In-Context Residual Calibration for Uncertainty Quantification of Energy Time Series over Graphs
Abstract
Accurate energy demand forecasting is essential for the reliable operation and planning of modern sustainable energy systems. Spatial-temporal graph neural networks (STGNNs) have recently achieved strong performance in point forecasting by jointly modeling temporal dynamics and relational dependencies across interconnected energy nodes. However, in real-world energy systems, accurate point forecasts alone are insufficient, as operators also require reliable uncertainty estimates to support risk-aware decision-making, grid stability, and operational planning under uncertainty. Conformal prediction provides a principled and model-agnostic framework for uncertainty quantification under exchangeability assumptions, making it particularly attractive for safety-critical energy applications. However, existing conformal prediction approaches often fail to fully capture the complex spatial-temporal structure of energy systems. To address these limitations, we propose STOIC (Spatial-Temporal uncertainty quantificatiOn via In-Context learning), a conformal-inspired post-hoc residual calibration framework that integrates graph-based forecasting with the in-context learning capabilities of tabular foundation models. STOIC first generates point forecasts using an STGNN and subsequently reformulates spatial-temporal residuals into a tabular representation suitable for in-context learning. Leveraging a tabular foundation model, STOIC estimates feature-conditional residual quantiles without task-specific retraining of the calibration model, effectively capturing both sequential and relational dependencies. STOIC should be viewed as a conformal-inspired residual calibration method and does not by itself provide a finite-sample distribution-free coverage guarantee under arbitrary temporal dependence...
Related
- Attribution-State Conformal Forecasting: Residual-Independent Explanation States for Uncertainty Calibration Under Distribution Shift
- TabCUQ: Context-Uncertainty Quantification for Tabular Foundation Models
- Uncertainty Quantification of State Variables Trajectories in the Context of Inverse Problems: An Approach from Bayesian Inference and FDA
- Forecast-Residual-Based Chance-Constrained Scheduling of Local Energy Communities under PV and Demand Uncertainty
- Residual Calibration via Local Feature-Space Refinement
BibTeX
@misc{niresi2026incontext,
title = {{In-Context Residual Calibration for Uncertainty Quantification of Energy Time Series over Graphs}},
author = {Keivan Faghih Niresi and Alice Cicirello and Olga Fink},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2606.31804},
eprint = {2606.31804},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2606.31804},
note = {CC BY-NC-SA 4.0},
}
RIS
TY - UNPB
TI - In-Context Residual Calibration for Uncertainty Quantification of Energy Time Series over Graphs
AU - Keivan Faghih Niresi
AU - Alice Cicirello
AU - Olga Fink
PY - 2026
DA - 2026/10/07
PB - arXiv
DO - 10.48550/arxiv.2606.31804
UR - https://arxiv.org/abs/2606.31804
AB - Accurate energy demand forecasting is essential for the reliable operation and planning of modern sustainable energy systems. Spatial-temporal graph neural networks (STGNNs) have recently achieved strong performance in point forecasting by jointly modeling temporal dynamics and relational dependencies across interconnected energy nodes. However, in real-world energy systems, accurate point forecasts alone are insufficient, as operators also require reliable uncertainty estimates to support risk-aware decision-making, grid stability, and operational planning under uncertainty. Conformal prediction provides a principled and model-agnostic framework for uncertainty quantification under exchangeability assumptions, making it particularly attractive for safety-critical energy applications. However, existing conformal prediction approaches often fail to fully capture the complex spatial-temporal structure of energy systems. To address these limitations, we propose STOIC (Spatial-Temporal uncertainty quantificatiOn via In-Context learning), a conformal-inspired post-hoc residual calibration framework that integrates graph-based forecasting with the in-context learning capabilities of tabular foundation models. STOIC first generates point forecasts using an STGNN and subsequently reformulates spatial-temporal residuals into a tabular representation suitable for in-context learning. Leveraging a tabular foundation model, STOIC estimates feature-conditional residual quantiles without task-specific retraining of the calibration model, effectively capturing both sequential and relational dependencies. STOIC should be viewed as a conformal-inspired residual calibration method and does not by itself provide a finite-sample distribution-free coverage guarantee under arbitrary temporal dependence...
ER -