Mevludin Glavic

TL;DR: In this article, the authors proposed an early detection of voltage instability from the system states provided by synchronized phasor measurements by fitting a set of algebraic equations to the sampled states, and performing an efficient sensitivity computation in order to identify when a combination of load powers has passed through a maximum.

TL;DR: This paper compares reinforcement learning with model predictive control in a unified framework and reports experimental results of their application to the synthesis of a controller for a nonlinear and deterministic electrical power oscillations damping problem.

TL;DR: In this paper, the authors explore how a computational approach to learning from interactions, called reinforcement learning (RL), can be applied to control power systems and discuss some challenges in power system control and discuss how some of those challenges could be met by using these RL methods.

TL;DR: In this article, the ability of three interior-point (IP) based algorithms, namely the pure primal-dual (PD), the predictor-corrector (PC) and the multiple centrality corrections (MCC), to solve various classical OPF problems: minimization of overall generation cost, minimisation of active power losses, maximization of power system loadability and minimizing the amount of load curtailment.

TL;DR: In this paper, the authors review past and very recent research considerations in using reinforcement learning (RL) to solve electric power system decision and control problems, and analyse the perspectives of RL approaches in light of the emergence of new generation, communications, and instrumentation technologies currently in use, or available for future use, in power systems.