Quote of the day

A person who never made a mistake never tried anything new.

- Albert Einstein

Contact

Time-Series Foundation Models for Few-Shot Probabilistic Forecasting at New Renewable Sites

Open Energy

Time-Series Foundation Models for Few-Shot Probabilistic Forecasting at New Renewable Sites

Time-Series Foundation Models for Few-Shot Probabilistic Forecasting at New Renewable Sites

Description

Evaluate whether time-series foundation models can deliver reliable probabilistic forecasts for newly commissioned renewable-energy sites with very limited operating history.

Details

Context and Problem Statement

Wind and solar forecasting models often require years of site-specific history. Newly commissioned plants therefore have poor forecasts precisely when operational support is most needed.

Research Question

After how many weeks of site history does a calibrated time-series foundation model outperform local statistical models, and are its prediction intervals sufficiently calibrated for balancing decisions?

Proposed Approach

Compare time-series foundation models with statistical and locally trained deep baselines, add meteorological exogenous variables, apply conformal recalibration, and evaluate using CRPS and quantile coverage.

Expected Contribution

A characterization of the low-history regime in which foundation models provide genuine benefit and a practical recalibration methodology.

Expected Prototype

A day-ahead probabilistic forecasting service with continuous calibration monitoring and automatic model selection.

Datasets

ERA5, open wind and solar generation datasets, and partner production series.

Challenges

Possible pre-training contamination, inference cost, non-stationarity, outages, and lack of long reference histories for new sites.

Research Question

Do time-series foundation models provide a measurable and well-calibrated advantage for renewable-generation forecasting under severe data scarcity?

Innovation

The project targets newly commissioned renewable assets and evaluates probabilistic calibration rather than relying only on point-error metrics.

Expected Deliverable

A reproducible benchmark, a probabilistic forecasting service, and an analysis of the history thresholds at which different model families become preferable.

Technologies

Time-Series Foundation Models (Chronos, Moirai) Probabilistic Forecasting and Proper Scoring Rules Conformal Prediction Meteorological Reanalysis Data MLOps and Model Monitoring

Required Skills

  • Time-Series Analysis and Statistical Forecasting
  • Deep Learning and Pre-Trained Models
  • Forecast Calibration Statistics
  • Data Engineering

Datasets

  • ERA5 (Copernicus Climate Data Store)
  • Open wind and photovoltaic generation datasets
  • Production series from a partner renewable-energy producer

Morocco & Africa Relevance

Rapid renewable deployment in Morocco and Africa continually creates sites with little historical data, making few-shot forecasting operationally important.