Aug 2026· 2026 IEEE International Conference on Mechatronics and Automation (ICMA)· pp. 796-801· 0 citations· 28 references
Abstract
Accurate renewable power forecasting is essential for grid operation, reserve scheduling, and renewable integration. This paper proposes a constraint-guided residual forecasting framework that combines a domain-informed baseline with data-driven residual correction for multi-horizon probabilistic forecasting. A Gradient Boosting Regression Tree (GBRT) model is used as a classical residual benchmark, while a Residual PatchTST model captures temporal dependencies from numerical weather prediction features, engineered time variables, and site information. Final forecasts are reconstructed by adding the predicted residual to the baseline and enforcing nonnegative outputs within site-level capacity limits. Across PV sites, GBRT reduces mean RMSE from 0.0909 to 0.0798 and mean MAE from 0.0400 to 0.0358, while wind RMSE decreases from 0.2574 to 0.1479. The deep probabilistic model also delivers stable multi-horizon performance and useful uncertainty intervals. These results show that residual learning with constraint-guided reconstruction provides accurate and operationally meaningful renewable power forecasts.
Accurate short-term solar irradiance forecasting is essential for reliable operation of renewable-dominated energy systems, where scheduling, flexibility management, and grid operation depend on prediction stability. Solar irradiance prediction remains challenging because it is influenced by both deterministic solar radiation behavior and uncertain atmospheric variations. Existing physical and data-driven approaches often struggle to represent both regular irradiance patterns and rapid weather-related fluctuations simultaneously. This paper proposes a physics-guided residual learning framework that separates these components through a sequential forecasting strategy. A deep temporal learning model first captures regular radiative behavior using meteorological observations and solar geometry features, while a secondary learning stage models the remaining structured forecasting errors. The final prediction combines the initial forecast with the learned residual correction. The proposed method is evaluated on a long-term, high-latitude solar dataset with chronologically separated data. The results demonstrate improved forecasting reliability across seasonal and weather-dependent conditions, providing a practical approach for renewable energy operation and digital energy applications.
Tareq Anwar Shikdar, Hannu Laaksonen· IEEE Access· 0 citations
: Accurate probabilistic wind farm power forecasting is essential for reserve scheduling, dispatch decision-making, and risk-aware operation under high levels of wind power penetration. However, short-term wind power sequences exhibit strong nonstationarity, heterogeneous environmental variables exhibit time-varying predictive relevance under different meteorological regimes and operating states, and historical operating states and future numerical weather prediction (NWP) variables contribute differently over the forecasting horizon. In addition, direct quantile forecasts may suffer from quantile crossing or physically inconsistent wind-speed-power responses. To address these issues, this paper proposes a physics-regularized gated model for short-term probabilistic wind farm power forecasting, using hourly Local Peak Power (LPP) as the operational evaluation target. The temporal encoder follows the PatchTST patching strategy to capture both short-term ramping behavior and longer-range temporal dependence. A group-gated environmental variable selection and fusion module is designed to adaptively emphasize physically relevant meteorological variable groups and conditionally integrate historical representations with future NWP information. Moreover, a monotone multi-quantile prediction structure with a physics-based regularization term is introduced to improve probabilistic coherence and wind-speed-power consistency. Experiments are conducted against ten representative baselines covering empirical, tree-based ensemble, recurrent, convolutional, and Transformer-based probabilistic forecasting methods. The proposed model achieves the lowest mean absolute error (MAE), root mean squared error (RMSE), and continuous ranked probability score (CRPS) and obtains a 90% prediction interval coverage probability (PICP90) of 0.9001 and a 90% prediction interval normalized average width (PINAW90) of 0.3123, indicating near-nominal interval coverage with a moderate interval width. Relative to the strongest baseline for each metric, the proposed model reduces MAE by 4.92% compared with LightGBM-QR and reduces RMSE and CRPS by 2.78% and 1.94% compared with XGBoost-QR, respectively. Statistical significance analysis then confirms the overall performance gains, while ablation, interpretability, and sensitivity analyses verify the effectiveness of group-gated fusion, the future NWP branch, and physics-based regularization. These results demonstrate that the proposed model provides accurate, reliable, and physically consistent probabilistic forecasts for short-term wind farm operation.
Zhong Chen, Zenan Wang, Siyu Chen et al.· Energy Engineering· 0 citations
Engineering use of AI forecasting models requires not only high nominal accuracy but also predictable behavior under uncertain inputs. In photovoltaic (PV) forecasting, this requirement is especially challenging because numerical weather prediction (NWP) errors are temporally correlated, state dependent, and physically coupled across variables. Existing evaluations, however, often rely on perfect forecast assumptions or simplistic perturbations that do not reflect these characteristics. This study presents a physically constrained robustness evaluation framework based on simulation, using virtual PV power as a controlled response variable to isolate the propagation of input uncertainty from confounders at the plant level. Six representative machine learning and deep sequence models, including PatchTST, GRU, N-HITS, and LightGBM, are evaluated under dynamic NWP perturbations with heteroscedasticity modulated by clear-sky conditions and Erbs reconstruction that preserves radiation consistency. The results show that sequence models provide stronger noise filtering and temporal resilience than a strong tabular baseline under medium to high disturbance regimes. SHapley Additive exPlanations (SHAP) and Integrated Gradients (IG) further support a feature reallocation tendency at the case level, in which predictive reliance shifts from corrupted future forecasts toward more stable historical observations and deterministic physical priors. A Pareto analysis of accuracy under clean conditions, robustness, and computational latency then translates these findings into engineering implications for robustness assessment and model selection under forecast uncertainty.
Given wind energy’s growing significance in the world’s energy structure, the demand for high-precision forecasting is more urgent than ever. However, wind power’s inherent non-stationarity is linked to complex and variable meteorological conditions, which pose significant challenges for accurate forecasting. The accuracy of short-term wind power forecasts hinges on estimated future wind speed. Systematic biases often degrade the accuracy of Weather Research and Forecasting (WRF) forecasts. A hybrid LSTM–LightGBM correction model is proposed to correct the WRF wind speed bias. The wind correction model significantly reduces the systematic wind speed bias in the WRF model and achieves a notable reduction in RMSE across the entire wind speed range, with the highest RMSE decreasing by 7%. A new physics-guided and deep learning-integrated model is designed for 24 h short-term wind power forecasting, which integrates physical laws with data-driven features, effectively alleviating the “black-box” problem of purely data-driven models and making prediction results more consistent with engineering practice. The model’s predicted wind power has an MAE of 103.94 kW and an R2 of 0.9853, demonstrating superior prediction capability. The results provide reliable technical support for the real-time scheduling of wind farms and support the reliable, stable operation of the power system.
Boni Wang, Mingjian Zeng, H. Shan et al.· Journal of Marine Science an...· 0 citations
A hybrid PV forecasting framework that combines stacking ensemble learning with a targeted residual correction strategy, and demonstrates that analyzing error distribution and forecasting robustness provides valuable insights beyond conventional aggregate metrics, contributing to the development of more reliable photovoltaic forecasting systems.
Khawla Oufrit, A. Mouadili, M. Zazoui· EPJ Web of Conferences· 0 citations
Accurate solar radiation forecasting is essential for photovoltaic energy generation, smart grid stability, and renewable energy management. This study proposes a lightweight hybrid deep learning framework that combines a transformer encoder and Gated Rrecurrent Uunit (GRU) network for short-term solar radiation forecasting in Makkah and Madinah, Saudi Arabia. Hourly meteorological data from the NASA POWER dataset (2020–2025) were utilized, including solar radiation intensity, temperature, humidity, wind speed, cloud amount, rainfall, surface pressure, and dew point temperature. A preprocessing pipeline consisting of missing value treatment, outlier removal, normalization, timestamp alignment, and data cleaning was applied to improve data quality. Feature engineering techniques were incorporated to capture temporal dependency, meteorological interactions, weather dynamics, and solar variability patterns. The transformer encoder was used to learn long-range temporal dependencies through multi-head self-attention, while the GRU layer modeled sequential temporal dynamics efficiently. Hyperparameter optimization was performed using Bayesian optimization with Optuna. The experimental results demonstrate that the proposed transformer GRU framework achieved a Mean Absolute Error (MAE) of 0.014, Root Mean Square Error (RMSE) of 0.0219, and a coefficient of determination (R2) of 0.98. The proposed model outperformed ARIMA, LSTM, GRU, and XGBoost models while maintaining stable performance across varying weather conditions and forecasting horizons.
