and using it as an interval division The endpoint of each interval, the mean value of each interval is used as the discretization result of continuous features; calculate the information entropy of the components of the power dispatch automation system and the transfer entropy between components, establish an information correlation matrix with or without an alarm segment, and measure the value before and after the alarm by its change rate and use normalization technology to obtain the information difference matrix; extract the characteristics of the high-change alarm information of the power dispatching automation system and the interaction information between the features, and further construct the information difference graph model combining the bidirectional graph and the self-information of the nodes. According to the fault degree index, the fault degree is sorted. The technical solution provided by the embodiment of the present invention improves the performance of fault source tracing in the electric power dispatching automation system.

Description

[technical field] [0001] The invention relates to a fault Traceability Method for solving unknown system topology relationship in the field of fault location, in particular to a fault Traceability Method of power dispatching automation system based on information difference graph model. [background technology] [0002] With the continuous maturity of intelligent technology and network technology, power dispatching automation system, as the unity of computing and physical process, is a complex system integrating computing, communication and physical environment. The system is usually composed of many components such as server, memory, network equipment and application software. Once the components fail, their correlation will affect other components, resulting in abnormalities or fluctuations in the whole system. Due to the unknown and complex topological relationship between components, it is extremely difficult to trace the fault source. Early tracing is of great significance to...

AI Technical Summary

Problems solved by technology

Modeling-based fault tracing methods mainly include models such as undirected graphs, directed graphs, fault trees, and invariant networks. Among them, the undirected graph model has the problem that the fault propagation direction cannot be determined; the directed graph model is based on complex system logic. Once some components are added or reduced, relevant knowledge in the professional field is required to modify and update, which greatly increases the maintenance cost; the fault tree requires the participation of experts in different fields, and can only be constructed correctly with the help of detailed system knowledge, which cannot meet the requirements for large systems. In addition, due to the subjective factors of expert experience, some causality is ignored, which ultimately limits the deployment of fault trees; the invariant network model is a data-driven way to model the system, which greatly gets rid of the problem of relying heavily on prior knowledge. However, it is necessary to train a huge set of fault candidates to backtrack the root cause fault components

Images