A functional link network based adaptive power system stabilizer
An on-line identifier using Functional Link Network (FLN) and Pole-shift (PS) controller for power system stabilizer (PSS) application are presented in this thesis. To have the satisfactory performance of the PSS controller, over a wide range of operating conditions, it is desirable to adapt PSS parameters in real time. Artificial Neural Networks (ANNs) transform the inputs in a low-dimensional space to high-dimensional nonlinear hidden unit space and they have the ability to model the nonlinear characteristics of the power system. The ability of ANNs to learn makes them more suitable for use in adaptive control techniques. On-line identification obtains a mathematical model at each sampling period to track the dynamic behavior of the plant. The ANN identifier consisting of a Functional link Network (FLN) is used for identifying the model parameters. A FLN model eliminates the need of hidden layer while retaining the nonlinear mapping capability of the neural network by using enhanced inputs. This network may be conveniently used for function approximation with faster convergence rate and lesser computational load. The most commonly used Pole Assignment (PA) algorithm for adaptive control purposes assign the pole locations to fixed locations within the unit circle in the z-plane. It may not be optimum for different operating conditions. In this thesis, PS type of adaptive control algorithm is used. This algorithm, instead of assigning the closed-loop poles to fixed locations within the unit circle in the z-plane, this algorithm assumes that the pole characteristic polynomial of the closed-loop system has the same form as the pole characteristic of the open-loop system and shifts the open-loop poles radially towards the centre of the unit circle in the z-plane by a shifting factor α according to some rules. In this control algorithm, no coefficients need to be tuned manually, so manual parameter tuning (which is a drawback in conventional power system stabilizer) is minimized. The PS control algorithm uses the on-line updated ARMA parameters to calculate the new closed-loop poles of the system that are always inside the unit circle in the z-plane. Simulation studies on a single-machine infinite bus and on a multi-machine power system for various operating condition changes, verify the effectiveness of the combined model of FLN identifier and PS control in damping the local and multi-mode oscillations occurring in the system. Simulation studies prove that the APSSs have significant benefits over conventional PSSs: performance improvement and no requirement for parameter tuning.
pole shift controller, power system stabilizer, artificial neural network
Master of Science (M.Sc.)
College of Engineering
College of Engineering