IEEE VIS 2024 Content: ChatGrid: Power Grid Visualization Empowered by a Large Language Model

ChatGrid: Power Grid Visualization Empowered by a Large Language Model



Sichen Jin - Georgia Institute of Technology, Atlanta, United States

 Shrirang Abhyankar - Pacific Northwest National Laboratory, Richland, United States

 Room: Bayshore VI

2024-10-14T16:00:00ZGMT-0600Change your timezone on the schedule page
2024-10-14T16:00:00Z

Exemplar figure, described by caption below — ChatGrid interface displaying the visualization and query interface. Queries asked by users are responded through both text and visualization. The vertical bars represent the generation sources that have a remaining capacity greater than 100 MW.

Fast forward

Abstract

This paper presents a novel open system, ChatGrid, for easy, intuitive, and interactive geospatial visualization of large-scale transmission networks. ChatGrid uses state-of-the-art techniques for geospatial visualization of large networks, including 2.5D map views, animated flows, hierarchical and level-based filtering and aggregation to provide visual information in an easy, cognitive manner. The highlight of ChatGrid is a natural language query based interface powered by a large language model (ChatGPT) that offers a natural and flexible interactive experience whereby users can ask questions and ChatGrid provides responses both in text and visually. This paper discusses the architecture, implementation, design decisions, and usage of large language models for ChatGrid.