Search Results

Now showing 1 - 3 of 3

Some of the metrics are blocked by your
consent settings
A heuristic training-based least squares support vector machines for power system stabilization by SMES
(2011-10-01)
Pahasa, Jonglak
;
Ngamroo, Issarachai
This paper presents the application of least squares support vector machines (LS-SVMs) to design of an adaptive damping controller for superconducting magnetic energy storage (SMES). To accelerate LS-SVMs training and testing, a large amount of training data set of a multi-machine power system is reduced by the measurement of similarity among samples. In addition, the redundant data in the training set can be significantly discarded. The LS-SVM for SMES controllers are trained using the optimal LS-SVM parameters optimized by a particle swarm optimization and the reduced data. The LS-SVM control signals can be adapted by various operating conditions and different disturbances. Simulation results in a two-area four-machine power system demonstrate that the proposed LS-SVM for SMES controller is robust to various disturbances under a wide range of operating conditions in comparison to the conventional SMES. © 2011 Elsevier Ltd. All rights reserved.
Some of the metrics are blocked by your
consent settings
Least squares support vector machine for power system stabilizer design using wide area phasor measurements
(2011-07-01)
Pahasa, Jonglak
;
Ngamroo, Issarachai
This paper proposes a design method of power system stabilizer by a least squares support vector machine (LS-SVMPSS) for wide area stability control. Both local and inter-area data based on synchronized phasor measurements considering time delay are considered as the input features of the LS-SVMPSS. A large number of the training data sets of a multi-machine power system are reduced by the measurement of similarity between samples. Removing the redundant data in the training set not only improves the LS-SVMPSS performance but also decreases computation expense during the operation of LS-SVMPSS. The LS-SVMPSS parameters and the similarity threshold are optimized by a genetic algorithm. As a result, the redundant data in the training set can be discarded while the reduced data are the optimal support vectors in the LS-SVMPSS model. The LS-SVMPSS control signals can be adapted in real time by various operating conditions and different disturbances. The performance of the LS-SVMPSS is compared with the conventional PSS and the neural network-based PSS. Simulation results in a two-area four-machine power system demonstrate that the proposed LS-SVMPSS is very robust to various disturbances under wide range of operating conditions in comparison to other PSSs. © 2011 ISSN.
Some of the metrics are blocked by your
consent settings
GA-based support vector machines for adaptive power system damping controller of SMES
(2010-07-30)
Pahasa, Jonglak
;
Ngamroo, Issarachai
This paper proposes the application of support vector machines (SVMs) to design of an adaptive power system damping controller for superconducting magnetic energy storage (SMES). A genetic algorithm is used to optimize the SVM parameters based on k-fold cross-validation. The SVMs for SMES controllers are trained by the data obtained from a multi-machine power system, and the optimal SVM parameters. The SVMs can be adapted by various operating conditions when the power system operates either inside or outside of the training set. Simulation results in a two-area four-machine power system demonstrate that the proposed SVMs for adaptive SMES is much superior to the conventional SMES controller with fixed parameters under various operating conditions and severe disturbances.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results