Aug 2026· Engineering, Technology & Applied Science Research· Vol 16, pp. 37889-37897· 0 citations· 46 references
TL;DR
A practical contribution is provided 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.
Abstract
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.
This paper proposes DCR-PatchTST-CQ, a unified multi-task probabilistic forecasting framework that combines condition-aware dynamic routing combined with stratified conformal calibration to jointly improve quantile ordering, interval sharpness, and coverage reliability.
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.
Uroš Ilić, O. Kundacina, Andrija Petrušić et al.· Energies· 0 citations
We propose a unified, risk-aware framework for renewable energy mix planning integrating meteorological parameterization, probabilistic machine learning forecasts and optimization. Using NASA POWER reanalysis, wind- and solar-relevant features are derived. Gaussian Process Regression provides point predictions with predictive covariances, capturing both variability and interdependence of renewable resources. These forecasts feed into a portfolio-theoretic optimization model: short-term scheduling is solved as mixed-integer quadratic programs with Alternating Direction Method of Multipliers (ADMM)-based decomposition, while long-term planning is formulated as binary quadratic programs with variance and lagged-covariance penalties. The exponential scaling of classical solvers motivates hybrid quantum–classical approaches such as quantum annealing for multi-period, high-resolution planning. The framework reduces exposure to scarcity events, enhances security of supply and directly supports decarbonization targets, while also offering a transferable methodology for risk-informed planning in other sectors facing stochastic variability. The results obtained from the implementation of the proposed framework for Germany indicate that endowed with quantum computing techniques the short-term optimization can facilitate robust integration of the renewables in the grid without compromising grid reliability and the long-term optimized planning (not feasible with classical computing resources) can avoid overproduction by about 30% at certain times, reducing storage costs and detrimental impact on grid frequency.
K. Ghosh, Biswajit Basu· npj Clean Energy· 0 citations
Accurate prediction of fine particulate matter (PM2.5) remains challenging because atmospheric processes are nonlinear, nonstationary, and influenced by temporal variability, measurement uncertainty, and episodic pollution events. This study develops an interpretable and uncertainty-aware machine-learning (ML) framework for station-level PM2.5 prediction in Visakhapatnam, a rapidly industrializing coastal urban environment in India characterized by complex meteorological and emission conditions. Multiple ML algorithms and Gradient Boosting loss formulations were comparatively evaluated using a leakage-free chronological validation framework based on daily observations collected during 2018–2024. The proposed framework integrates temporal feature engineering, rolling time-series cross-validation, residual diagnostics, regime-wise evaluation, conformal uncertainty estimation, bootstrap confidence intervals, and SHAP-based interpretability analysis. Predictive performance was assessed using Coefficient of Determination, Root Mean Squared Error, Mean Absolute Error, Mean Absolute Scaled Error, and Mean Absolute Percentage Error metrics across training, validation, and independent testing datasets. Results demonstrate that ensemble-based ML models consistently outperform linear and kernel-based approaches under temporally ordered evaluation conditions. Among the evaluated models, Random Forest achieved the highest overall predictive accuracy on the independent testing dataset, while robustness-oriented Gradient Boosting formulations, particularly the Huber-loss configuration, demonstrated comparatively stable predictive behavior under heterogeneous and noisy atmospheric conditions. Central Pollution Control Board regime-wise evaluation further revealed reduced predictive performance during elevated pollution episodes, emphasizing the importance of pollution-regime-specific evaluation beyond aggregate metrics alone. Overall, the proposed framework provides a computationally efficient, interpretable, and rigorously validated approach for PM2.5 prediction in complex coastal urban environments, supporting operational air-quality monitoring and environmental decision-support applications.
The inherent uncertainties of renewable energy sources—specifically their intermittent and volatile nature—create significant obstacles for power system planning. With the growing integration of renewables into the grid, mapping the precise interdependencies among wind generation, solar photovoltaic (PV) yield, and power demand has become crucial for designing and managing resilient power networks. To address the challenge of simulating representative scenarios for correlated wind and solar outputs, this study initially employs non-parametric kernel density estimation (KDE) to model extensive empirical datasets. Following rigorous accuracy and goodness-of-fit validation, specific KDE formulas for both wind and solar resources are derived. Subsequently, the research constructs various Copula-based joint probability models to represent the combined power generation of wind and solar farms. The performance of these models is comparatively assessed using Maximum Likelihood Estimation (MLE) alongside Akaike and Bayesian Information Criteria (AIC/BIC). reduce nce, the most suitable Copula function is identified to capture the joint probabilistic behavior of wind and PV systems. Ultimately, this optimal Copula model drives the generation of annual power output profiles for wind and solar energy. Computational experiments and validation procedures confirm that the simulated yearly scenarios accurately preserve the underlying correlation structures of the original data.
Lijian Chen· International Conference on...· 0 citations
To address the low accuracy and poor reliability of short-term photovoltaic (PV) power forecasting under complex weather conditions, this study proposes a multi-strategy synergistic optimization framework for point-interval prediction. The methodology integrates similar day classification (SDC) via RDP-DTW-DBA-K-means, a hybrid BiTCN-MAOBiGRU-AM model with a mutation-aware mechanism, and Dream Optimization Algorithm (DOA) for global hyperparameter tuning of six key parameters. For interval prediction, an adaptive bandwidth kernel density estimation (ABKDE) dynamically adjusts bandwidth based on local error density and weather scenarios. Experiments using data from a Guangxi PV station demonstrate that the synergistic model reduces RMSE by 29.58% (cloudy) and 32.37% (overcast/rainy) versus the baseline, and cuts RMSE by 16.2–19.0% under abrupt weather events and 22.4–40.2% under non-ideal input data. At the 95% confidence level, ABKDE improves prediction interval coverage probability by 3.9–5.4 percentage points and reduces normalized average width by 20.8–23.6% compared to conventional KDE. The proposed framework significantly enhances prediction accuracy, robustness, and generalization, offering a reliable solution for PV power forecasting in highly variable meteorological scenarios.
Jian-Xin Zhang, Huan-Huan Yang, He Huang et al.· Energies· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
