Single Network Adaptive Critic Design for Power System Stabilizers (original) (raw)
Related papers
Single network adaptive critic design for power system stabilisers
IET Generation, Transmission & Distribution, 2009
The recently developed single network adaptive critic (SNAC) design has been used in this study to design a power system stabiliser (PSS) for enhancing the small-signal stability of power systems over a wide range of operating conditions. PSS design is formulated as a discrete non-linear quadratic regulator problem. SNAC is then used to solve the resulting discrete-time optimal control problem. SNAC uses only a single critic neural network instead of the action-critic dual network architecture of typical adaptive critic designs. SNAC eliminates the iterative training loops between the action and critic networks and greatly simplifies the training procedure. The performance of the proposed PSS has been tested on a single machine infinite bus test system for various system and loading conditions. The proposed stabiliser, which is relatively easier to synthesise, consistently outperformed stabilisers based on conventional lead-lag and linear quadratic regulator designs.
2007
Power system stabilizers are widely used to damp out the low frequency oscillations in power systems. In power system control literature, there is a lack of stability analysis for proposed controller designs. This paper proposes a Neural Network (NN) based stabilizing controller design based on a sixth order single machine infinite bus power system model. The NN is used to compensate the complex nonlinear dynamics of power system. To speed up the learning process, an adaptive signal is introduced to the NN's weights updating rule. The NN can be directly used online without offline training process. Magnitude constraint of the activators is modeled as saturation nonlinearities and is included in the stability analysis. The proposed controller design is compared with Conventional Power System Stabilizers whose parameters are optimized by Particle Swarm Optimization. Simulation results demonstrate the effectiveness of the proposed controller design.
Robust Control Design of Power System Stabilizer Using Artificial Neural Networks
One of the important issues in power systems dynamics is stabilizing by means of the power system stabilizer (PSS). In this paper, an optimal method for designing an artificial neural network (ANPSS) is presented. The main advantage of this method is the robustness to the system parameters variations such as load and governor parameters. The use of ANNPSS also causes the system dynamical behavior is improve remarkably. This method uses a suitable signal as an input signal for PSS. The used neural network is a feed forward artificial neural network with a learning algorithm which has the error back propagation. The learning network data is obtained using the classic power system stabilizer (CPSS). The proposed method of ANPSS design is simulated on a test system. The results are compared with results of system with CPSS. The results show that the system with ANNPSS is capable of stabilizing the system under different situations of the parameters variations of the power system.
An optimal adaptive power system stabilizer
199 IEEE Power Engineering Society Summer Meeting. Conference Proceedings (Cat. No.99CH36364), 1999
Power system operation is characterized by the random variation of load conditions, continuous change in generation schedule and network interconnections. Also, power systems are subject to different exogenous disturbances. An adaptive optimal controller is highly desirable to enhance the performance and guarantee stability under such complicated conditions.
An adaptive power system stabilizer using on-line trained neural networks
IEEE Transactions on Energy Conversion, 1997
This paper presents an approach t o 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 t o 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. K e y w o r d s -P o w e r System Stabilizer, Neural Networks, On-line Training, Indirect Adaptive Control.
Neural network based power system stabilizers
1993
Novel power system artificial neural network (ANN) based power system stabilizers (PSSs) are presented. The two ANN-PSS designs are driven by the speed error and its rate of change. Other supplementary stabilizing signals such as voltage deviation, excursion error, and PSS output rate of change are utilized to ensure the best matching between the ANN-PSS design and the optimized conventional analog PSS benchmark model. The use of ANN based PSSs is motivated by their noise rejection and robustness under varying network topologies, loading conditions, parametric variations, and model uncertainties
Tehnicki vjesnik - Technical Gazette
Electrical power systems usually suffer from instabilities because of some disturbances occurring due to environmental conditions, system failures, and loading conditions. The most frequently encountered problem is the loss of synchronization between the rotor angle and the stator magnetic angle for synchronous generators. The contribution of this study is that a nonlinear adaptive control approach called feedback error learning (FEL) is utilized to improve the small-signal stabilities of an electric power system. The power system under study is composed of a synchronous machine connected to infinite bus. Many advantages of FEL control approach makes it capable to robustly adapting with all possible operating conditions rather than using optimization algorithms for tuning the conventional power system stabilizer (CPSS) that is still unsatisfactory especially at some critical operating points. The performances of two controllers, namely the proposed FEL scheme and the conventional controller CPSS, are tested by Matlab simulations. It is found that the FEL controller can be effectively used as an alternative stabilizer for improving small-signal stabilities of the power system.
Neural network stabilizing control of single machine power system with control limits
2004
Power system stabilizers are widely used to generate supplementary control signals for the excitation system in order to damp out the low frequency oscillations. This paper proposes a stable neural network (NN) controller for the stabilization of a single machine infinite bus power system. I n the power system control literature, simplified analytical models are used to represent the power system and the controller designs are not based on rigorous stability analysis. This paper overcomes the two major problems by using an accurate analytical model for controller development and presents the closed-loop stability analysis. The NN is used to approximate the complex nonlinear power system online and the weights of which can he set to zero to avoid the time consuming offline training process. Magnitude constraint of the activators is modeled as saturation nonlinearities and is included in the Lyapnnov stability analysis. Simulation results demonstrate that the proposed design can successfully damp oot oscillations. The control algorithms of this paper can also be applied to other similar control problems.
Power system stabilizer based on artificial neural network
2011 International Conference on Power and Energy Systems, 2011
This paper describes a systematic approach for designing a self-tuning adaptive power system stabilizer (PSS) based on artificial neural network (ANN). An ANN is used for selftuning the parameters of PSS e.g. stabilizing gain K stab and time constant (T1) for Lead PSS in realtime. The inputs to the ANN are generator terminal active power (P) and reactive power (Q). Investigations are carried out to assess the dynamic performance of the system with selftuning PSS based on ANN (ST-ANNPSS) over a wide range of loading conditions. The simulations are performed using Matlab/Simulink's neural network toolbox. The simulation and experimental results demonstrate the effective dynamic performance of the proposed system. Keywords-power system stabilizer, Artificial Neural Network (ANN), Kstab and T 1 .
Adaptive Critic Designs for Optimal Control of Power Systems
Proceedings of the 13th International Conference on, Intelligent Systems Application to Power Systems
The increasing complexity of the modern power grid highlights the need for advanced modeling and control techniques for effective control of excitation, turbine and Flexible AC Transmission Systems (FACTS). The crucial factors affecting the modern power systems today is voltage and load flow control. Simulation studies in the PSCAD/EMTDC environment and realtime laboratory experimental studies carried out are described and the results show the successful control of the power system elements and the entire power system with adaptive and optimal neurocontrol schemes. Performances of the neurocontrollers are compared with the conventional PI controllers for damping under different operating conditions for small and large disturbances.