Real power transfer allocation via Continuous Genetic Algorithm-Least Squares Support Vector Machine technique

This paper proposes a new hybrid technique, Continuous Genetic Algorithm and Least Squares Support Vector Machine to allocate the real power transfer from generators to loads, namely CGA-LSSVM. CGA is used to obtain the optimal value of hyper-parameters of LS-SVM and supervised learning approach is adopted in the training of LS-SVM model. The technique that uses proportional sharing principle (PSP) is utilized as a teacher. Based on load profile of the system and followed by PSP technique for power tracing procedure, the description of inputs and outputs of the training data are created. The CGA-LSSVM is expected to be able to assess which generators are supplying to which specific loads. In this paper, the 25-bus equivalent system of southern Malaysia is used to illustrate the effectiveness of the CGA-LSSVM technique compared to that of the PSP technique.