Historically, centrally computed algorithms have been the primary means of power system
optimization and control. With increasing penetrations of distributed energy resources …

With the increased variability and uncertainty of net load induced from high penetrations of
renewable energy resources and more flexible interchange schedules, power systems are …

The power flow equations relate the power injections and voltages in an electric power
system and are therefore key to many power system optimization and control problems …

This paper proposes a novel model-free/data-driven centralized training and decentralized
execution multi-agent deep reinforcement learning (MADRL) framework for distribution …

Modern distribution grids are currently being challenged by frequent and sizable voltage
fluctuations, due mainly to the increasing deployment of electric vehicles and renewable …

Active distribution networks are being challenged by frequent and rapid voltage violations
due to renewable energy integration. Conventional model-based voltage control methods …

This paper proposes attention enabled multi-agent deep reinforcement learning (MADRL)
framework for active distribution network decentralized Volt-VAR control. Using the …

Accurate knowledge of the distribution system topology and parameters is required to
achieve good voltage control performance, but this is difficult to obtain in practice. This paper …

Large scale integration of variable and uncertain Renewable Generation (RG) in power
systems causes frequent load-generation imbalances. Systems require additional …

The increasing penetration of renewable distributed generation (DG) sources in distribution
networks can lead to violations of network constraints. Thus, significant network …