README.md

metadata

title: FBMC Chronos-2 Forecasting
emoji: ⚡
colorFrom: blue
colorTo: green
sdk: gradio
sdk_version: 4.44.0
app_file: app.py
pinned: false
tags:
  - forecasting
  - time-series
  - electricity
  - zero-shot
suggested_hardware: a100-large
suggested_storage: small

FBMC Flow-Based Market Coupling Forecasting API

Zero-shot electricity cross-border flow forecasting for 38 European FBMC borders using Amazon Chronos-2.

🚀 Quick Start

This HuggingFace Space provides a Gradio API for GPU-accelerated zero-shot forecasting.

How to Use (Web Interface)

1. Select run date: Choose the forecast date (YYYY-MM-DD format)
2. Choose forecast type:
   • Smoke Test: 1 border × 7 days (~30 seconds)
   • Full Forecast: All 38 borders × 14 days (~5 minutes)
3. Click "Run Forecast"
4. Download results: Parquet file with probabilistic forecasts

How to Use (Python API)

from gradio_client import Client

client = Client("evgueni-p/fbmc-chronos2")
result_file = client.predict(
    run_date="2025-09-30",
    forecast_type="smoke_test"
)

# Download and analyze locally
import polars as pl
df = pl.read_parquet(result_file)
print(df.head())

📊 Dataset

Source: evgueni-p/fbmc-features-24month

• Rows: 17,880 hourly observations

• Date Range: Oct 1, 2023 - Oct 14, 2025

• Features: 2,553 engineered features

  • Weather: 375 features (52 grid points)
  • ENTSO-E: ~1,863 features (generation, demand, prices, outages)
  • JAO: 276 features (CNEC binding, RAM, utilization, LTA, net positions)
  • Temporal: 39 features (hour, day, month, etc.)

• Targets: 38 FBMC cross-border flows (MW)

🔬 Model

Amazon Chronos 2 (120M parameters)

• Pre-trained foundation model for time series
• Zero-shot inference (no fine-tuning)
• Multivariate forecasting with future covariates
• Dynamic time-aware data extraction (prevents leakage)

⚡ Hardware

GPU: NVIDIA A10G (24GB VRAM)

• Model inference: ~5 minutes for complete 14-day forecast
• Recommended for production workloads

📈 Performance Target

D+1 MAE Goal: <150 MW per border

This is a zero-shot baseline. Fine-tuning (Phase 2) expected to improve accuracy by 20-40%.

🔐 Requirements

Set HF_TOKEN in Space secrets to access the private dataset.

🛠️ Technical Details

Feature Availability Windows

The system implements time-aware forecasting to prevent data leakage:

• Full-horizon D+14 (603 features): Weather, CNEC outages, LTA
• Partial D+1 (12 features): Load forecasts (masked D+2-D+14)
• Historical only (1,899 features): Prices, generation, demand

Dynamic Forecast System

Uses DynamicForecast module to extract context and future covariates based on run date:

• Context window: 512 hours (historical data)
• Forecast horizon: 336 hours (14 days)
• Automatic masking for partial availability

📚 Documentation

• Project Repository
• Activity Log
• Feature Engineering Details

🔄 Phase 2 Roadmap

Future improvements (not included in zero-shot MVP):

• Fine-tuning on FBMC data
• Ensemble methods
• Probabilistic forecasting
• Real-time data pipeline
• Production API

👤 Author

Evgueni Poloukarov

📄 License

MIT License - See LICENSE file for details

---

Last Updated: 2025-11-14 Version: 1.0.0 (Zero-Shot MVP)