02611nam a2200265 a 4500 vtls000055039 KUKTEM 20251114204501.0 110722t2009 my a f m 000 0 eng d THE0006680(Local) 201905171505 amirul 201107221559 ida UMP TK1005 .L53 2010 rs Bc. Liang, Kai Feng Case study of power system state estimation by using artificial neural network / Liang Kai Feng Case study of power system state estimation by using artificial neural network [computer file] Kuantan, Pahang : UMP, 2010 xiv, 68 p. : ill. (some col.) ; 30 cm. + 1 computer disc Project paper (Bachelor of Electrical Engineering (Power System)) -- Universiti Malaysia Pahang - 2010 Bibliography : p. 67-68 This is a study that mains in Artificial Neural Network technique which introduces approach towards the problem of errors that arise due to the practical equipment and actual measurements in distribution systems. Real time data or the state variables measured in power system are often incorporated with error. This project outputs a software program that performs power system state estimation using artificial intelligence optimization. It was developed using Artificial Neural Network in MATLAB software. This method considers nonlinear characteristics of the practical equipment and actual measurements in distribution systems. It can estimate bus voltage and load angle values at each node by minimizing difference between measured and calculated state variables. This is accomplished by the utilization of load flow analysis program which acts as computerized conventional solution that calculates mathematically the exact target outputs in accordance to the inputs applied. The significant functions of the developed software program also include the accurate estimation of power system state with insufficient input data applied. This project has successfully built a power system state estimation software program that perform accurate state estimation achieving desired outputs even when provided with insufficient input data magnitudes. It helps identify the current operating state of the system on which, security assessment functions and hence contingencies can be analyzed leading to the required corrective actions Electric power system State estimation Neural networks 0 0 0 1 20000 20000 2019-09-04 0 TK1005 .L53 2010 rs Bc. 0000058232 2019-09-04 00:00:00 1 2019-09-04 PSM 0 0 0 1 20000 20000 2019-09-04 0 CD 5316 | TK1005 .L53 2010 rs Bc. 0000058233 2019-09-04 00:00:00 1 2019-09-04 PSM VIRTUA40 2808 2814 VTLSSORT0080*0200*0400*0900*1000*2450*2460*2600*3000*5020*5040*5200*6500*6501*9992