Change search
ReferencesLink to record
Permanent link

Direct link
PMU Data Mining in and analysis of suitable algorithm for fault pattern recognition.
KTH, School of Electrical Engineering (EES), Industrial Information and Control Systems.
2012 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

Phasor measurement unit (PMU) is getting much attention in recent days to acquire power system data. It is because PMU provides the opportunity to collect high resolution system. Having a high resolution data provides scopes to monitor a system with different computational methods. Data mining is one of the effective methods. In the age of power system automation high resolution power system data storage and management has become more feasible. Data mining can be implemented on high resolution PMU data and many advantages can be achieved from such an operation.  

Data mining is a scientific process through which a knowledge or patterns are identified from a large amount of data base. Data mining in power system based on PMU data is getting much focus in the recent years. Some of the prominent research on mining power system data and finding pattern is already going on in this field.

There are different pattern recognition algorithms deployed in data mining field. Research has also been done to check the efficacy of those algorithms in action.

In this thesis implementation of existing pattern recognition algorithms based on background study is carried out. Along with it one work-process is proposed to check out the possibilities of data mining in power system regarding fault pattern recognition. The mining process proposed here is a mixture of different existing algorithms and a new algorithm for fault classification. The work here mostly offers a broad perspective of data mining in power system rather than dealing with a specific application.

Place, publisher, year, edition, pages
2012. , 94 p.
Keyword [en]
Data mining, pattern recognition, PMU, power system fault, k-NN, k-means clustering, decision tree, naive bayes, Microsoft business intelligence development studio, rapid miner.
National Category
Electrical Engineering, Electronic Engineering, Information Engineering Electrical Engineering, Electronic Engineering, Information Engineering
URN: urn:nbn:se:kth:diva-93057OAI: diva2:514687
Subject / course
Industrial Control Systems
Educational program
Master of Science - Electric Power Engineering
2012-01-26, 10:50 (English)
Available from: 2012-04-12 Created: 2012-04-10 Last updated: 2012-04-12Bibliographically approved

Open Access in DiVA

No full text

By organisation
Industrial Information and Control Systems
Electrical Engineering, Electronic Engineering, Information EngineeringElectrical Engineering, Electronic Engineering, Information Engineering

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 604 hits
ReferencesLink to record
Permanent link

Direct link