Improving Supervised Phase Identification Through the Theory of Information Losses

TL;DR

This paper introduces two novel information-theoretic techniques to enhance supervised phase identification in power systems, significantly boosting accuracy and leveraging system properties for better data representation.

Contribution

It develops data selection and representation methods based on information theory, improving supervised learning accuracy in phase identification tasks.

Findings

Accuracy improved from 51.7% to 97.3% in experiments

Techniques outperform existing methods on real datasets

Applicable to other problems with similar physical properties

Abstract

This paper considers the problem of Phase Identification in power distribution systems. In particular, it focuses on improving supervised learning accuracies by focusing on exploiting some of the problem's information theoretic properties. This focus, along with recent advances in Information Theoretic Machine Learning (ITML), helps us to create two new techniques. The first transforms a bound on information losses into a data selection technique. This is important because phase identification data labels are difficult to obtain in practice. The second interprets the properties of distribution systems in the terms of ITML. This allows us to obtain an improvement in the representation learned by any classifier applied to the problem. We tested these two techniques experimentally on real datasets and have found that they yield phenomenal performance in every case. In the most extreme case, they improve phase identification accuracy from $51.7\%$ to $97.3\%$. Furthermore, since many problems share the physical properties of phase identification exploited in this paper, the techniques can be applied to a wide range of similar problems.