GRIDD
Forecasting solar photovoltaic (PV) power production is hard: As clouds move over PV panels, the power output moves up and down rapidly. To keep the energy grid in balance, operators need to have read
Videos
Descripción
### ⚡ Project Title: Gridd — AI-Powered Demand Forecasting & Dispatch Optimizer
### 🌍 Problem
Power grids must perfectly balance supply and demand at every second. Overgeneration wastes energy and burns unnecessary fuel. Undergeneration causes outages. Solar/wind variability makes this harder, and grid operators rely on fossil-fuel "spinning reserves" to stay safe — defeating the point of clean energy.
### 🤖 Solution
We use machine learning to forecast energy demand using public smart meter data and weather inputs, enabling:
• Smarter scheduling of generators (esp. renewables)
• Load-shifting recommendations
• Reduced backup fuel reliance
### 🧱 Stack
• ML: XG Boost and Gradient Boost
• Data: Hugging Face and Open Weather Map
• Backend: Python (Fast API) APIs for model inference
• Frontend: Web dashboard (React
### 🔥 Why It Wins
• Tackles a real, high-impact climate+AI problem
• Works with real public data — extensible across countries
• Bridges consumers, grid ops, and policy needs
• Pitchable to startups, governments, and climate NGOs
Progreso del hackathon
Everything, from the idea's inception to the final product development, was completed during the hackathon's timeframe.
Pila tecnológica
Estado de recaudación de fondos
0