A neural network based power system stabilizer suitable for on-linetraining-a practical case study for EGAT system

This paper presents the development of a neural network based power system stabilizer (PSS) designed to enhance the damping characteristics of a practical power system network representing a part of Electricity Generating Authority of Thailand (EGAT) system. The proposed PSS consists of a neuro-identifier and a neuro-controller which have been developed based on functional link network (FLN) model. A recursive on-line training algorithm has been utilized to train the two neural networks. Simulation results have been obtained under various operating conditions and severe disturbance cases which show that the proposed neuro-PSS can provide a better damping to the local as well as interarea modes of oscillations as compared to a conventional PSS     

An adaptive power system stabilizer using on-line trained neuralnetworks

This paper presents an approach to the design of an adaptive power system stabilizer (PSS) based on on-line trained neural networks. Only the inputs and outputs of the generator are measured and there is no need to determine the states of the generator. The proposed neural adaptive PSS (NAPSS) consists of an adaptive neuro-identifier (ANI), which tracks the dynamic characteristics of the plant, and an adaptive neuro-controller (ANC) to damp the low frequency oscillations. These two subnetworks are trained in an on-line mode utilizing the backpropagation method. The use of a single-element error vector along with a small network simplifies the learning algorithm in terms of computation time. The improvement of the dynamic performance of the system is demonstrated by simulation studies for a variety of operating conditions and disturbances     

An adaptive power system stabilizer based on recurrent neuralnetworks

Application of recurrent, neural networks in the design of an adaptive power system stabilizer (PSS) is presented in this paper. The architecture of the proposed adaptive PSS has two recurrent neural networks. One functions as a tracker to learn the dynamic characteristics of the power plant and the second one functions as a controller to damp the oscillations caused by the disturbances. In the proposed approach, the weights of the neural networks are updated on-line. Therefore, any new information available during actual control of the plant is considered. Simulation studies show that the artificial neural network (ANN) based PSS can provide very good damping over a wide range of operating conditions     

A fuzzy logic based power system stabilizer with learning ability

A fuzzy logic-based power system stabilizer (PSS) with learning ability is proposed in this paper. The proposed PSS employs a multilayer adaptive network. The network is trained directly from the input and the output of the generating unit. The algorithm combines the advantages of artificial neural networks (ANNs) and fuzzy logic control (FLC) schemes. Studies show that the proposed adaptive network-based fuzzy logic PSS (ANF PSS) can provide good damping of power systems over a wide range of operating conditions and improve the dynamic performance of the power system     

An artificial neural network based adaptive power system stabilizer

An artificial neural network (ANN)-based power system stabilizer (PSS) and its application to power systems are presented. The ANN-based PSS combines the advantages of self-optimizing pole shifting adaptive control strategy and the quick response of ANN to introduce a new generation PSS. A popular type of ANN, the multilayer perceptron with error backpropagation training method, is used in this PSS. The ANN was trained by the training data group generated by the adaptive power system stabilizer (APSS). During the training, the ANN was required to memorize and simulate the control strategy of APSS until the differences were within the specified criteria. Results show that the proposed ANN-based PSS can provide good damping of the power system over a wide operating range and significantly improve the dynamic performance of the system     

Application of an inverse input/output mapped ANN as a power systemstabilizer

An artificial neural network (ANN), trained as an inverse of the controlled plant, to function as a power system stabilizer (PSS) is presented in this paper. In order to make the proposed ANN PSS work properly, it was trained over the full working range of the generating unit with a large variety of disturbances. Data used to train the ANN PSS consisted of the control input and the synchronous machine response with an adaptive PSS (APSS) controlling the generator. During training, the ANN was required to memorize the reverse input/output mapping of the synchronous machine. After the training, the output of the synchronous machine was applied as the input of the ANN PSS and the output of the ANN PSS was used as the control signal. Simulation results show that the proposed ANN PSS can provide good damping of the power system over a wide operating range and significantly improve the system performance     

Artificial neural network power system stabilizers in multi-machinepower system environment

The effectiveness of an artificial neural network (ANN), functioning as a power system stabilizer (PSS), in damping multi-mode oscillations in a five-machine power system environment is investigated in this paper. Accelerating power of the generating unit is used as the input to the ANN PSS. The proposed ANN PSS using a multilayer neural network with error-backpropagation training method was trained over the full working range of the generating unit with a large variety of disturbances. The ANN was trained to memorize the reverse input/output mapping of the synchronous machine. Results show that the proposed ANN PSS can provide good damping for both local and inter-area modes of oscillations     

Neural network identification of power system transfer functions

This paper describes an investigation into the use of a multilayered neural network for measuring the transfer function of a power system for use in power system stabilizer (PSS) tuning and assessing PSS damping. The objectives are to quickly and accurately measure the transfer function relating the electric power output to the AVR PSS reference voltage input of a system with the plant operating under normal conditions. In addition, the excitation signal used in the identification procedure is such that it will not adversely affect the terminal voltage or the system frequency. This research emphasized the development of a neural network that is easily trained and robust to changing system conditions. Performance studies of the trained neural network are described. Simulation studies suggest the practical feasibility of the algorithm as a stand-alone identification package and as a portion of a self-tuning algorithm requiring identification in the strategy. The same technique applied to a forward modelling scheme can be used to test the damping contribution from different control strategies     

Transient power characteristic measurement of a proton exchange membrane fuel cell generator

An experimental study on the transient power characteristics of a fuel cell generator has been conducted. The generator is hybridized by a proton exchange membrane (PEM) as the main power source and a lithium-ion battery as the secondary power source. power-conditioning module consisting of a main bidirectional converter and an auxiliary converter has been designed to manage the hybrid power of the generator that copes with fast dynamics of variable loads. Sensors embedded in the generator have measured the electrical properties dynamically. It was found that the present power-conditioning scheme has well controlled the power flow between the fuel cell stack and the battery by regulating the power flow from or to the battery. In addition, the thermal management system using pulse width modulation (PWM) schemes could limit the operation temperature of the fuel cell generator in a designed range. Furthermore, the dynamics of electrical efficiency of the generator are found to be parallel with those of the net system power. Finally, the stability and reliability of the fuel cell generator is proven by the rational dynamic behaviors of thermal and electrical properties for over 30-h demonstration.     

Tuning of power system stabilizers using an artificial neuralnetwork

A new approach using an artificial neural network is proposed to adapt power system stabilizer (PSS) parameters in real time. A pair of online measurements i.e., generator real-power output and power factor which are representative of the generator's operating condition, are chosen as the input signals to the neural net. The outputs of the neural net are the desired PSS parameters. The neural net, once trained by a set of input-output patterns in the training set, can yield proper PSS parameters under any generator loading condition. Digital simulations of a synchronous machine subject to a major disturbance of a three-phase fault under different operating conditions are performed to demonstrate the effectiveness of the proposed neural network     

Performance of a generalized neuron-based PSS in a multimachine power system

An artificial neural network can work as an intelligent controller for nonlinear dynamic systems through learning, as it can easily accommodate the nonlinearities and time dependencies. In dealing with complex problems, most common neural networks have some drawbacks of large training time, large number of neurons and hidden layers. These drawbacks can be overcome by a nonlinear controller based on a generalized neuron (GN) which retains the quick response of neural net. Results of studies with a GN-based power system stabilizer on a five-machine power system show that it can provide good damping over a wide operating range and significantly improve the dynamic performance of the system.     

Dynamic model of wind energy conversion systems with variable speed synchronous generator and full-size power converter for large-scale power system stability studies

This paper presents a dynamic model for variable speed wind energy conversion systems, equipped with a variable pitch wind turbine, a synchronous electrical generator, and a full power converter, specially developed for its use in power system stability studies involving large networks, with a high number of buses and a high level of wind generation penetration. The validity of the necessary simplifications has been contrasted against a detailed model that allows a thorough insight into the mechanical and electrical behavior of the system, and its interaction with the grid. The developed dynamic model has been implemented in a widely used power system dynamics simulation software, PSS/E, and its performance has been tested in a well-documented test power network.     

Robust design of multimachine power system stabilizers usingsimulated annealing

Robust design of multimachine power system stabilizers (PSSs) using simulated annealing (SA) optimization technique is presented in this paper. The proposed approach employs SA to search for optimal parameter settings of a widely used conventional fixed-structure lead-lag PSS (CPSS). The parameters of the proposed simulated annealing based power system stabilizer (SAPSS) are optimized in order to shift the system electromechanical modes at different loading conditions and system configurations simultaneously to the left in the s-plane. Incorporation of SA as a derivative-free optimization technique in PSS design significantly reduces the computational burden. One of the main advantages of the proposed approach is its robustness to the initial parameter settings. In addition, the quality of the optimal solution does not rely on the initial guess. The performance of the proposed SAPSS under different disturbances and loading conditions is investigated for two multimachine power systems. The eigenvalue analysis and the nonlinear simulation results show the effectiveness of the proposed SAPSS's to damp out the local as well as the interarea modes and enhance greatly the system stability over a wide range of loading conditions and system configurations     

基于RBF神经网络的核动力装置故障诊断方法研究

核动力装置是一个高度复杂并具有高度安全性要求的结构体系,其故障检测方法一般采用传统的阈值方法。为克服阈值方法的不足,提出了基于RBF(radial basis function)神经网络的核动力装置故障诊断方法。该方法选择对核动力装置安全具有重要影响的运行参数作为神经网络的输入,并利用核动力装置正常运行模式及典型故障模式的监测数据作为训练样本,网络训练采用正交最小二乘算法(orthogonal least square,OLS)。为了验证所提方法的可行性,利用核动力装置运行监测数据进行检验。结果表明,RBF神经网络成功地诊断出了故障,具有良好的诊断效果。     

Optimal design of power system stabilizers using evolutionary programming

The optimal design of power system stabilizers (PSSs) using evolutionary programming (EP) optimization technique is presented in this paper. The proposed approach employs EP to search for optimal settings of PSS parameters that shift the system eigenvalues associated with the electromechanical modes to the left in the s-plane. Incorporation of EP algorithm in the design of PSSs significantly reduces the computational burden. The performance of the proposed PSSs under different disturbances, loading conditions, and system configurations is investigated for a multimachine power system. The eigenvalue analysis and the nonlinear simulation results show the effectiveness and robustness of the proposed PSSs to damp out the local as well as the interarea modes of oscillations and work effectively over a wide range of loading conditions and system configurations.     

Analytical investigation of factors influencing power systemstabilizers performance

Results of simulations, designed to illustrate the influence of power system stabilizers (PSS) on inter-area and local oscillations in interconnected power systems, are reported. It is shown that the PSS location and the voltage characteristics of the system loads are significant factors in the ability of a PSS to increase the damping of interarea oscillations. It is also shown that an interaction between modes in two distinct parts of a power system is possible, due to resonance, and that this might cause distortions in mode shape and participation factors     

Reducing the effect of penstock pressure pulsations on hydroelectric plant power system stabilizer signals

A characteristic trait of Francis turbines operating at low-head is pressure pulsations that occur during certain load levels of the generator. These stem from pressure variations across the turbine due to pulsating flow in the draft tube. This surging action of the water column is related to draft tube geometry and flow rate of water in the penstock. The pressure pulsations cause torque variations on the turbine and corresponding electric power pulsations. If electric power is used as a feedback signal to the power system stabilizer (PSS), then MVAr and terminal voltage pulsations will occur when the generator is operating in the "rough zone". This paper describes field test results for investigating feedforward control from the penstock, draft tube and spiral case pressure to reduce the effects of MW pulsations on PSS output signals. This investigation involved a PSS with generator power as the feedback signal and the PSS tuned for local and inter-area damping     

Nonlinear control of the doubly-fed induction generator in wind power systems

This paper describes the models of a wind power system, such as the turbine, generator, power electronics converters and controllers, with the aim to control the generation of wind power in order to maximize the generated power with the lowest possible impact in the grid voltage and frequency during normal operation and under the occurrence of faults. The presented work considers a wind power system equipped with the doubly-fed induction generator and a vector-controlled converter connected between the rotor and the grid. The paper presents comparative results between proportional-integral controllers and neural networks based controllers, showing that better dynamic characteristics can be obtained using neural networks based controllers.     

A robust H∞ power system stabilizer with noadverse effect on shaft torsional modes

The H^∞ optimal control theory has been used to design a robust power system stabilizer (PSS) to improve transient and dynamic stabilities of a turbogenerator connected to an infinite busbar. It is demonstrated that the effects of disturbances in the machine output can be minimized and sufficient closed-loop stability margins (robustness) can be obtained to tolerate variations in the loop transfer functions, such as those which might arise from unmodeled low-damped high-frequency modes of oscillations. The resulting controller would effectively enhance the synchronizing and damping torques of the machine without the risk of exciting the shaft torsional modes. This is in marked contrast with the unstable performance of linear quadratic (LQ) optimal controllers under similar conditions. The H^∞ design methodology also ensures a satisfactory performance of the PSS under a wide range of system operating conditions     

Accelerating power versus electrical power as input signals topower system stabilizers

Power system stabilizers (PSSs) using electrical and accelerating power as supplementary signals are compared. The effect on terminal voltage and volt-ampere reactive, offset and damping of a simulated single-machine-infinite-bus system is investigated. The results show that the damping offered by a PSS using accelerating power and electrical power feedback is very similar even in the presence of large mechanical power disturbances. The benefits of accelerating power over electrical power as the supplementary signal to the PSS are not evident in the simulation studies considered. Considering the relative ease of measuring the electrical power signal compared to accelerating power signal, it is concluded that a PSS using electrical power as a supplementary signal is sufficient for damping rotor oscillations. Frequency response data are shown to support this point of view