Mohsen Farahani

Intelligent control of SVC using wavelet neural network to enhance transient stability

In order to enhance transient stability in a power system, a new intelligent controller is proposed to control a Static VAR compensator (SVC) located at center of the transmission line. This controller is an online trained wavelet neural network controller (OTWNNC) with adaptive learning rates derived by the Lyapunov stability. During the online control process, the identification of system is not necessary, because of learning ability of the proposed controller. One of the proposed controller features is robustness to different operating conditions and disturbances. The test power system is a two-area two-machine system power. The simulation results show that the oscillations are satisfactorily damped out by the OTWNNC.

A Multi-Objective Power System Stabilizer

This paper proposes an integrated controller to regulate the terminal voltage of generators as well as to mitigate power system oscillations, instead of employing the combination of the conventional power system stabilizer and automatic voltage regulator. This intelligent controller is an online trained self-recurrent wavelet neural network controller (OTSRWNNC). To achieve the aforementioned objectives, two control errors are simultaneously minimized by updating the parameters of OTSRWNNC. In addition, the adaptive learning rates derived by the discrete Lyapunov theory are used to enhance the convergence speed of proposed controller. The proposed controller does not require any identifier to approximate the dynamic of controlled power system, because of its high learning ability. The performance of proposed controller is evaluated on a single-machine infinite-bus power system and two large power systems. Simulation results and comparative studies demonstrate the effectiveness and robustness of proposed controller in stabilizing power systems in a wide range of loading conditions and different disturbances.

An online trained fuzzy neural network controller to improve stability of power systems

The purpose of this paper is to improve the stability in a power system using a new intelligent controller. This controller is an online trained fuzzy neural network controller (OTFNNC) in which adaptive learning rates derived by the Lyapunov stability are employed to guarantee the convergence of the proposed controller. During the online control process, the identification of system is not necessary, because of learning ability of the proposed controller. One of the proposed controller features is robustness to different operating conditions and disturbances. Moreover, the Prony method is used to obtain the exponential damping of power system oscillations in this paper.The test power system is a two-area four-machine system power. The simulation results show that the oscillations are satisfactorily damped out by the OTFNNC. The proposed approach is effective to mitigate power system oscillations and improve the stability. Literature review show that no method is proposed to compute the damping of power system oscillation if adaptive and online controllers like fuzzy and neural network controller are utilized for damping power system oscillations. In this paper, the damping rate of power system oscillations is estimated by the Prony method.

Damping of subsynchronous resonance using self‐tuning PID and wavelet neural network

Purpose – Subsynchronous resonance (SSR) problem is often created in generator rotor systems with long shafts (non‐rigid shaft) and large inertias constituting a weakly damped mechanical system. When the electrical network resonance frequency (in which the transmission line is compensated by series capacitors) approaches shaft natural frequencies, the electrical system increases torsional torques amplitude on the shaft. The purpose of this paper is to propose a self‐tuning proportional, integral, derivative (PID) controller to damp the SSR oscillations in the power system with series compensated transmission lines.Design/methodology/approach – To accommodate the PID controller in all power system loading conditions, the gradient descent (GD) method and a wavelet neural network (WNN) are used to update the PID gains on‐line. All parameters of the WNN are trained by the gradient descent method using adaptive learning rates (ALRs). The ALRs are derived from discrete Lyapunov stability theorem, which are appl...

Intelligent control of a DC motor using a self-constructing wavelet neural network

This paper proposes an intelligent method to control the speed of a DC motor. This controller is a self-constructing wavelet neural network (SCWNN) in which the self-constructing and training algorithms are simultaneously performed. At first, there are no wavelets in the wavelet layer; they are automatically generated in the online control process. In order to increase the convergence speed of the proposed controller, adaptive learning rates (ALRs) updated at each sampling time are used. In the online control process, no identifier is used to approximate the dynamic of the controlled plant, because of the learning ability of the proposed controller. Several simulations are used to demonstrate the effectiveness and adaptiveness of SCWNN.

Intelligent Control of a Static Synchronous Series Compensator via a Self-tuning Proportional-integral-derivative Controller Based on the Lyapunov Method to Mitigate Inter-Area Oscillations

Abstract In order to mitigate inter-area oscillations in power systems, a new self-tuning method based on the Lyapunov stability theory is proposed to tune parameters of a proportional-integral-derivative controller. The proportional-integral-derivative controller tuned by this method is implemented in on-line mode in order to enhance the damping of a static synchronous series compensator. In addition, an auto-tuning neuron composed of only one neuron is used to approximate the complex dynamic of a controlled power system. A two-area four-machine power system is used to demonstrate the performance of the proposed approach. All the simulations show that the proposed self-tuning proportional-integral-derivative controller can effectively damp out the inter-area oscillations.

On-line Tuning of a Wavelet Neural Proportional-integral Controller for Excitation Control of a Generator

Abstract The effective control of generators needs intelligent techniques and advanced modeling. In this article, a wavelet neural proportional-integral controller, which combines the capabilities of a proportional-integral and wavelet neural network controller, is used to control a turbo-generator connected to an infinite bus via a transmission line. In the structure of the proposed controller, a wavelet neural network is also used to identify the complex non-linear dynamic of a power system. The conventional automatic voltage regulator is replaced by the proposed controller. To demonstrate the ability of the proposed controller, several simulations are performed. The simulation results show that the wavelet neural proportional-integral controller can return the terminal voltage of generator to the pre-specified level with less oscillation under a wide range of loading conditions and different disturbances. In addition, it is shown that unlike the fixed parameters based conventional automatic voltage regulator, the performance of the proposed controller is satisfactory even when the parameters of a power system are varied.

Intelligent power system stabilizer design using adaptive fuzzy sliding mode controller

Abstract This paper proposes an adaptive fuzzy sliding mode controller (AFSMC) with a PI switching surface to damp power system oscillations. To overcome the difficulties in the design of a sliding-mode controller, which are the supposition of known uncertainty bounds and the chattering phenomenon in the control effort, a wavelet neural network (WNN) sliding-mode control system is studied. In the control system of the WNN sliding-mode, a WNN bound observer is developed to adjust the bound of uncertainties in real time. An adaption law is obtained from the Lyapunov stability theory, so the stability of the closed-loop system can be guaranteed. Then, the effectiveness of the AFSMC is studied under different situations of a two-area four-machine power system. The results verify that performance of AFSMC is much better than conventional power system stabilizer (CPSS).

Design of an Intelligent Controller Based on Wavelet Neural Network to Improve the Stability of Power Systems

To damp the oscillations in a power system, a new intelligent controller is proposed. This controller is an online trained wavelet neural network controller (OTWNNC) in which adaptive learning rates derived by the Lyapunov stability are employed to guarantee the convergence of the proposed controller. During the online control process, the identification of system is not necessary, because of learning ability of the proposed controller. One of the proposed controller features is robustness to different operating conditions and disturbances. Moreover, the Prony method is used to obtain the exponential damping of power system oscillations in this paper. The test power system is a two-area four-machine system power. The simulation results show that the oscillations are satisfactorily damped out by the OTWNNC.

Suppression of inter-area oscillations in a multi-machine power system using a new intelligent controller

The purpose of this paper is to improve the stability in a power system using a new intelligent controller. In this paper, a new online control strategy of a static synchronous series compensator SSSC is proposed to improve the transient stability of power systems. In this strategy, an auxiliary damping controller with an adaptive structure is used to generate an essential signal which can enhance the damping of the SSSC. This auxiliary damping controller consists of a Wiener-type neural network controller WNNC. The back propagation BP algorithm is utilized to online training of the WNNC. The Lyapunov method is used to guarantee the stability of WNNC. The test power system is a two-area four-machine system power. The simulation results show that the oscillations are satisfactorily damped out by the WNNC. The proposed approach is effective to mitigate power system oscillations and improve the stability. Since the Lyapunov stability theory is used to obtain the adaptive learning rates, the stability of closed-loop system can be guaranteed. In this case, the overall control scheme has capabilities of learning and adaptiveness.