Inspiration
We were inspired by a 2036-scale problem: AI and data centres are growing faster than local grid capacity, so we need better ways to plan demand, generation, and infrastructure together.
What it does
GRID is a geospatial digital simulator that shows substation stress over time, lets users place proposed data centres and wind farms, simulates grid impact, and generates a viability report with sustainability-focused metrics.
How we built it
We built a CesiumJS frontend for 3D grid visualization and scenario placement, a Python/Flask backend for APIs, and a scoring/report engine that processes 7-day grid data, computes performance metrics, and produces PDF outputs.
Challenges we ran into
Data quality and alignment were hard: matching substation names/locations, handling inconsistent time-series data, and balancing model realism with hackathon speed and usability.
Accomplishments that we're proud of
We delivered an end-to-end working prototype: real data ingestion, interactive what-if simulation, clear viability statuses, renewable offset modeling, and automated evidence-backed reporting.
What we learned
We learned that sustainability decisions need both strong technical modeling and clear communication. A transparent tool that planners can trust is as important as algorithm accuracy.
What's next for GRID
Next, we plan to improve forecasting and weather-linked renewable modeling, add deeper power-flow constraints, support more regions, and build collaboration features for planners, operators, and policymakers.
Built With
- cesium
- flask
- javascript
- national-grid
Log in or sign up for Devpost to join the conversation.