Data quality aware chance-constrained DCOPF: A variational Bayesian Gaussian mixture approach

Xiong Wu*, Xiuli Wang, Chao Duan, Can Dang, Li Yao, Yue Fan, Rui Song

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

The contamination of outliers severely damages the data quality, resulting in the inaccurate data-driven optimisation model. This study proposes a data quality aware chance-constrained model for the direct current optimal power flow (DC-OPF) problem under uncertainties. Under the framework of Bayesian statistics, the variational Bayesian Gaussian mixture model (VBGMM) is employed to extract the probabilistic information from the available historical data, i.e. realisations of random variables. VBGMM can identify the outliers by capturing their probability characteristics, in which way improving the data quality. Notably, VBGMM automatically determines the number of components, which is a remarkable difference from the conventional Gaussian mixture model. In addition, based on the affine policy, a method integrating VBGMM with chance-constrained programming is proposed to make VBGMM scalable. The proposed method is firstly tested on a 6-bus system for an illustrative purpose, and then on a 118-bus system for validating the potential practical application. Comparative studies verify the effectiveness of the proposed method.

Original languageEnglish (US)
Pages (from-to)3412-3421
Number of pages10
JournalIET Generation, Transmission and Distribution
Volume14
Issue number17
DOIs
StatePublished - Sep 4 2020
Externally publishedYes

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Energy Engineering and Power Technology
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Data quality aware chance-constrained DCOPF: A variational Bayesian Gaussian mixture approach'. Together they form a unique fingerprint.

Cite this