loading page

Denoising with Singular Value Decomposition for Phase Identification in Power Distribution Systems
  • Nicholas Zaragoza ,
  • Vittal Rao
Nicholas Zaragoza
Texas Tech University, Texas Tech University, Texas Tech University

Corresponding Author:[email protected]

Author Profile
Vittal Rao
Author Profile

Abstract

Phase identification is the problem of determining what phase(s) that a load is connected to in a power distribution
system. However, real world sensor measurements used for phase identification have some level of noise that can hamper the ability to identify phase connections using data driven methods. Knowing the phase connections is important to keep the distribution system balanced so that parts of the system aren’t overloaded which can lead to inefficient operations, accelerated component degradation, and system destruction at worst. We use Singular Value Decomposition (SVD) with the optimal Singular Value Hard Threshold (SVHT) as part of a feature engineering pipeline to denoise data matrices of voltage magnitude measurements. This approach results in a reduction in frobenius error and an increase in average phase identification accuracy over a year of time series data. K-medoids clustering is used on the denoised voltage magnitude measurements to perform phase identification.