To address the challenges posed by the volatility and uncertainty of wind power generation, this study presents a hybrid model combining complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), variational mode decomposition (VMD), convolutional neural network (CNN), and bidirectional long short-term memory (BiLSTM) for wind power forecasting. The model first employs CEEMDAN to decompose the original wind power sequence into multiple scales, obtaining several intrinsic mode functions (IMFs). These IMFs are then classified using sample entropy and k-means clustering, with high-frequency IMFs further decomposed using VMD. Next, the decomposed signals are processed by a CNN to extract local spatiotemporal features, followed by a BiLSTM network that captures bidirectional temporal dependencies. Experimental results demonstrate the superiority of the proposed model over ARIMA, LSTM, CEEMDAN-LSTM, and VMD-CNN-LSTM models. The proposed model achieves a mean squared error (MSE) of 67.145, a root mean squared error (RMSE) of 8.192, a mean absolute error (MAE) of 6.020, and a coefficient of determination (R2) of 0.9840, indicating significant improvements in forecasting accuracy and reliability. This study offers a new solution for enhancing wind power forecasting precision, which is crucial for efficient grid operation and energy management.

To address the nonlinear and non-stationary characteristics of dissolved gas concentration data in transformer oil, this paper proposes a hybrid prediction model (VMD-SSA-LSTM-SE) that integrates Variational Mode Decomposition (VMD), the Whale Optimization Algorithm (WOA), the Sparrow Search Algorithm (SSA), Long Short-Term Memory (LSTM), and the Squeeze-and-Excitation (SE) attention mechanism. First, WOA dynamically optimizes VMD parameters (mode number k and penalty factor α to effectively separate noise and valid signals, avoiding modal aliasing). Then, SSA globally searches for optimal LSTM hyperparameters (hidden layer nodes, learning rate, etc.) to enhance feature mining for non-continuous data. The SE attention mechanism recalibrates channel-wise feature weights to capture critical time-series patterns. Experimental validation using real transformer oil data demonstrates that the model outperforms existing methods in prediction accuracy and computational efficiency. For instance, the CH₄ test set achieves a Mean Absolute Error (MAE) of 0.17996 μL/L, a Mean Absolute Percentage Error (MAPE) of 1.4423%, and an average runtime of 82.7 s, making it significantly faster than CEEMDAN-based models. These results provide robust technical support for transformer fault prediction and condition-based maintenance, highlighting the model’s effectiveness in handling non-stationary time-series data.

To address the challenges posed by the volatility and uncertainty of wind power generation, this study presents a hybrid model combining Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN), Variational Mode Decomposition (VMD), Convolutional Neural Network (CNN), and Bidirectional Long Short-Term Memory (BiLSTM) for wind power forecasting. The model first employs CEEMDAN to decompose the original wind power sequence into multiple scales, obtaining several Intrinsic Mode Functions (IMFs). These IMFs are then classified using sample entropy and k-means clustering, with high-frequency IMFs further decomposed using VMD. Next, the decomposed signals are processed by a CNN to extract local spatiotemporal features, followed by a BiLSTM network that captures bidirectional temporal dependencies. Experimental results demonstrate the superiority of the proposed model over ARIMA, LSTM, CEEMDAN-LSTM, and VMD-CNN-LSTM models. The proposed model achieves a mean squared error (MSE) of 67.145, root mean squared error (RMSE) of 8.192, mean absolute error (MAE) of 6.020, and a coefficient of determination (R2) of 0.9840, indicating significant improvements in forecasting accuracy and reliability. This study offers a new solution for enhancing wind power forecasting precision, which is crucial for efficient grid operation and energy management. Future work will focus on optimizing the model structure and parameters to reduce computational costs and improve robustness, further advancing the application of hybrid models in wind power forecasting.

In the context of global sustainability goals and the integration of renewable energy sources, the efficient and reliable performance of medium- and high-voltage power equipment is critical. This paper presents a high-capacity testing system based on power supply, which significantly enhances the sustainability of power systems by addressing the challenges of low testing efficiency, poor reproducibility, and safety hazards in traditional methods. By proposing a standardized test circuit configuration and an automated monitoring and control system, this study aims to improve the efficiency, safety, and consistency of testing, thereby supporting the reliable operation and integration of renewable energy sources into power grids. The system achieves complete automation in test parameter selection, circuit connection, and data acquisition, reducing human intervention and ensuring the accuracy of test data. Through simulations and physical tests, the feasibility and accuracy of the standardized test circuit design method have been verified. These improvements contribute to sustainable development by reducing resource consumption and environmental impact, and enhancing the reliability and stability of power supply. This research provides a technical foundation for the sustainable operation of power systems, supporting global efforts to achieve carbon neutrality and energy transitions.

With the expansion of power system scale and the advancement of new energy grid integration, the performance verification of medium and high-voltage power equipment faces increasingly stringent requirements. This paper addresses the issues of low efficiency, poor reproducibility, and safety hazards in traditional large-scale testing by proposing a system model for a high-capacity test system and a measurement and control system solution based on power system power sources. By establishing simulation models of the main test circuits, the paper analyzes the short-circuit currents and Transient Recovery Voltage (TRV) waveforms of high-voltage switchgear and introduces a standardized method for configuring test circuits. This method has been validated through simulations and physical tests, demonstrating its feasibility and accuracy. Based on this, a standardized method for test circuits is proposed, and its feasibility is verified through practical testing. Additionally, an automated monitoring and control system is designed to streamline the testing process, reduce human intervention, and ensure the accuracy of test data, achieving full-process automation in test parameter selection, circuit connection, and data acquisition. This system significantly enhances testing efficiency, safety, and consistency, effectively improving the efficiency and reliability of inspections and testing for medium and high-voltage power equipment.