Conference Paper

Radial basis function network based power system stabilizers for multimachine power systems

Dept. of Electr. Eng., King Fahd Univ. of Pet. & Miner., Dhahran
DOI: 10.1109/ICNN.1997.616093 Conference: Neural Networks,1997., International Conference on, Volume: 2
Source: IEEE Xplore


A radial basis function network (RBFN) based power system
stabilizer (PSS) is presented in this paper to improve the dynamic
stability of multimachine power systems. The proposed RBFN is trained
over a wide range of operating conditions in order to re-tune the
parameters of the PSS in real-time. Time domain simulations of a
multimachine power system with different operating conditions subject to
a three phase fault are studied and investigated. The performance of the
proposed RBFN PSS is compared to that of conventional power system
stabilizer (CPSS). The results show the good damping characteristics of
the proposed RBFN PSS over a wide range of operating conditions

2 Reads
  • Source
    • "A wide range of PSS tuning approaches has been recommended. These approaches have included pole placement [2], damping torque concepts [3], H 1 [4], variable structure [5], and the different optimization and artificial intelligence techniques [6] [7] [8]. However, PSS may adversely affect voltage profile and may not be able to arrest oscillations resulting from severe disturbances, such as three-phase faults at generator terminals [9]. "
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents dynamic model of power system installed with a novel UPFC that consist of two shunt converters and a series capacitor. In this configuration, a series capacitor is used between two shunt converters to inject desired series voltage. As a result, it is possible to control the active and reactive power flow. The main advantage of the proposed UPFC in comparison with the conventional configuration is injection of a series voltage waveform with a very low total harmonic distortion (THD). In addition, a linearized Phillips–Heffron model is obtained and a supplementary controller for the modeling of proposed UPFC to damp low frequency oscillations with considering four alternative damping controllers is recommended. The problem of robustly novel UPFC based damping controller is formulated as an optimization problem according to the time domain-based objective function, which are solved using particle swarm optimization (PSO) and Imperialist Competitive Algorithm (ICA) techniques.
    Ain Shams Engineering Journal 09/2014; 5(3). DOI:10.1016/j.asej.2014.01.003
  • Source
    • "In hidden neuron activation it is determined by a nonlinear function of the distance between the input vector and a reference vector. The RBF has a simple architecture, consisting two layers of weights (W E and W S ), where the first one contains the radial bases functions parameters and the second form linear combinations of the function's radial base activations to generate the output [4]. It is trained in two periods, with the functions of radial base being determined first for not-supervised techniques, using for "
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents a parameter modeling to Power System Stabilizers (PSS) using MLP and RBF neural networks. The application of neural networks in PSS aims to improve the dynamic stability of electric power systems by reducing the machine eletromechanic damping oscillation when a disturbance occurs. According to the current plant operating conditions, the PSS parameters are automatically adjusted by the neural network in sense to give a satisfactory control. The observed performance for the proposed approach is tested in simulations, using a nonlinear dynamic model of infinite bus machine-type. The results show that it is possible to improve the power system dynamic performance with the new modeling. In this paper two modeling forms for PSS's parameters using neural networks are proposals: MLP - Multi Layer Perceptron and RBF - Radial Basis Function. The use of a neural network for parameters adjustment becomes possible the practical implementation of the method and the parameters adequacy for different operation points. The neural network advantage it is in the diverse of operations points since it operates with inexact data and not total defined situations.
  • Source
    • "A wide spectrum of PSS tuning approaches has been proposed. These approaches have included damping torque concepts [1], H ∞ [2], and variable structure [3], and the different optimization and artificial intelligence techniques [4]-[5]. FACTS devices have shown very promising results when used to improve power system steady-state performance. "
    [Show abstract] [Hide abstract]
    ABSTRACT: The use of the supplementary controllers of a unified power flow controller (UPFC) to damp low frequency oscillations is investigated. The potential of the UPFC supplementary controllers to enhance the dynamic stability is evaluated by measuring the electromechanical controllability through singular value decomposition (SVD) analysis. Individual designs of the UPFC controllers using particle swarm optimization (PSO) technique are discussed. A nonlinear, time-domain objective function is considered. The effectiveness of the proposed controllers on damping low frequency oscillations is tested through eigenvalue analysis and non-linear time simulation. For comparison, power system stabilizer (PSS) performance is also included.
    GCC Conference (GCC), 2006 IEEE; 01/2006
Show more