LS-SVM based AGC of power system with dynamic participation from DFIG based wind turbines

Modern power systems are large and complex with growing trends to integrate wind energy to the grid. The penetration of wind energy has motivated researchers to investigate the dynamic participation of wind generators in load frequency control besides conventional generators. This has necessitated relooking of the classical AGC problem in the new environment. Literature surveys shows that pattern recognition techniques such as ANNs have the potential to design non linear controller for better dynamic performance in the AGC system under wide range of operating conditions. The Support vector machine (SVM) is a class of supervised learning model with associated learning algorithm that analyzes data and recognizes patterns. It has excellent pattern recognition and function estimation capability. In this paper, a least squares support vector machines (LS-SVM) based automatic generation control (AGC) regulators have been investigated for a two-area interconnected power system with dynamic participation of doubly fed induction generator (DFIG) based wind turbines. The RBF kernel is used for support vector machines. AC tie-line is used as an area interconnection between the control areas. The designed LS-SVM based AGC regulators are implemented and the system dynamic responses for various system states are obtained and compared with that obtained using multi-layer perceptron neural networks (MLP NNs) and conventional PI based AGC regulators for various cases of plant parameter changes under diverse operating conditions.