Key Takeaways & Executive Findings
- •• • The proposed model achieves at least 1.46% RMSE improvement, 2.44% MAE improvement, and 14.67% MAPE improvement over all comparison models across three wind farms, directly reducing grid dispatch pressure and imbalance penalties in electricity markets. • • The fluctuation continuation scenario identification framework decouples wind power into nonlinear and linear components, enabling quantitative analysis of continuation scales that traditional Hurst exponent methods cannot provide, thus improving scenario classification reliability for downstream forecasting. • • The sparse neural network (SNN) combining sparse autoencoder (SAE) and self-attention mechanism (SAM) effectively handles high-dimensional sparse features, overcoming the curse of dimensionality that plagues random forest and support vector machine approaches in scenario identification. • • The LSTM-Transformer hybrid model tailored for each fluctuation continuation scenario demonstrates robust performance across three real wind farms, validating its industrial applicability for station-level ultra-short-term forecasting where existing methods fail to capture multi-scale turbulent coupling.
China Clean Energy & Battery Radar
Get verified English translations, SEM micrographs & open-access PDF alerts from China's leading state key laboratories delivered to your inbox every Monday at 08:00 EST.
Abstract
Existing ultra-short-term wind power forecasting methods exhibit limited performance due to insufficient extraction of fluctuation information and inadequate analysis of evolution patterns. This paper proposes an ultra-short-term wind power forecasting method based on fluctuation continuation scenario identification. First, the coupling mechanism of wind power fluctuations under multiple turbulence processes is investigated, and historical wind power dynamics are decoupled into a combination of nonlinear and linear fluctuation components. A fluctuation continuation concept is introduced, and the future continuation scale of wind power fluctuations is derived from nonlinear and linear decoupling parameters, thereby classifying fluctuation continuation scenarios. A sparse neural network (SNN) oriented to high-dimensional sparse features is constructed to identify historical fluctuation continuation scenarios, and ultra-short-term power forecasting is conducted separately for each scenario. Validation using measured wind speed and power data from three wind farms shows that, compared with baseline models, the proposed model improves root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE) by at least 1.46%, 2.44%, and 14.67%, respectively, demonstrating superior accuracy and stability. The method addresses the limitations of signal decomposition techniques that lack physical interpretability and are sensitive to hyperparameters, and overcomes the high-dimensional sparsity challenges faced by traditional scenario identification models.
1. Introduction
Wind power integration faces persistent challenges from the inherent volatility and intermittency of wind speed, which are exacerbated by multi-source turbulence coupling around wind farms. Existing ultra-short-term forecasting methods—physical, statistical, and artificial neural network approaches—each exhibit critical limitations: physical methods depend heavily on parameter accuracy and struggle with micro-scale variations; statistical methods like ARIMA cannot capture complex coupling fluctuations under multi-source turbulence; and while ANN-based hybrid models have shown promise, their performance is constrained by insufficient extraction of fluctuation information and inadequate analysis of evolution patterns. Scenario classification has been employed to enhance hybrid models, but traditional statistical features (extremes, means, variances) fail to capture the multi-level fluctuation information inherent in wind power under multi-source turbulence.
Signal decomposition methods such as VMD, MVMD, EMD, and EEMD have been introduced to decouple wind power into modal components, but they suffer from strict requirements on preset mode numbers, sensitivity to hyperparameters, abstract parameters lacking physical meaning, and mode mixing under complex fluctuation scenarios. The physical mechanism of turbulence energy transfer across eddies introduces delay effects, causing wind speed fluctuations to continue existing states, and wind turbine mechanical inertia and control systems further induce response delays, resulting in continuation characteristics in wind power evolution. However, existing studies remain largely qualitative, and the Hurst exponent, while capable of measuring long-term correlation, is dimensionless, difficult to map to specific time scales, and lacks robustness under non-stationary and scenario-switching conditions. This paper addresses these gaps by proposing a quantitative analysis of coupled wind power fluctuation continuation scales, developing a Gaussian component dynamic mixing based multimodal FP decoupling (GCDM-MFPD) method for nonlinear components and a gradient adaptive multilinear FP decoupling (GA-MFPD) method for linear components, and constructing a sparse neural network (SNN) that integrates sparse autoencoder (SAE) and self-attention mechanism (SAM) for high-dimensional sparse feature scenario identification, ultimately enabling scenario-specific ultra-short-term forecasting via an LSTM-Transformer model.
Loading authentic research manuscript (Pages 1–5)...
LIU Xiaoyan, ZHEN Zhao, WANG Fei, HUANG Yuehui, CHANG Xiqiang, MI Zengqiang (2026). Ultra-Short-Term Wind Power Forecasting Based on Fluctuation Continuation Scenario Identification. Acta Energiae Solaris Sinica. https://doi.org/10.19912/j.0254-0096.tynxb.202608_9730
Research & Educational Purpose Only: The translations, structured abstracts, analytical annotations, and data reports provided by SinoGreenTechare intended exclusively for academic research, internal corporate R&D, and educational benchmarking. They do not constitute formal engineering, chemical safety, legal, or professional advice.
Copyright & Intellectual Property Notice: Original copyright of the underlying source articles and experimental data remains with the respective authors, institutions, and original publishing journals. SinoGreenTech claims intellectual property only over its proprietary translations, analytical syntheses, and AEO structured enhancements in accordance with international fair use and academic citation principles.
Frequently Asked Questions
What specific failure mechanisms in existing signal decomposition methods does the proposed GCDM-MFPD and GA-MFPD approach overcome, and how does this translate to industrial reliability?
VMD and MVMD require strict preset mode numbers, and improper selection degrades forecasting performance; they are also highly sensitive to hyperparameters. EMD and EEMD suffer from mode mixing and produce abstract parameters lacking physical meaning. The proposed GCDM-MFPD dynamically combines Gaussian components to decouple nonlinear fluctuation processes, while GA-MFPD uses gradient adaptation for multilinear components, eliminating hyperparameter sensitivity and providing physically interpretable parameters. This directly enhances scenario classification reliability, reducing forecasting errors by at least 1.46% RMSE, which is critical for grid dispatch where inaccurate forecasts incur financial penalties.
How does the sparse neural network (SNN) architecture address the high-dimensional sparse feature problem that cripples traditional scenario identification models like random forest and SVM?
Random forest and SVM face the curse of dimensionality and feature selection difficulties when handling high-dimensional sparse wind power fluctuation features. The SNN integrates a sparse autoencoder (SAE) that imposes sparsity constraints in hidden layers to achieve low-dimensional representation, and a self-attention mechanism (SAM) that captures long-term dependencies via global association modeling. This combination forms a complementary 'key feature screening–long dependency modeling' pipeline, improving identification accuracy and robustness. Empirical results show MAPE improvement of at least 14.67%, demonstrating its effectiveness in real-world high-dimensional sparse scenarios.
What is the quantitative basis for the fluctuation continuation scale, and how does it outperform the Hurst exponent in non-stationary conditions?
The Hurst exponent is a dimensionless statistic that cannot directly map to specific time scales and requires additional model assumptions to infer continuation duration, lacking robustness under non-stationary and scenario-switching conditions. The proposed method derives the future continuation scale directly from nonlinear and linear decoupling parameters obtained via GCDM-MFPD and GA-MFPD, providing a quantitative, physically meaningful measure. This enables K-means clustering to partition fluctuation continuation scenarios with higher reliability, as evidenced by the consistent forecasting improvements across three wind farms.
How does the LSTM-Transformer hybrid model achieve scenario-specific forecasting, and what are the computational cost implications for real-time deployment?
The LSTM-Transformer model is trained separately for each fluctuation continuation scenario identified by the SNN. LSTM captures temporal dependencies, while Transformer models global interactions, together providing accurate ultra-short-term forecasts. While the scenario-specific training increases offline computational load, the online inference remains efficient because each scenario uses a dedicated lightweight model. The SNN's sparse feature extraction reduces input dimensionality, mitigating computational cost. The achieved RMSE improvement of at least 1.46% justifies the additional training overhead for grid operators seeking high-precision forecasts.
What are the scalability bottlenecks when deploying this method across diverse wind farms with varying terrain and turbulence conditions?
The method was validated on three wind farms with different measured wind speed and power data, demonstrating adaptability. However, scalability depends on the availability of sufficient historical data for each farm to train the GCDM-MFPD, GA-MFPD, and SNN models. Terrain-specific turbulence characteristics may require re-tuning of decoupling parameters and scenario clustering. The K-means clustering for scenario division is computationally efficient, but the SNN training may need re-initialization for new sites. Nevertheless, the consistent performance improvements across three farms suggest robust generalization, with the primary bottleneck being data collection and preprocessing rather than algorithmic limitations.
Related Chinese Research & Cross-Citations
Wind Turbine Gearbox Fault Diagnosis Method Based on Improved CNN-XGBoost Fusion Model Under Gramian Angular Difference Field
Gearbox failures account for 20–30% of total wind turbine faults and incur maintenance costs equivalent to 10–15% of overall turbine value. Conventional vibration diagnostic pipelines—complementary ensemble empirical mode decomposition with singular value energy spectrum, time-varying filtering empirical mode decomposition, and Teager energy spectrum analysis—remain bounded below 90% accuracy and depend on expert-driven feature engineering that is sensitive to non-stationary operating conditions and noise. This study proposes an intelligent diagnostic architecture that converts one-dimensional gearbox vibration signals into two-dimensional images via Gramian angular difference field (GADF) transformation, preserving intrinsic temporal correlation and time-frequency structure while exploiting matrix sparsity to suppress interference. An improved convolutional neural network (CNN) extracts multi-dimensional features: a convolutional block attention module (CBAM) is embedded in the convolutional layers to weight critical channels and focus on fault-sensitive spatial regions, and a modified βc-ACONC activation function replaces ReLU to mitigate neuron necrosis and enable selective activation. The extracted composite features are then fed into an XGBoost network whose hyperparameters are optimized by an improved sparrow search algorithm (ISSA). Validation on a laboratory wind turbine gearbox dataset yields diagnostic accuracy exceeding 99%, demonstrating robust fault identification capability under complex operating conditions.
Joint Forecasting of Wind and Photovoltaic Power Considering Complementarity
The inherent spatiotemporal complementarity between wind and solar resources offers a theoretical basis for improving renewable power forecasting accuracy. This study proposes a joint wind-photovoltaic (PV) power forecasting strategy that explicitly exploits this complementarity. A bidirectional long short-term memory (BiLSTM) neural network serves as the baseline forecasting model, and a novel sorting and comparative optimization (SCO) algorithm is developed to optimize the model's hyperparameters. The SCO algorithm ranks individuals in ascending order and compares adjacent fitness values to escape local optima, a known deficiency in conventional metaheuristics such as genetic algorithms and particle swarm optimization. For wind farms and PV plants exhibiting significant complementarity, the joint forecasting strategy first aggregates their power outputs, normalizes the combined signal, and then feeds it into the optimized BiLSTM model. Experimental results demonstrate that the proposed SCO-BiLSTM model reduces the eMAPE by 10.313% compared with PSO-BiLSTM. Furthermore, joint forecasting under SCO-BiLSTM lowers the eRMSE by 27.443% relative to standalone PV power forecasting. The study also establishes that forecasting accuracy improves with stronger wind-solar complementarity but degrades as the forecasting horizon extends. These findings confirm that exploiting complementarity in joint forecasting substantially enhances predictive performance for renewable energy integration.
Multi-Classifier Open Adversarial Network for Rolling Bearing Fault Diagnosis in Wind Turbine Generator Systems
Rolling bearings in wind turbine generator systems operate under variable speed and load conditions that induce significant data distribution shifts between training and field data, while unknown fault modes absent from the source domain are frequently misclassified as known classes. This study proposes a multi-classifier open adversarial network (MCOAN) for open-set fault diagnosis. Within an adversarial domain adaptation framework, a K-way classifier and an additional K+1-way one-vs-all classifier independently estimate target-sample similarity to the source domain. These similarity scores drive a dynamic weighting mechanism that adaptively reweights target samples during open-set adversarial training and supplies per-sample dynamic thresholds for known/unknown discrimination, thereby promoting cross-domain alignment of shared-class features while suppressing negative transfer from unknown samples. A non-adversarial domain classifier is introduced to stabilize dynamic weight estimation. Validation on two datasets demonstrates high-precision shared-class distribution alignment and unknown-class recognition with favorable robustness. The method removes reliance on empirically preset thresholds that plague conventional open-set back-propagation approaches, where a fixed threshold of 0.5 in the binary cross-entropy adversarial loss provides no per-sample adaptivity. By coupling K-way and K+1-way similarity estimates, MCOAN achieves simultaneous known-class alignment and unknown-class separation without prior knowledge of the unknown-class cardinality, addressing a persistent bottleneck in wind turbine drivetrain condition monitoring where unanticipated bearing failure modes emerge under field conditions.
Unsupervised Automated Identification Method for Abnormal States of Wind Turbine Gearboxes
Addressing the scarcity of labeled data for training classification models in wind turbine planetary gearbox anomaly identification, this study proposes an unsupervised automated detection method. Log Mel-band energy features are extracted from raw vibration signals and fed into an unsupervised anomaly recognition model centered on a U-net autoencoder. A health-state threshold is established based on reconstruction error between model input and output, enabling anomaly identification. The method is validated using factory gearbox test data and operational data from a wind farm in Yangtouya, Shanxi. For factory gearboxes, dual validation is performed using a spectrum amplitude modulation-based signal processing method. Results demonstrate that the proposed method achieves 93.34% recognition accuracy on both factory and wind farm test sets, confirming its capability to automatically and correctly separate abnormal wind turbine gearboxes. The approach eliminates reliance on labeled fault data, offering a scalable solution for full-lifecycle health monitoring, from factory acceptance testing to in-service early anomaly detection, adaptable across different operating conditions and turbine models.
Improved Adaptive Super-Twisting Sliding Mode Control for Permanent Magnet Synchronous Motors
Adaptive super-twisting sliding mode control (ASTSMC) for permanent magnet synchronous motors (PMSM) suffers from prolonged convergence and insufficient disturbance rejection under complex operating conditions. This paper proposes an improved ASTSMC incorporating a fixed-time disturbance observer (FTDO). A power term is introduced into the adaptive super-twisting controller to accelerate convergence far from the origin, while the discontinuous sign function is replaced by a continuous h(s) function to mitigate chattering. The FTDO ensures disturbance estimation converges within a fixed time independent of initial states, overcoming the limitations of traditional and finite-time observers. The estimated disturbance is fed forward to the sliding mode controller for compensation, enhancing robustness. The FTDO design is based on an auxiliary state variable z and its derivative, with error dynamics analyzed via Lyapunov stability. Comparative simulations against conventional disturbance observers and sliding mode controllers validate the proposed strategy. The results demonstrate shorter convergence time, improved dynamic performance, and superior disturbance rejection, making the approach suitable for high-performance servo systems. The method addresses the critical need for robust, fast-response control in electric vehicles, rail transit, and aerospace applications where PMSM drives face significant uncertainties and external disturbances.
Data-Model Jointly Driven Fault Diagnosis for Wind Turbine Planetary Gearboxes
Fault diagnosis of wind turbine planetary gearboxes is severely constrained by the scarcity of high-quality fault data, as gearboxes operate predominantly in healthy states and automatic shutdowns prevent fault progression. This paper proposes a data-model jointly driven diagnosis method to address low diagnostic accuracy under limited fault samples. A high-fidelity lumped-parameter dynamic model of the planetary gearbox is constructed to generate pseudo-fault data, supplementing the training set. A domain-shared residual network feature extractor incorporating convolutional block attention modules extracts key physical features from both pseudo and measured data. Local maximum mean discrepancy aligns feature distributions at the fault-category level between pseudo and real fault data. A Kolmogorov-Arnold network module enhances the model's capacity to learn complex data relationships, enabling classification and identification of different fault types. Validation on a wind turbine planetary gearbox fault diagnosis test rig demonstrates that the proposed method achieves superior diagnostic performance under fault sample scarcity compared to classical methods. The framework offers an effective solution for known fault types, though identification of unknown and atypical faults remains a challenge for future work via open-set domain generalization.