Power distribution network fault information mining and diagnosing method based on multi-source heterogeneous data

Abstract

The power distribution network fault information mining and diagnosing method based on the multi-source heterogeneous data comprises the steps of firstly, formulating a pre-set rule for a power distribution network fault event, carrying out data mining, and then preprocessing and fusing the multi-source heterogeneous information of the power distribution network, and finally, performing fault diagnosis on the power distribution network based on the multi-source data. According to the method, a production management system, fault repair and SCADA data are fused, SCADA system and TCM system event pre-set rules are established, the information related to the faults is extracted, and the information is stored in a big data platform; the relevance of the multi-source heterogeneous data is mined, information and attributes of events in the distribution network system are diagnosed, the auxiliary information is combined to verify the diagnosis result, and the technical support is provided forthe high-quality, safe and stable operation of the power distribution network.

Description

technical field [0001] The invention belongs to the technical field of electric power, relates to mining and diagnosis of distribution network fault information, and is a method for mining and diagnosing distribution network fault information based on multi-source heterogeneous data. Background technique [0002] With the development of the national economy and the improvement of people's living standards, power users have higher and higher requirements for power supply reliability and power quality. However, due to the harsh environment and unpredictable human factors, the distribution network, especially the overhead line, has a high probability of failure. occur [1] . How the distribution network actively responds to emergencies requires not only accurate, reliable, comprehensive and timely status information of the distribution network covering the jurisdiction, but also professional analysis and diagnosis of these multi-source heterogeneous complex data [2,3] . [0...

AI Technical Summary

Problems solved by technology

Although the expert system can obtain diagnostic results in line with human thinking habits, with the increase in the scale and complexity of the power grid, the number of switches and protections has increased significantly, and the action logic has become more complex. It is very difficult to establish a complete knowledge base [21]

Neural networks need to learn a large number of representative samples before application, and usually complete and sufficient samples are difficult to obtain, which makes it difficult for the general application of neural networks, and the convergence speed of learning algorithms is usually slow [22]

When modeling a large-scale distribution network, the Petri network will face the situation of combinatorial explosion, and the modeling has a strong dependence on the network structure and poor fault tolerance. [23]

Rough set theory can only be used to deal with discrete data. For continuous data, it must be discretized first, and information deviation or loss may occur during this process. [24]

Images