TY - GEN
T1 - Power flow allocation method with the application of hybrid genetic algorithm-least squares support vector machine
AU - Mustafa, Mohd Wazir
AU - Khalid, Saifulnizam Abd
AU - Sulaiman, Mohd Herwan
AU - Shareef, Hussain
PY - 2010
Y1 - 2010
N2 - This paper proposes a new power flow allocation method in pool based power system with the application of hybrid genetic algorithm (GA) and least squares support vector machine (LS-SVM), namely GA-SVM. GA is utilized to find the optimal values of regularization parameter, γ and Kernel RBF parameter, σ2, which are embedded in LS-SVM model so that the power flow allocation problem can be solved by using machine learning adaptation approach. The supervised learning paradigm is used to train the LS-SVM model where the proportional sharing principle (PSP) method is utilized as a teacher. Based on converged load flow and followed by PSP technique for power tracing procedure, the description of inputs and outputs of the training data are created. The GA-SVM model will learn to identify which generators are supplying to which loads. In this paper, the 25-bus equivalent system of southern Malaysia is used to illustrate the proposed method. The comparison result with artificial neural network (ANN) technique is also will be presented.
AB - This paper proposes a new power flow allocation method in pool based power system with the application of hybrid genetic algorithm (GA) and least squares support vector machine (LS-SVM), namely GA-SVM. GA is utilized to find the optimal values of regularization parameter, γ and Kernel RBF parameter, σ2, which are embedded in LS-SVM model so that the power flow allocation problem can be solved by using machine learning adaptation approach. The supervised learning paradigm is used to train the LS-SVM model where the proportional sharing principle (PSP) method is utilized as a teacher. Based on converged load flow and followed by PSP technique for power tracing procedure, the description of inputs and outputs of the training data are created. The GA-SVM model will learn to identify which generators are supplying to which loads. In this paper, the 25-bus equivalent system of southern Malaysia is used to illustrate the proposed method. The comparison result with artificial neural network (ANN) technique is also will be presented.
KW - Artificial neural network (ANN)
KW - Genetic algorithm (GA)
KW - Least squares support vector machine (LS-SVM)
KW - Machine learning
KW - Proportional sharing princple (PSP)
UR - http://www.scopus.com/inward/record.url?scp=79951659496&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=79951659496&partnerID=8YFLogxK
U2 - 10.1109/IPECON.2010.5696998
DO - 10.1109/IPECON.2010.5696998
M3 - Conference contribution
AN - SCOPUS:79951659496
SN - 9781424473991
T3 - 2010 9th International Power and Energy Conference, IPEC 2010
SP - 1164
EP - 1169
BT - 2010 9th International Power and Energy Conference, IPEC 2010
T2 - 2010 9th International Power and Energy Conference, IPEC 2010
Y2 - 27 October 2010 through 29 October 2010
ER -