The increasing integration of photovoltaic systems into modern power grids requires forecasting models that not only provide accurate predictions but also reliable uncertainty quantification under evolving operating conditions. In this paper, we propose an Out-of-distribution-aware time series conformal prediction framework with adaptive retraining, designed to address key limitations of standard conformal prediction methods in temporally dependent and dynamically changing environments. The framework is built upon the Ensemble batch prediction intervals method, which enables distribution-free uncertainty quantification without relying on a fixed calibration set, making it particularly suitable for time series applications. To ensure robustness to distribution shifts, a conformal out-of-distribution detection module is incorporated, where out-of-distribution detection is formulated as a hypothesis testing problem and enhanced through calibration-conditional p-values obtained via the Simes correction, providing conservative false-positive control intended to limit unnecessary model retraining. The proposed framework demonstrates superior performance compared to state-of-the-art approaches in uncertainty quantification, while conformal out-of-distribution detection reduces false positives and the adaptive retraining mechanism ensures effective adaptation to evolving data distributions in real-world scenarios.
We propose ABF-T-GLCP, a model-agnostic framework for forecasting and uncertainty quantification in nonstationary multivariate time series. The central idea is to learn an adaptive predictive state representation for point forecasting and reuse it for conformal calibration. The forecasting module combines horizon-specific temporal experts through a learned gate and refines predictions using sparse predictive transfer across related series. The uncertainty module, Gate-Localized Conformal Prediction (GLCP), uses the learned gate state, together with temporal recency, to select locally relevant calibration residuals, thereby coupling uncertainty calibration to the predictive regimes used by the forecasting model. This shared representation allows point forecasts and prediction intervals to adapt consistently under evolving temporal dynamics while retaining the model-agnostic nature of conformal prediction and yielding approximate local coverage under mild stability conditions. Experiments on a large-scale high-frequency commodity forecasting benchmark show consistent gains in point forecasting accuracy and substantially narrower prediction intervals with empirical coverage close to the nominal level. Additional results indicate that the framework extends beyond the motivating financial application.
Ziling Ma, Junshu Jiang, Ángel López-Oriona et al.· 0 citations
Wind energy forecasting has increasingly shifted from point to probabilistic approaches to support risk-aware decision-making. However, most existing methods evaluate models using global calibration metrics, which fail to capture reliability in real-time operations. In this paper, we emphasize the importance of local calibration for trustworthy decision support in wind power generation. We propose a set of local calibration metrics to assess probabilistic forecasts at a finer temporal scale. Furthermore, we incorporate the Adaptive Conformal Inference (ACI) framework as a model-agnostic, post-hoc approach to improve calibration. Extensive experiments on real-world wind power datasets using deep probabilistic forecasting models show that ACI consistently enhances local calibration performance, with improvements of up to 30% in the proposed metrics. These results highlight the significance of local calibration and demonstrate the effectiveness of ACI in improving the reliability of probabilistic forecasts for real-time, risk-aware decision-making.
Reliable uncertainty quantification is essential for integrating solar and wind generation into modern power systems, where operators must weigh risk rather than act on point forecasts alone. Existing probabilistic methods, however, often either lack finite-sample validity or require per-site recalibration, so a single model rarely transfers across the diverse climates of a dispersed generation fleet. This paper proposes a heteroscedastic, asymmetric, group-conditional split-conformal framework built on a bootstrap-diverse XGBoost ensemble, producing prediction intervals that adapt in width to local difficulty while retaining distribution-free coverage guarantees. A single fixed specification, with no per-site or per-horizon tuning, is evaluated across four climatologically distinct sites spanning both hemispheres, at horizons of 1 to 12 hours, for both solar irradiance and wind speed. The framework holds near-nominal coverage on both targets and reduces the Interval Score by up to 35% relative to competitive baselines, with the calibration and sharpness of its intervals shown to be properties of the method rather than of site-specific tuning.
Shreedhar Gangwar, Abhinav Bains, Banalaxmi Brahma B. R. Ambedkar National Institute of Technology et al.· 0 citations
High load variability and the low quality of building monitoring data pose substantial operational challenges for modern energy management systems. This study develops a robust and computationally efficient probabilistic forecasting framework by integrating data-issue handling with uncertainty calibration. Using an experimental design on a high-resolution multi-energy dataset (2018–2023), the study compares Gradient Boosting Decision Trees (GBDTs) with a linear baseline under a strict out-of-time validation protocol and Conformalized Quantile Regression (CQR). The results indicate the superiority of non-linear models: CatBoost delivers the best point-forecast accuracy, achieving a Mean Absolute Error (MAE) of 37,752.04 kW, corresponding to an 11–12% performance improvement over ElasticNet. Conformal calibration substantially improves the validity of prediction intervals, increasing the Prediction Interval Coverage Probability (PICP) from 82.22% to 87.28%, thereby approaching the nominal 90% confidence target without imposing strong distributional assumptions. Further ablation analyses reveal that rolling-window features contribute more to accuracy than external weather variables. Overall, these findings provide a practical contribution in the form of a forecasting method that is not only accurate but also statistically reliable in estimating operational risk, thereby bridging the gap between industry demands for robust systems and the constraints imposed by real-world data quality.
Lasmedi Afuan, Agus Darmawan, Raden Demas Amirul Plawirakusumah et al.· Engineering, Technology &...· 0 citations
Remaining Useful Life (RUL) prediction for turbofan engines is critical for balancing operational safety against maintenance costs and environmental impact from premature replacements. Models must reliably extrapolate beyond training data, yet no single method performs optimally across all operational contexts, making model selection fundamentally heuristic. Rather than demonstrating individual model superiority, this work recognizes that reliable prognostic performance emerges from adaptive model contribution. This work introduces an ensemble framework integrating three components: (1) legacy-representative data splitting that mirrors realistic deployment where models predict for newer assets using historical data, (2) median absolute deviation-based outlier filtering for stability, and (3) WTA³ weighting that dynamically adjusts model influence based on cycle-by-cycle performance. This treats model coordination as a time-varying optimization problem adapting to evolving degradation patterns. The framework is validated on NASA CMAPSS data using six diverse models spanning traditional machine learning (Random Forest, XGBoost, Support Vector Regression) and deep learning (LSTM, CNN, Transformer). We investigate how prediction robustness changes during temporal extrapolation, whether adaptive weighting provides more stable forecasts than individual models or fixed combinations, and how uncertainty quantification supports safer maintenance decisions. Initial validation demonstrates that the WTA³ meta-ensemble achieves approximately 3 cycles RMSE and under 3 cycles MAE, representing over 30% improvement over the best individual model, with particularly strong performance in the critical late-life phase. The ensemble maintains highly stable predictions with well-calibrated confidence intervals and substantially improved coverage compared to individual models. This work reframes prognostics from competitive model selection to adaptive coordination, demonstrating that ensemble stability under extrapolation can be systematically achieved. The approach provides actionable confidence bounds for aerospace maintenance programs, enabling cost-efficient scheduling while reducing environmental waste, directly supporting both economic and sustainability objectives where data scarcity and safety criticality are paramount.
Ayushi Bharti, N. Kim, Hee-Cheol Kim· e-Journal of Nondestructive...· 0 citations
This work develops a unified one-day-ahead probabilistic forecasting framework that aligns temporal resolution, reconstructs the unavailable inputs, and derives causal features, and compares a modular post-hoc residual-quantile scheme with an integrated in-model quantile-learning scheme.
S. Al-Shareeda, Gulcihan Ozdemir, H. Jeon· Electric power systems resea...· 0 citations
