DSpace Collection: Scholarly Publication from UNITEN Community (College of Engineering)
http://dspace.uniten.edu.my/jspui/handle/123456789/5
Scholarly Publication from UNITEN Community (College of Engineering)
2024-03-28T10:32:48Z
-
Fast voltage collapse evaluation via fuzzy decision tree method
http://dspace.uniten.edu.my/jspui/handle/123456789/11430
Title: Fast voltage collapse evaluation via fuzzy decision tree method
Authors: Abidin, H.I.H.Z.; Lo, K.L.; Hussein, Z.F.
Abstract: Voltage stability is considered to be a complex field of study since it has a number of contributing factors. Due to this, numerous studies or research has been made to look into various methods of analysis, detection and mitigation. In general, these methods would involve either complex computation for accurate results but suffers from high computation time. Some methods may also be simple and fast but then has the disadvantage of inaccuracy. This paper presents an alternative method of analysing the voltage stability problem by incorporating machine learning techniques, i.e. fuzzy decision tree method. The author proposed a general overview on how the algorithm is created. The algorithm is then tested using an IEEE 300 bus test system to test the algorithm's capability. Results presented show that the proposed FDT has a lot of future potential as an online tool for voltage stability analysis. © 2003 IEEE.
2003-01-01T00:00:00Z
-
Multiple attribute dynamic fuzzy decision tree approach for voltage collapse evaluation
http://dspace.uniten.edu.my/jspui/handle/123456789/11429
Title: Multiple attribute dynamic fuzzy decision tree approach for voltage collapse evaluation
Authors: Abidin, H.I.H.Z.; Lo, K.L.; Hussein, Z.F.
Abstract: Voltage collapse is a complex phenomenon which has a variety of contributing factors. Past efforts have been given in analysing this phenomenon. As a result, various methods of analysis have been devised. Some methods are considered to be complex, slow but accurate and some methods are considered to simple, fast but inaccurate. With the emergence of machine learning techniques, a data mining method can also be used as an alternative diagnostic tool. This method is known as fuzzy decision tree. This paper will outline improvements made to an existing fuzzy decision tree method by adding more contributing attributes for partitioning, creating a hybrid fuzzy decision tree. Comparison and tests are made using an IEEE 300 bus system. © 2003 IEEE.
2003-01-01T00:00:00Z
-
Lightning prediction using radiosonde data
http://dspace.uniten.edu.my/jspui/handle/123456789/11426
Title: Lightning prediction using radiosonde data
Authors: Weng, L.Y.; Omar, J.B.; Siah, Y.K.; Abidin, I.B.Z.; Ahmad, S.K.
Abstract: This paper presents a concept of predicting lightning with the data from radiosonde using only a simple back propagation neural network model written in C code. The location of interest in this research is Kuala Lumpur International Airport (KLIA). In this model, the parameters related to wind were disregarded. Preliminary results indicate that this method shows some positive results. Future work should include wind parameters to fully capture all properties for lightning formation, subsequently its prediction.
2008-01-01T00:00:00Z
-
Adaptive protection for voltage instability mitigation scenario
http://dspace.uniten.edu.my/jspui/handle/123456789/11424
Title: Adaptive protection for voltage instability mitigation scenario
Authors: Abidin, I.Z.; Ahmad, N.; Zahidi, R.A.; Hashim, H.; Hussein, Z.F.; Omar, Y.R.; Hashim, A.H.
Abstract: Modern power system network are usually operated to its maximum capabilities. This in turn would expose the system towards possible voltage instability condition. Coupled with peak load condition where lines can be loaded to its limit, probable scenarios relating to voltage instability could lead to tripping of overload lines which would then lead to possible cascading tripping; ultimately lead towards voltage collapse condition. However, possible mitigating action is possible which could reduce the line loading and ultimately push the system back towards a voltage stable condition. This paper demonstrates a possibility of this occurring utilizing Fast Voltage Stability Index (FVSI) approaches to quickly assess the network voltage stability. Results show that these mitigating action does improve the stability of the system hence lead to a possible Wide Area Protection application which is synonymously linked to a smart grid system. ©2009 IEEE.
2009-01-01T00:00:00Z