Machine Learning for German Redispatch Forecasting under Data Delays and Temporal Distribution Shift

Key points

• Public redispatch records provide empirical data for grid congestion forecasting, but delayed reporting, zero-inflated distributions, and temporal shift present major modeling challenges.1
• We compare seasonal empirical, regularized autoregressive (ARX), quantile LightGBM, GRU, and Transformer models under a minimum seven-day target-latency constraint.1
• Static, rolling, and adaptive delayed-feedback calibration are evaluated using normalized weighted interval score (nWIS), empirical coverage, and block-bootstrap inference.1
• These results show that boosted-tree models with rolling calibration provide accurate probabilistic forecasts of aggregate redispatch volumes under target delays, while nominal aggregate validity does not ensure reliability during extreme congestion events.1

Sources (1)

• [1]Machine Learning for German Redispatch Forecasting under Data Delays and Temporal Distribution Shift
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 6, 01:35 PM

  We assess the accuracy and reliability of probabilistic machine-learning forecasts using published German transmission records under experimentally imposed information-age constraints.

  Public redispatch records provide empirical data for grid congestion forecasting, but delayed reporting, zero-inflated distributions, and temporal shift present major modeling challenges.

Extractive summary: sentences quoted from the sources.