Unsupervised Learning for Equitable DER Control: Preprint

Zhenyi Yuan, Guido Cavraro, Ahmed Zamzam, Jorge Cortes

Research output: Contribution to conferencePaper


In the context of managing distributed energy resources (DERs) within distribution networks (DNs), this work focuses on the task of developing local controllers. We propose an unsupervised learning framework to train functions that can closely approximate optimal power flow (OPF) solutions. The primary aim is to establish specific conditions under which these learned functions can collectively guide the network towards desired configurations asymptotically, leveraging an incremental control approach. The flexibility of the proposed methodology allows to integrate fairness-driven components into the cost function associated with the OPF problem. This addition seeks to mitigate power curtailment disparities among DERs, thereby promoting equitable power injections across the network. To demonstrate the effectiveness of the proposed approach, power flow simulations are conducted using the IEEE 37-bus feeder. The findings not only showcase the guaranteed system stability but also underscore its improved overall performance.
Original languageAmerican English
Number of pages11
StatePublished - 2024
EventPower Systems Computation Conference (PSCC) - Paris, France
Duration: 4 Jun 20247 Jun 2024


ConferencePower Systems Computation Conference (PSCC)
CityParis, France

NREL Publication Number

  • NREL/CP-5D00-89139


  • asymptotic stability
  • DER control
  • equitable control
  • unsupervised learning


Dive into the research topics of 'Unsupervised Learning for Equitable DER Control: Preprint'. Together they form a unique fingerprint.

Cite this