Conference Paper

Design a Robust and Adaptive Reinforcement Learning Based SVC Controller for Damping Enhancement in Power Systems.

DOI: 10.1007/978-3-540-30133-2_98 Conference: Knowledge-Based Intelligent Information and Engineering Systems, 8th International Conference, KES 2004, Wellington, New Zealand, September 20-25, 2004. Proceedings. Part II
Source: DBLP

ABSTRACT This paper proposes a reinforcement learning based SVC controller to improve the damping of power systems in the presence
of load model parameters uncertainty. The proposed method is trained over a wide range of typical load parameters in order
to adapt the gains of the SVC stabilizer. The simulation results show that the tuned gains of the SVC stabilizer using reinforcement
learning can provide better damping than the conventional fixed-gains SVC stabilizer. To evaluate the usefulness of the proposed
method, we compare the response of this method with PD controller. The simulation results show that our method has the better
control performance than PD controller.

1 Read
  • [Show abstract] [Hide abstract]
    ABSTRACT: The paper explores the influence of power system loads on static VAr compensator (SVC) damping effectiveness. Equipped with properly tuned additional stabilizers, SVCs have been successfully used for improving the damping of electromechanical oscillations in power systems. The damping improvement is usually achieved through indirect voltage influence through voltage dependent loads. Tuning of an additional compensator stabiliser (ACS) traditionally assumes that loads are statically voltage dependent. However, load parameters are generally uncertain and loads often exhibit same dynamic response. This uncertain dynamic behaviour of loads can introduce an additional phase shift between voltage and load response and such can detune the ACS. Examples of detuning effects of dynamic loads as well as robust tuning of ACS are presented and discussed
    IEEE Transactions on Power Systems 12/1998; DOI:10.1109/59.736268 · 2.81 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: A scheme using fuzzy logic control (FLC) is proposed to form a supplementary damping loop for the static VAr compensator (SVC) to increase the transmission capacity. Design of the FLC supplementary loop is based on transient energy analysis for damping a certain mode of inter-area oscillations. A genetic algorithm (GA) is used to tune the rules and membership functions needed in the FLC scheme. Simulation results have shown considerable damping improvements from the proposed schemes in the study system during the postfault period
    Advances in Power System Control, Operation and Management, 1997. APSCOM-97. Fourth International Conference on (Conf. Publ. No. 450); 12/1997
  • [Show abstract] [Hide abstract]
    ABSTRACT: A novel approach using an artificial neural network (ANN) for tuning a static var compensator (SVC) controller over a wide range of load models is presented in this paper. To enhance power system damping over a wide range of load models, it is desirable to adapt the SVC controller gain in real time based on load models. To do this, online measurements of load parameters which are representative of load models are chosen as the input signals to the neural network. The output of the neural network is the desired gain of the SVC controller. The neural network, once trained by a set of input-output patterns in the training set, can yield a proper SVC controller gain under any load model. Simulation results show that the tuning gain of a SVC controller using the ANN approach can provide better damping of the power system over a wide range of load models than the fixed-gain controller.
    Electric Power Systems Research 08/1996; 38(2-38):97-104. DOI:10.1016/S0378-7796(96)01067-X · 1.75 Impact Factor
Show more