Data Enrichment Opportunities for Distribution Grid Cable Networks using Variational Autoencoders

TL;DR

This paper explores using Variational Autoencoders to enrich and impute missing data in distribution grid cable networks, aiming to improve predictive maintenance and reliability assessments.

Contribution

It demonstrates the potential of VAEs for data imputation and synthetic data generation in distribution grid applications, highlighting areas for further enhancement.

Findings

VAEs can effectively impute missing cable age data

Synthetic data generation supports data balancing

Identifies limitations and future directions for VAE applications

Abstract

Electricity distribution cable networks suffer from incomplete and unbalanced data, hindering the effectiveness of machine learning models for predictive maintenance and reliability evaluation. Features such as the installation date of the cables are frequently missing. To address data scarcity, this study investigates the application of Variational Autoencoders (VAEs) for data enrichment, synthetic data generation, imbalanced data handling, and outlier detection. Based on a proof-of-concept case study for Denmark, targeting the imputation of missing age information in cable network asset registers, the analysis underlines the potential of generative models to support data-driven maintenance. However, the study also highlights several areas for improvement, including enhanced feature importance analysis, incorporating network characteristics and external features, and handling biases in missing data. Future initiatives should expand the application of VAEs by incorporating semi-supervised learning, advanced sampling techniques, and additional distribution grid elements, including low-voltage networks, into the analysis.