Gerald D. Swann

A novel Radial Basis Function Neural Network based intelligent adaptive architecture for Power System Stabilizer

In this paper, we propose a new class of intelligent adaptive control systems based on a system-centric approach for the control of generators under transient operating conditions. The proposed architecture consists of a Model Reference Adaptive Controller (MRAC) operating in parallel with a Radial Basis Function Neural Network (RBFNN) to control generator oscillations in the presence of disturbances. The underlying structural feature is the introduction of an Intelligent Supervisory Loop (ISL) to augment a conventional adaptive controller. The main advantage of this algorithm is that it is precise, feasible, stable, and more effective than other nonlinear adaptive controllers acting alone. Simulation results are presented showing substantial improvement in the oscillatory and transient response of a generator in a Single Machine Infinite Bus (SMIB) while using the proposed control scheme.

An intelligent paradigm for electric generator control based on supervisory loops

In this paper a new approach to a neural network based intelligent adaptive controller, which consists of an online growing dynamic Radial Basis Function Neural Network (RBFNN) structure along with a Model Reference Adaptive Control (MRAC), is proposed. RBFNN control is used to approximate the nonlinear function and the MRAC control adapts when plant parametric set changes. The adaptive laws, including neural network approximation error, are derived based on a Lyapunov function. The update details of the RBFNN width, centers, and weights are derived in order to ensure the error reduction and for improved tracking accuracy. Main advantage and uniqueness of the proposed scheme is the controllers ability to complement each other in case of parametric and functional uncertainty. Moreover, the online neural network produces a plant functional approximation control with growing and pruning nodes. The theoretical results are validated by conducting simulation studies on a single machine infinite bus (SMIB) system for electric generator control.

A novel power system stabilizer based on fuzzy model reference adaptive controller

The main objective of this work is to illustrate the development of a new class of intelligent adaptive control system based on a system-centric approach for the control of generators under transient operating conditions. The benefit of such a structure is its ability to control time varying power system operations including complex and multimodal dynamics and scheduled/unscheduled ‘Jumps’. The underlying structural feature is the introduction of Intelligent Supervisory Loops (ISL) to augment a conventional adaptive controller. The proposed fuzzy model reference adaptive controller uses a Fuzzy Reference Model Generator (FRMG) in parallel with the Model Reference Adaptive Controller (MRAC). The main advantage of this algorithm is that it is precise, feasible and more effective than other nonlinear adaptive controllers reported to-date. Simulation results are presented in order to show that, the oscillatory and transient response of a generator in a Single Machine Infinite Bus (SMIB) has substantially improved while using the proposed control scheme.

An intelligent hybrid controller for speed control and stabilization of synchronous generator

In this paper, an intelligent approach to synchronous generator control is described. This method combines two controllers, one a neural network based controller with explicit neuro-identifier, and the other an intelligent adaptive controller implemented as a Model Reference Adaptive Controller (MRAC) to perform a hybrid control operation. The neuro-control identifier combination is used to approximate the nonlinear function and the MRAC control adapts when plant parametric set changes. Additionally, a Feed Forward Neural Network (FFNN) identifier is used to predict system response to control values and those values adjusted to obtain improved system response. The FFNN is trained offline with extensive test data, and is also adjusted online. Main advantage and uniqueness of the proposed scheme is the controllers ability to complement each other in case of parametric and functional uncertainty. Moreover, the online neural network produces a plant functional approximation. The theoretical results are validated by conducting simulation studies on a single machine infinite bus system for electric generator control.

A novel self-evolving multi-agent architecture for power system monitoring and protection against attacks of malicious intent

In this paper, we propose a novel self-evolving multi-agent methodology (MAM) for power system monitoring and protection. The uniqueness of the proposed architecture is the ability of MAM to evolve in the wake of an attack of malicious intent by mutation and thus always monitoring a power system bus remotely. Also, the architecture interacting with the mutated agents uses a voting methodology thus alleviating the effect of agent malfunction in the presence of attack. This novel architecture is tested on a Single Machine Infinite Bus (SMIB) power network and a two area network with five equivalent generators and eight bus, two area power system for abnormal condition detection and generator bus isolation. Simulation studies indicate that the proposed methodology is capable of not only detecting the power grid attack once, but can also continuously monitor and isolate the generator bus even in the presence of sustained attack as the agents are regenerated.

An approach for temperature and frequency control of a crystal oscillator

This paper presents a new architecture for precise temperature control and stabilization of a crystal oscillator using microcontroller based proportional control and circuit compensation. By precisely controlling the temperature of the frequency-determining element of an oscillator, a very stable signal in the frequency domain is obtained. Additionally, holding the temperature constant at the crystal ldquoturning pointrdquo will minimize the effect on output frequency even when there is a small change in the temperature. The proposed architecture utilizes a temperature control circuit for stabilization, a digital voltage controlled circuit for precise tuning and an output buffer for load balancing and isolation. Main advantage of the proposed architecture is in its ability to precisely track frequency drift and stabilize the temperature variations of the crystal. Simulation results and practical implementations are detailed in the paper.

An intelligent system-centric control approach to power system stabilization using linear adaptive and optimal DHP controller

In this paper, we propose an intelligent approach to power system stabilization using a system-centric controller. This architecture uses a control algorithm based on a supervisory loop concept implemented with a system centric controller combining both a Dual Heuristic Programming (DHP) and Model Reference Adaptive Controller (MRAC) controller. The controller performance is tested on a Single Machine Infinite Bus (SMIB) power network and also on a five generator, eight bus, two area power network. Simulation studies indicate that the proposed controller is capable of improving the stabilization of the generator over the use of MRAC alone while continuously improving its performance through the use of online learning.

Analysis of inter-area mode oscillations using intelligent system-centric controllers

In this paper, we analyze the inter-area mode oscillations in a two-area power system network using a new class of intelligent adaptive control systems based on a system-centric approach used for the control of multiple generators. The proposed architecture consists of a Model Reference Adaptive Controller (MRAC) operating in parallel with a Radial Basis Function Neural Network (RBFNN) to control individual generator oscillations in the presence of disturbances. The underlying structural feature is the introduction of an Intelligent Supervisory Loop (ISL) to augment a conventional adaptive controller. The main advantage is that the proposed architecture provides individual generator control as well as suppresses inter-area mode oscillations in a two area, five machine, eight bus power system network in the presence of torque and fault disturbances.