Learning Local Volt/VAR Controllers Toward Efficient Network Operation with Stability Guarantees: Preprint

Guido Cavraro, Zhenyi Yuan, Manish Singh, Jorge Cortes

Research output: Contribution to conferencePaper

Abstract

This paper considers the problem of voltage regulation in distribution network. The primary motivation is to keep voltages within pre-assigned operating limits by commanding the reactive power output of distributed energy resources (DERs) deployed in the grid. We develop a framework for developing local Volt/Var control that comprises of two main steps. In the first, exploiting historical data and for each DER, we learn a function representing desirable equilibrium points for the power network. These points approximate solutions of an Optimal Power Flow problem. In the second, we propose a control scheme for steering the network towards these favorable configurations. Theoretical conditions are derived to formally guarantee the stability of the developed control scheme and numerical simulations illustrate the effectiveness of the proposed approach.
Original languageAmerican English
Number of pages10
StatePublished - 2022
Event61st IEEE Conference on Decision and Control - Cancun, Mexico
Duration: 6 Dec 20229 Dec 2022

Conference

Conference61st IEEE Conference on Decision and Control
CityCancun, Mexico
Period6/12/229/12/22

NREL Publication Number

  • NREL/CP-5D00-83750

Keywords

  • data-driven control
  • local control
  • neural networks
  • reactive power
  • voltage control

Fingerprint

Dive into the research topics of 'Learning Local Volt/VAR Controllers Toward Efficient Network Operation with Stability Guarantees: Preprint'. Together they form a unique fingerprint.

Cite this