intelligent control; reinforcement learning; control lyapunov functions
Abstract :
[en] This text complements material presented in [1,2] where the opportunity to make power system controls with increased capabilities by synergetic fusion of the domain-specific knowledge and the methodologies from control theory and artificial intelligence, is presented. The particular approach in [1,2] considered combination of Control Lyapunov Functions (CLF), a constructive control technique, and Reinforcement Learning (RL) to optimize a mix of system stability and performance. Domain specific knowledge is used to derive CLF for power systems as well as reward in RL. Furthermore, this text position the approach as constructive intelligent control for damping power system electromechanical oscillations. Two control schemes are proposed and the capabilities of the resulting controllers are illustrated on a control problem involving a Thyristor Controlled Series Capacitor (TCSC) for damping oscillations in a four-machine power system.
Disciplines :
Electrical & electronics engineering
Author, co-author :
Glavic, Mevludin ; Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Smart grids
Language :
English
Title :
A Constructive Intelligent Power System Damping Control