Data Enrichment Opportunities for Distribution Grid Cable Networks using Variational Autoencoders
This addresses data scarcity for utility companies managing distribution grids, but it is incremental as it builds on existing VAE methods without major breakthroughs.
The study tackled incomplete data in electricity distribution cable networks by applying Variational Autoencoders for tasks like imputing missing age information, showing potential for data-driven maintenance in a Denmark case study, though it noted areas for improvement without providing concrete numerical results.
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.