Experiments on ERA5 data show that AMBHFN outperforms eight retrained baselines over the 0–23 h forecast horizon, with an average error reduction of more than 12%.
Abstract
Accurate wind vector prediction is essential for renewable energy utilization and power system stability, yet existing methods struggle to jointly model local dynamics, global structures, and temporal robustness. To address this limitation, an Adaptive Multi-Branch Heterogeneous Fusion Wind Prediction Network (AMBHFN) is proposed. Local dynamic, global structural, and temporal robustness modeling are assigned to dedicated heterogeneous branches, whose outputs are coordinated through the Adaptive Multi-Branch Prediction Collaboration Mechanism (AMBPC). Multi-source meteorological variables and terrain information are used for local dynamic modeling, while global spatiotemporal structures are captured by a 3D U-shaped fully convolutional branch and temporal robustness is enhanced by an iTransformer-based multi-agent branch with graph convolution. Experiments on ERA5 data show that AMBHFN outperforms eight retrained baselines over the 0–23 h forecast horizon, with an average error reduction of more than 12%. At the first forecast step, the root mean square error (RMSE) and mean absolute error (MAE) are 0.33 m/s and 0.25 m/s, respectively. Under the strict 22.5° threshold, wind direction forecast accuracy (WDFA) reaches 97.72% at 0 h and 78.06% at 6 h. Fine-tuning in two target regions reduces the 13–23 h RMSE to 1.54 and 1.96. Statistical tests confirm significant improvements over MFWPN, and ablation studies verify the complementarity of the three branches. With 128 giga floating-point operations (GFLOPs) and a 22 ms per-sample forward inference time, AMBHFN achieves a competitive balance among accuracy, stability, and efficiency.
To address the limitations of existing wind power forecasting methods in mixed-frequency signal modeling, multi-site spatial correlation capture, and single-model generalization, this paper proposes a multi-site wind power forecasting system based on power decomposition and deep model ensemble. The system applies Variational Mode Decomposition (VMD) to separate raw power sequences into high-frequency and low-frequency components, each directed into a structurally symmetric dual-branch framework. Within each branch, three heterogeneous sub-models – ConvGAT-LSTM, Spectral Transformer, and TCN – operate in parallel; branch outputs are aggregated by simple averaging and linearly combined into a base prediction, which is subsequently refined by an XGBoost residual correction layer. Experiments on six Chinese wind farm datasets demonstrate that the proposed system achieves an average RMSE of 0.1065±0.0021 and R2 of 0.8335±0.0167 at the 24-step forecast horizon, improving over the state-of-the-art baseline TCOAT by 1.4% and 0.5%, respectively. The VMD module alone contributes an 11.6% RMSE reduction, and the system reduces local RMSE during ramp events at Site 6 by 34.9% relative to the baseline. Ablation experiments and statistical significance tests (p<0.05, Cohen’s d>0.82) confirm that each module contributes meaningfully to overall performance.
Accurate wind speed forecasting plays a crucial role in the safe and stable operation of wind farms and the efficient integration of renewable energy into modern power systems. However, wind speed exhibits complex spatiotemporal variations affected by diverse meteorological conditions, making high-precision prediction a long-standing bottleneck in wind power scheduling. This paper develops a U-shaped spatiotemporal feature fusion network named U-STNet, which realizes joint modeling of inter-turbine spatial correlations and multi-period long-range temporal dependencies. The model maps raw wind speed series to high-dimensional embeddings and adopts an encoder–decoder U-shaped architecture to complete feature encoding, reconstruction and multi-scale feature extraction, which effectively captures the inherent periodic and seasonal patterns of wind speed. Experiments on the SDWPF wind farm dataset show that U-STNet obtains competitive prediction accuracy across all multi-step forecasting horizons. Compared with traditional statistical models, recurrent neural networks and state-of-the-art Transformer baselines, the proposed method exhibits more stable error accumulation characteristics and superior long-step prediction performance. This verifies the effectiveness of jointly modeling turbine spatial topology and multi-scale temporal dependencies for wind speed forecasting.
Trajectory prediction is fundamental to Trajectory-Based Operations (TBO). However, prediction accuracy in Terminal Manoeuvring Area (TMA) is limited by the heterogeneous dynamics of trajectories and the lack of complexity metrics aligned with deep-learning model performance. This paper proposes a complexity-aware trajectory prediction framework comprising two integrated components. At its core is the Adaptive Dual-Stream Fusion Network (ADSF-Net), which combines a Temporal Convolutional Network branch for local kinematic features and a Bidirectional LSTM branch for global temporal intent, integrated through a Dynamic Context Gating mechanism that adaptively arbitrates between the two streams. An altitude-consistent regime-partitioning strategy then decomposes the airspace into homogeneous subspaces, coupled with a Mixture-of-Experts routing strategy that selects an appropriate expert per regime; this design reduces test-set altitude MAE by up to 41.8% relative to a single global model under a flight-level oracle, with a deployment-realistic causal estimator preserving a 28.6% reduction using only past-observed data at each prediction step. A transparent decomposition shows that the dominant share of this gain (39.2 of the 41.8 percentage points) stems from regime partitioning itself. To characterise the resulting regimes and to drive the residual gain from architecture switching, we introduce the Trajectory Statistical-Moment Predictability Index (TSMPI) as a lightweight, model-agnostic diagnostic and routing signal rather than a predictive component; it exhibits a moderate, outlier-robust correlation with per-flight prediction error (Pearson $r \approx 0.30$ , $p \lt 10^{-4}$ ) and provides a principled basis for routing decisions. We additionally derive a moment-based information-theoretic lower bound on the achievable altitude-prediction error that grounds this empirical relationship, identifying dispersion as the dominant complexity driver and clarifying why a purely moment-based signal correlates only moderately with realised error. A sensitivity analysis confirms that TSMPI is robust to weight choice under both local perturbation and uniform random sampling from the Dirichlet simplex.
Accurate wind power forecasting is imperative for ensuring grid stability and facilitating the large-scale integration of renewable energy—both central pillars of the global energy transition and the Dual Carbon strategic goals. However, existing methods often fail to fully capture the spatial heterogeneity and interdependencies among individual turbines, limiting their effectiveness for sustainable grid operation. To address this gap, this paper proposes an ultra-short-term wind power forecasting framework that incorporates explicit multi-dimensional spatial features. At the feature level, a 12-dimensional spatial feature system is constructed to quantify the microscale topology of wind farms. These static spatial attributes are seamlessly fused with dynamic temporal data using a dimensionality-balance factor strategy. Finally, a hybrid deep learning network comprising a multi-scale CNN, a multi-layer BiLSTM, and a multi-head self-attention mechanism is developed to capture complex spatiotemporal patterns. Experimental results on three real-world datasets show that the proposed method significantly outperforms baseline models, reducing the Mean Absolute Percentage Error by up to 11.09% and improving the coefficient of determination R2 up to 0.9120. By improving forecast accuracy and robustness, the method directly supports more reliable grid dispatching, reduces curtailment of wind energy, and thus contributes to the sustainable utilization of renewable resources. These findings demonstrate that incorporating explicit spatial correlation effectively enhances the accuracy and robustness of ultra-short-term wind power forecasting, providing robust decision support for power grid dispatching and advancing the sustainability of modern power systems.
Yanxia Wang, Weilong Yu, Minghan Ma et al.· Sustainability· 0 citations
ABSTRACT With the continuous increase in wind power penetration, accurate and reliable short-term wind power forecasting is pivotal for optimizing grid dispatch and ensuring system stability. However, the complex spatiotemporal coupling within wind farms poses severe challenges for forecasting. Most existing Spatiotemporal Graph Neural Networks (STGNNs) are confined to predefined static graph structures, failing to effectively capture the dynamic wake effects induced by wind direction fluctuations and the non-stationarity of spatial distributions. Furthermore, the temporal modules of existing models often struggle to balance the acute capture of local high-frequency abrupt changes with the effective modeling of global long-range dependencies. To address these limitations, this paper proposes a Dynamic Spatiotemporal Convolutional Attention Network (DST-CAN). First, we design a Metric-Learning-based Dynamic Topology Module that reconstructs the time-evolving spatial dependency topology among wind turbines by adaptively fusing physical distance priors with real-time feature similarities. Second, a hierarchical hybrid spatiotemporal architecture is introduced, which synergistically utilizes dilated causal convolutions to extract local trends and instantaneous fluctuations, while incorporating a multi-head self-attention mechanism to aggregate global context information, thereby achieving a complementary fusion of local and global features. Extensive experiments on the real-world datasets demonstrate that DST-CAN significantly outperforms existing methods in multi-step forecasting tasks. Ablation studies further validate the effectiveness of dynamic topology modeling in handling non-stationary wake effects.
Peng Chen, Danhong Zhang, Yixin Su· International Journal of Gre...· 0 citations
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.
Naif Nafea J. Alanazi, Q. Lei· 2026 IEEE International Conf...· 0 citations