Machine Learning-Based Prediction of Distribution Network Voltage and Sensor Allocation

Alvaro Bastos, Surya Santoso, Venkat Krishnan, Yingchen Zhang

Research output: Contribution to conferencePaper

15 Scopus Citations

Abstract

Increasing penetration levels of fast-varying energy resources might negatively affect power system operation. At the same time, sensor deployment throughout distribution networks improves system awareness and enables the development of new and advanced voltage control solutions. Such control techniques rely on accurate prediction in anticipation of voltage violation scenarios. This paper analyzes various approaches to voltage prediction in a distribution system, and it is shown that combining multiple techniques into a single regressor improves its predictive power. Moreover, a two-step regressor is proposed in which initial predictions based on a global regressor are refined by local regressors; in this case, prediction errors decrease significantly. Additionally, a clustering approach is employed to perform sensor allocation so that only the most influential buses are selected for monitoring without diminishing prediction accuracy.
Original languageAmerican English
Number of pages5
DOIs
StatePublished - 2020
Event2020 IEEE Power & Energy Society General Meeting (PESGM) - Montreal, Canada
Duration: 2 Aug 20206 Aug 2020

Conference

Conference2020 IEEE Power & Energy Society General Meeting (PESGM)
CityMontreal, Canada
Period2/08/206/08/20

Bibliographical note

See NREL/CP-5D00-75247 for preprint

NREL Publication Number

  • NREL/CP-5D00-79002

Keywords

  • distributed generation
  • ensemble regressor
  • machine learning
  • sensor allocation
  • voltage prediction

Fingerprint

Dive into the research topics of 'Machine Learning-Based Prediction of Distribution Network Voltage and Sensor Allocation'. Together they form a unique fingerprint.

Cite this