FACTS; reinforcement learning; power system oscillations; discrete time optimal control; adaptive control
Abstract :
[en] Reinforcement learning consists of a collection of methods for approximating solutions to deterministic and stochastic optimal control problems of unknown dynamics. These methods learn by experience how to adjust a closed-loop control rule which is a mapping from the system states to control actions. This paper proposes an application of reinforcement learning methods to the control of a FACTS device aimed to damp power system oscillations. A detailed case study is carried out on a synthetic four-machine power system.
Disciplines :
Electrical & electronics engineering
Author, co-author :
Ernst, Damien ; Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation
Wehenkel, Louis ; Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation
Language :
English
Title :
FACTS devices controlled by means of reinforcement learning algorithms
Publication date :
2002
Event name :
14th Power Systems Computation Conference (PSCC 2002)
Event place :
Sevilla, Spain
Event date :
June 22-24, 2002
Audience :
International
Main work title :
Proceedings of the 14th Power Systems Computation Conference (PSCC 2002)