Voltage Problem Location Using Support Vector Machine

Oleh :
Khaled Abduesslam-M - S951208510 - Sekolah Pascasarjana

This thesis presented voltage problem location using least squares support vector machine (LS-SVM) for electrical power system to proper voltage problem location implemented by IEEE 39 bus now England. The data was collected from the time domain simulation by using Power System Analysis Toolbox (PSAT). Output from simulation data such as voltage, phase angle, real power and reactive power have taken as input to estimated voltage stability at particular buses based on Power Transfer Stability Index (PTSI). The simulation data carried out on the IEEE 39 bus test system by considering load bus increased on the system. To verify of the proposed (LS-SVM) its performance was compare to Learning Vector Quantization (LVQ). The results showed that LS-SVM faster and better compared to (LVQ). The results show the (LS-SVM) can be estimated of 0% misclassification compare to (LVQ) is 38.54% which has misclassification.