Electric power dispatching automation system fault tracing method based on bidirectional weighted graph model

Abstract

The embodiment of the invention provides an electric power dispatching automation system fault tracing method based on a bidirectional weighted graph model, which comprises the following steps: collecting resource occupation data of a server component in an electric power dispatching automation system, discretizing a plurality of time sequences formed by the data to obtain a time sequence containing an alarm section, eliminating alarm time periods contained in the time sequence to obtain a non-alarm-period time sequence; calculating component information entropies and inter-component transfer entropies, establishing an information correlation matrix with or without alarm sections, measuring the difference degree before and after alarm through the change rate of the information correlation matrix, and obtaining an information difference matrix by adopting a normalization technology; and extracting features with relatively high information change and interaction information among the features, constructing a bidirectional weighted graph model, fitting fault source degree indexes in combination with node information and in-out degree information change to sort, and tracing a fault source according to a sorting result. According to the technical scheme provided by the embodiment of the invention, the fault tracing performance of the power dispatching automation system is improved.

Description

【Technical field】 [0001] The invention relates to a fault tracing method for solving an unknown system topology relationship in the field of fault location, in particular to a fault tracing method for a power dispatching automation system based on a bidirectional weighted graph model. 【Background technique】 [0002] With the continuous maturity of intelligent technology and network technology, the power dispatching automation system, as a unity of computing and physical processes, is a complex system that integrates computing, communication, and physical environments. The system is usually composed of many components such as servers, storage, network devices, and application software. It has the characteristics of numerous components, tight coupling between components, and complex relationships between components, which makes it difficult to obtain the logical topology relationship between components. Once a component fails, its correlation will affect other components, whic...

AI Technical Summary

Problems solved by technology

The rule-based fault tracing method relies too much on expert knowledge, and when the rule base reaches a certain scale, the management of the rule base will become difficult, and the traceability through the rule base will reduce the efficiency

Modeling-based fault tracing methods mainly include models such as directed graphs, fault trees, invariant networks, and information difference graphs, among which directed graph models require complex system logic relationships and relevant knowledge in various fields to be established and modified. It relies heavily on prior knowledge; the fault tree requires the participation of experts in different fields, and it can only be constructed correctly with the help of detailed system knowledge, which cannot meet the requirements for large-scale systems. In addition, some causal factors will be ignored due to the subjective factors of expert experience The problem of relationship; 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, but it needs to train a huge fault candidate set to trace the root fault components

The information difference graph model based on transfer entropy also performs system modeling in a data-driven manner, and does not need to train a huge fault candidate set, but the sorting algorithm fitted in the information difference graph model is only sorted according to the fault degree index, which will Secondary faults that lead to high levels of faults may also be ranked in the forefront of the sorting table and considered as primary faults, resulting in confusion between primary faults and secondary faults, affecting the traceability effect

Images