An Interactive Insight Identification and Annotation Framework for Power Grid Pixel Maps using DenseU-Hierarchical VAE

TL;DR

This paper introduces an interactive framework using a novel DenseU-Hierarchical VAE to automatically identify and annotate critical insights in power grid pixel maps, improving efficiency and accuracy over manual methods.

Contribution

The paper presents a new DenseU-Hierarchical VAE architecture for large PGPMs and an interactive system for insight discovery and annotation, advancing automated analysis in power grid monitoring.

Findings

Outperforms baseline models in insight identification

Achieves tighter ELBO than existing Hierarchical VAEs

Supports interactive visual exploration and annotation

Abstract

Insights in power grid pixel maps (PGPMs) refer to important facility operating states and unexpected changes in the power grid. Identifying insights helps analysts understand the collaboration of various parts of the grid so that preventive and correct operations can be taken to avoid potential accidents. Existing solutions for identifying insights in PGPMs are performed manually, which may be laborious and expertise-dependent. In this paper, we propose an interactive insight identification and annotation framework by leveraging an enhanced variational autoencoder (VAE). In particular, a new architecture, DenseU-Hierarchical VAE (DUHiV), is designed to learn representations from large-sized PGPMs, which achieves a significantly tighter evidence lower bound (ELBO) than existing Hierarchical VAEs with a Multilayer Perceptron architecture. Our approach supports modulating the derived representations in an interactive visual interface, discover potential insights and create multi-label annotations. Evaluations using real-world PGPMs datasets show that our framework outperforms the baseline models in identifying and annotating insights.