To improve photovoltaic (PV) power forecasting under variable meteorological conditions, this paper proposes a hybrid model combining signal decomposition, clustering, and deep learning. An improved complete ensemble empirical mode decomposition with adaptive noise method is used for multi-scale decomposition of meteorological inputs such as temperature, solar radiation, and wind direction. Sample entropy-guided K-means clustering segments signals into high, medium, and low-frequency components, with high-frequency parts further denoised using variational mode decomposition. A convolutional neural network-bidirectional long short-term memory network is then optimized by the crown porcupine optimization algorithm to fine-tune key hyperparameters. Experiments on real PV data show a 20% root mean squared error reduction (to 7.30 kW), demonstrating strong adaptability and robustness for intelligent PV scheduling.
Short-term wind power prediction is pivotal for maintaining the stability of power grids characterized by high renewable energy penetration. However, wind power time series exhibit complex characteristics, including local turbulence-induced fluctuations and long-term temporal dependencies, which challenge traditional forecasting models. Furthermore, the performance of hybrid deep learning models is often compromised by the difficulty of tuning hyperparameters over non-convex optimization surfaces. To address these challenges, this study proposes a novel framework: CPO—BiTCN—BiGRU—Attention. Adopting a physically motivated “Filter–Memorize–Focus” strategy, the model first employs a Bidirectional Temporal Convolutional Network (BiTCN) with dilated causal convolutions to extract multi-scale local features and denoise raw data. Subsequently, a Bidirectional Gated Recurrent Unit (BiGRU) captures global temporal evolution, while an attention mechanism dynamically weights critical time steps corresponding to ramp events. To mitigate hyperparameter uncertainty, the Crowned Porcupine Optimization (CPO) algorithm is introduced to adaptively tune the network structure, balancing global exploration and local exploitation more effectively than traditional swarm algorithms. Experimental results obtained from real-world wind farm data in Xinjiang, China, demonstrate that the proposed model consistently outperforms State-of-the-Art benchmark models. Compared with the best competing methods, the proposed framework reduces MAE and MAPE by approximately 30–45%, while maintaining competitive RMSE performance, indicating improved average forecasting accuracy and robustness under varying operating conditions. The results confirm that the proposed architecture effectively decouples local noise from global trends, providing a robust and practical solution for short-term wind power forecasting in grid dispatching applications.
Thermal power plants rely on extensive sensor networks to monitor key operational parameters, yet harsh industrial environments often lead to incomplete data characterized by significant noise, complex physical dependencies, and abrupt state transitions. This impedes accurate monitoring and predictive analyses. To address these domain-specific challenges, we propose a novel Hybrid Multi-Head Attention (HybridMHA) model for time series imputation. The core novelty of our approach lies in the synergistic combination of diagonally-masked self-attention and dynamic sparse attention. Specifically, the diagonally-masked component strictly preserves temporal causality to model the sequential evolution of plant states, while the dynamic sparse component selectively identifies critical cross-variable dependencies, effectively filtering out sensor noise. This tailored design enables the model to robustly capture sparse physical inter-dependencies even during abrupt operational shifts.Using a real-world dataset from a thermal power plant, our model demonstrates statistically significant improvements, outperforming existing methods by 10%–20% on key metrics. Further validation on a public benchmark dataset confirms its generalizability. These findings highlight the model's potential for robust real-time monitoring in complex industrial applications. The code is publicly available at: https://github.com/huangls2024/ImputationTSD.