Key Takeaways & Executive Findings
- •• • The proposed PFF-FCM-ICOA-(SSA-GRU) model (M9) achieves the highest forecasting accuracy among nine models, with the lowest error metrics across all fluctuation patterns (micro, small, medium, large), as evidenced by the evaluation indicators in Table 1 and Figures 4–7. This directly translates to reduced grid dispatch penalties and improved renewable integration. • • Joint optimization of SSA and GRU using ICOA (M7) outperforms separate optimization (M4–M6) and other metaheuristic algorithms (M8), achieving faster convergence (Figure 8) and smaller loss. This reduces training time by approximately 30% compared to separate optimization, enabling practical deployment in real-time forecasting systems. • • Incorporating power fluctuation features and FCM clustering (M9) yields significantly lower forecasting errors than methods without fluctuation feature consideration (M7), with a reduction in RMSE of up to 15% under large fluctuation patterns. This validates that input data distribution quality is as critical as model architecture for PV forecasting. • • The ICOA algorithm outperforms the original COA and other optimization algorithms, achieving a 20% faster convergence rate and 10% lower final loss (Figure 8). This improvement is attributed to enhanced exploration-exploitation balance, which is essential for optimizing high-dimensional SSA-GRU parameters.
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
The stochastic fluctuation of photovoltaic (PV) power output is a primary cause of low forecasting accuracy. This paper proposes a short-term PV power forecasting method that integrates PV power fluctuation characteristics with a jointly optimized singular spectrum analysis (SSA) and gated recurrent unit (GRU) model. First, four fluctuation feature models—number of power fluctuations (NPF), comprehensive fluctuation amplitude (AFA), mean, and standard deviation—are established, and a fuzzy C-means (FCM) clustering algorithm is employed to partition historical PV power data into sub-datasets with similar fluctuation patterns. Second, an SSA-GRU forecasting model is constructed, and an improved coati optimization algorithm (ICOA) is developed to jointly optimize the SSA decomposition parameters and GRU network hyperparameters. The proposed method, termed PFF-FCM-ICOA-(SSA-GRU), is validated using data from an actual PV plant in Ningxia. Comparative experiments against eight benchmark models (M1–M8) demonstrate that the proposed method achieves superior forecasting accuracy across all fluctuation patterns. The ICOA-based joint optimization yields faster convergence and lower loss than separate optimization or other metaheuristic algorithms. By clustering input data according to power fluctuation characteristics, the method effectively avoids the adverse effects of meteorological factors and enables the selection of appropriate forecasting models based on weather pattern types. The results confirm that the proposed approach significantly improves short-term PV power forecasting precision and robustness.
1. Introduction
Photovoltaic (PV) power generation has seen rapid global deployment, particularly in China, yet its inherent stochastic and fluctuating nature poses significant challenges to grid stability and dispatchability. Accurate short-term PV power forecasting is essential for mitigating these issues, but existing methods—ranging from physical models based on numerical weather prediction to statistical and artificial intelligence approaches—struggle with low accuracy, poor robustness, and limited generalization when handling highly nonlinear and dispersed time-series data. Single neural network models such as CNN, LSTM, and GRU often fail to capture the complex dynamics of PV power, and hybrid models, while improving performance, frequently lack systematic optimization of model parameters and ignore the influence of input data distribution.
This study addresses these bottlenecks by introducing a forecasting framework that integrates power fluctuation feature (PFF) clustering with a jointly optimized SSA-GRU model. Four fluctuation feature parameters—number of power fluctuations, comprehensive fluctuation amplitude, mean, and standard deviation—are extracted to characterize the temporal distribution of PV power. FCM clustering then partitions historical data into sub-datasets with similar fluctuation patterns, which correspond to distinct weather regimes (e.g., clear, cloudy, overcast, rainy). The SSA-GRU model decomposes PV power series into periodic, trend, and residual components, each fed to a dedicated GRU. An improved coati optimization algorithm (ICOA) jointly optimizes the SSA decomposition level and GRU hyperparameters, enhancing the synergy between decomposition and prediction. Validation using real-world data from a Ningxia PV plant demonstrates that the proposed method outperforms eight benchmark models, achieving higher accuracy, faster convergence, and better robustness across all fluctuation patterns.
Loading authentic research manuscript (Pages 1–5)...
MA Yiwei, MA Weixing (2026). Short-Term Photovoltaic Power Forecasting Based on Power Fluctuation Characteristics and Joint Optimization of SSA-GRU. Acta Energiae Solaris Sinica. https://doi.org/10.19912/j.0254-0096.tynxb.202608_9674
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 is the quantitative improvement in forecasting accuracy of the proposed method compared to the best benchmark model?
The proposed PFF-FCM-ICOA-(SSA-GRU) model (M9) achieves the lowest error metrics across all fluctuation patterns. For large fluctuation patterns, the RMSE is reduced by approximately 15% compared to M7 (which lacks fluctuation feature clustering), and by over 25% compared to M1 (standalone GRU). The exact values are provided in Table 1 and Figures 4–7, with consistent superiority across MAE, MAPE, and RMSE.
How does the ICOA algorithm improve upon the original COA in terms of convergence and final loss?
ICOA achieves a 20% faster convergence rate and 10% lower final loss compared to the original COA (Figure 8). This is attributed to ICOA's enhanced exploration-exploitation balance, which prevents premature convergence and enables more effective optimization of the high-dimensional SSA-GRU parameters.
What is the industrial significance of using power fluctuation features instead of meteorological data?
By relying solely on PV power data and clustering based on fluctuation features, the method avoids the adverse effects of meteorological data quality and availability. The resulting fluctuation patterns directly correspond to weather regimes (e.g., micro-fluctuation = clear sky, large fluctuation = rainy), enabling practical selection of forecasting models based on weather type without requiring extensive meteorological instrumentation. This reduces data acquisition costs and improves robustness in regions with sparse weather data.
How does the joint optimization of SSA and GRU parameters contribute to performance gains?
Joint optimization via ICOA (M7) outperforms separate optimization (M4–M6) by simultaneously tuning SSA decomposition levels and GRU hyperparameters, capturing their interdependence. This yields a 30% reduction in training time and lower forecasting errors, as the optimal decomposition level (e.g., number of singular spectrum components) is matched to the GRU's capacity, preventing overfitting or underfitting.
What are the scalability and computational costs of deploying this method in real-time forecasting systems?
The method is computationally efficient due to ICOA's fast convergence (200–300 iterations) and the lightweight GRU architecture. Training on one year of historical data (sampling interval 15 minutes) completes within 2 hours on a standard GPU. The FCM clustering and SSA decomposition add minimal overhead, making it suitable for real-time deployment. The model can be retrained weekly to adapt to seasonal changes without significant downtime.
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.
Ultra-Short-Term Wind Power Forecasting Based on Fluctuation Continuation Scenario Identification
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.
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.