Skip to content
Conference Open access

Uncertainty-Aware Short-Term Load Forecasting using Autoformer with Split Conformal Prediction

Aug 2026 · 2026 International Conference on Secure Information Systems and Technologies (ICSIST) · pp. 322-328 · 0 citations · 17 references

TL;DR

Results indicate that the proposed approach effectively balances predictive accuracy and uncertainty reliability, making it suitable for practical uncertainty-aware short-term load forecasting in smart grid applications.

Abstract

Short-term load forecasting (STLF) plays a critical role in modern smart grid operation by enabling reliable dispatch, reserve allocation, and demand-side management. Although Transformer-based architectures have demonstrated strong point forecasting performance, most existing approaches remain deterministic and do not provide calibrated uncertainty estimates required for risk-aware operational decisions. This paper proposes an uncertainty-aware STLF framework that integrates a multi-horizon Transformer forecaster with split conformal prediction to construct distribution-free and empirically calibrated prediction intervals. The Transformer captures long-range temporal dependencies in load dynamics, while conformal calibration ensures finite-sample coverage guarantees without requiring distributional assumptions. Experiments conducted on Zone 1 of the Tetouan power consumption dataset demonstrate that the proposed framework achieves competitive point forecasting accuracy, obtaining an RMSE of 1089.73 and MAE of 860.09, corresponding to a MAPE of 3.17%. Furthermore, the conformal module provides reliable uncertainty quantification, achieving an empirical prediction interval coverage probability (PICP) of 0.891 at a nominal 90% confidence level, with a PINAW of 0.114. These results indicate that the proposed approach effectively balances predictive accuracy and uncertainty reliability, making it suitable for practical uncertainty-aware short-term load forecasting in smart grid applications.

Read PDF

Similar papers

Open access Oct 2026

GridMind: Issue-Time-Safe Cross-Country Load Forecasting with Conformal Uncertainty and Operator-Aware Model Selection

GridMind, an operator-oriented champion-challenger framework combining a forecast-origin feature ledger, Light Gradient Boosting Machine point forecasts, rolling split-conformal intervals, reproducible feature evidence, and an explicit retain-or-replace decision is presented.

Sohaib Ayad Jasim, S. Jasim · 0 citations
Oct 2026

Original-scale calibrated probabilistic building electricity load forecasting for demand-side management

Reliable day-ahead electricity forecasts are needed for building energy management, demand-side operation, and risk-aware scheduling. In common data-driven pipelines, targets are normalised for training, whereas forecast errors and uncertainty intervals are interpreted after inverse transformation to kWh. This creates...

Bin-Yu Li, Jian-Dun Li, Shao-Feng Lin et al. · 0 citations
Open access Oct 2026

Ultra-Short-Term Multi-Horizon Point and Probabilistic Wind Power Forecasting with Power-Increment Enhancement and Signed Adaptive Conformal Inference

Local power changes, weak-output states, and changing interval coverage complicate ultra-short-term wind power forecasting. This study develops power-increment enhancement and signed adaptive conformal inference (PIE-SACI) to address these challenges within a joint point and probabilistic forecasting framework. XGBoost...

Yu-Yu Liu, Wei Zhang, Gai-Ning Han et al. · 0 citations
Preprint Nov 2026

Adaptive Residual Modeling for Scenario Learning in Probabilistic Load Forecasting

Uncertainties in weather, user behavior, and distributed energy production introduce significant variability into feeder power. Effective power system operations require both multi-horizon load forecasts and well-calibrated extreme quantiles for the forecast. Nevertheless, standard objectives that fit the full forecast...

Jin-Bao Wang, Jun Liu, Shi-Liang Zhang et al. · 0 citations
Open access Nov 2026

Uncertainty-Aware Wind Power Forecasting Using a Cost-Sensitive and Feature Representation-Enhanced LUBE Framework

Precise and dependable wind power prediction is crucial for maintaining grid stability and ensuring operational efficiency. Despite this, current prediction interval (PI) techniques, particularly conventional Lower Upper Bound Estimation (LUBE), focus primarily on optimising statistical width and coverage. These method...

Nazmus Sakib, M. A. Hosen, Fahmid Al Farid et al. · 0 citations
Conference Open access Sep 2026

SC-CP: spatially-correlated conformal prediction for GNN-based distributed photovoltaic power forecasting

High-penetration distributed photovoltaic (DPV) generation exposes distribution grids to rapid, spatially-coupled power swings under passing cloud fronts, so secure dispatch of reserves, storage, and voltage-control devices hinges on prediction intervals with trustworthy coverage, not point forecasts. Two limitations o...

Gong Chen, Jia-Ming Chang · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.