[en] This paper proposes an application of a Reinforcement Learning (RL) method to the control of a dynamic brake aimed to enhance power system transient stability. The control law of the resistive brake is in the form of switching strategies. In particular, the paper focuses on the application of a model based RL method, known as prioritized sweeping, a method proven to be suitable in applications in which computation is considered to be cheap. The curse of dimensionality problem is resolved by the system state dimensionality reduction based on the One Machine Infinite Bus (OMIB) transformation. Results obtained by using a synthetic four-machine power system are given to illustrate the performances of the proposed methodology.
Kundur, P., (1994) Power System Stability and Control, , McGraw Hill
Lubkeman, D.L., Heydt, G.T., The application of dynamic programming in a discrete supplementary control for transient stability enhancement of multimachine power system (1985) IEEE Trans. on PAS, PAS-104 (9), pp. 2342-2348. , Sept
Pavella, M., Ernst, D., Ruiz-Vega, D., (2000) Transient Stability of Power System - A Unified Approach to Assessment and Control, , KAP
De Tuglio, E., Dicorato, M., La Scala, M., Scarpellini, P., A corrective control for angle and voltage stability enhancement on the transient time-scale (2000) IEEE Trans. on Power Systems, 15 (4), pp. 1345-1353
State of the art in non classical means to improve power system stability (1988) Electra, (118), pp. 87-113. , CIGRE SC38-WG02, May
Druet, C., Ernst, D., Wehenkel, L., Application of reinforcement learning to electrical power system closed-loop emergency control Proc. 2000 PKDD2000, pp. 86-95. , Lyon, France
Li, B.H., Wu, Q.H., Learning coordinated fuzzy logic control of dynamic quadrature boosters in multimachine power systems (1999) IEE Part C-generation, Transmission, and Distribution, 146 (6), pp. 577-585
Ernst, D., Wehenkel, L., FACTS devices controlled by means of reinforcement learning algorithms Proc. 2002 14-th PSCC, , Sevilla, Spain, Paper 18-6
You, H., Vittal, V., Jung, J., Liu, C.C., Amin, M., Adapa, R., An intelligent adaptive load shedding scheme Proc. 2002 14-th PSCC, , Sevilla, Spain, Paper 17-6
Imthias Ahamed, T.P., Nagendra Rao, P.S., Sastry, P.S., A reinforcement learning approach to automatic generation control (2002) Electric Power Systems Research, 63, pp. 9-26. , Aug
Moore, A.W., Atkeson, C.G., Prioritized sweeping: Reinforcement learning with less data and less real time (1993) Machine Learning, 13, pp. 103-130
Sutton, R.S., Barto, A.G., (1998) Reinforcement Learning: An Introduction, , MIT Press
Bellman, R., (1957) Dynamic Programming, , Princeton University Press
Atkeson, C.G., Santamaria, J.C., A Comparison of direct and model-based reinforcement learning (1997) International Conference on Robotics and Automation, , http://www.cc.gatech.edu/fac/Chris.Atkeson/publications.html, [Online]
Xue, Y., (1988) A New Method for Transient Stability Assessment and Preventive Control of Power System, , PhD Thesis, University of Liège, Belgium
Joshi, S.S., Tamaskar, D.G., Augmentation of transient stability limit of a power system by automatic multiple application of dynamic braking (1985) IEEE Trans. on PAS, PAS-104 (11), pp. 3004-3012
Jiang, H., Habelter, D.T., Eckroth, K.V., A cost effective generator brake for improved generator transient response (1994) IEEE Trans. on Power Syst., 9 (4), pp. 1840-1846
Wang, Y., Mittelstadt, W., Maratukulam, D.J., Variable structure braking resistor control in a multimachine power system (1994) IEEE Trans. on Power Syst., 9 (3), pp. 1557-1562
Katsikopoulos, K.V., Engelbrecht, S.E., Markov Decision Process with delays and asynchronous cost collection (2003) IEEE Transactions on Automatic Control, 48 (4), pp. 568-574
