Constrained Intelligent Frequency Control in an AC Microgrid: An Online Reinforcement Learning Based PID Tuning Approach

K. Nosrati, A. Tepljakov, E. Petlenkov, V. Skiparev, J. Belikov, Y. Levron

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Variable output power in isolated microgrids (MGs) threatens frequency stability and may even degrade power quality. In response, intelligent control methods have been developed and applied to frequency deviation control systems with excellent results. Nevertheless, a potential problem is that the application of such advanced techniques with a large search space is not enough to deal with highly dynamic environment and real-time operations of MGs. In this light, the present study introduces a flexible artificial neural network (ANN)-based frequency deviation control solution in a constrained structure that operates as follows. First, the stable controller parameter space of the PID-based AC microgrid is derived by using the stability boundary locus method. Then, the controller parameters are tuned and updated online by searching for an optimal combination of the coefficients with consideration of output variations sensed by a constrained ANN in the derived reduced parameter space. To accomplish this step, a reinforcement learning technique is applied to train the ANN-based tuners. The performance of the proposed technique has been verified under a given scenario to demonstrate how the reduced parameter space should facilitate the optimization procedure.

Original languageEnglish
Title of host publication2023 IEEE Power and Energy Society General Meeting, PESGM 2023
ISBN (Electronic)9781665464413
DOIs
StatePublished - 2023
Event2023 IEEE Power and Energy Society General Meeting, PESGM 2023 - Orlando, United States
Duration: 16 Jul 202320 Jul 2023

Publication series

NameIEEE Power and Energy Society General Meeting
Volume2023-July

Conference

Conference2023 IEEE Power and Energy Society General Meeting, PESGM 2023
Country/TerritoryUnited States
CityOrlando
Period16/07/2320/07/23

Keywords

  • AC microgrid
  • Constrained neural networks
  • Load frequency control
  • Reinforcement learning

All Science Journal Classification (ASJC) codes

  • Energy Engineering and Power Technology
  • Electrical and Electronic Engineering
  • Nuclear Energy and Engineering
  • Renewable Energy, Sustainability and the Environment

Fingerprint

Dive into the research topics of 'Constrained Intelligent Frequency Control in an AC Microgrid: An Online Reinforcement Learning Based PID Tuning Approach'. Together they form a unique fingerprint.

Cite this