Haibo Li

This paper presents an optimized hybrid deep learning model for power load forecasting—QR-FMD-CNN-BiGRU-Attention—that integrates similar day selection, load decomposition, and deep learning to address the nonlinearity and volatility of power load data. Firstly, the original data are classified using Gaussian Mixture Clustering optimized by ICPO (ICPO-GMM), and similar day samples consistent with the predicted day category are selected. Secondly, the load data are decomposed into multi-scale components (IMFs) using feature mode decomposition optimized by ICPO (ICPO-FMD). Then, with the IMFs as targets, the quantile interval forecasting is trained using the CNN-BiGRU-Attention model optimized by ICPO. Subsequently, the forecasting model is applied to the features of the predicted day to generate interval forecasting results. Finally, the model’s performance is validated through comparative evaluation metrics, sensitivity analysis, and interpretability analysis. The experimental results show that compared with the comparative algorithm presented in this paper, the improved model has improved RMSE by at least 39.84%, MAE by 26.12%, MAPE by 45.28%, PICP and MPIW indicators by at least 3.80% and 2.27%, indicating that the model not only outperforms the comparative model in accuracy, but also exhibits stronger adaptability and robustness in complex load fluctuation scenarios.

Timely and accurate detection of wind turbine blade surface defects is crucial for ensuring operational safety and improving maintenance efficiency with respect to large-scale wind farms. However, existing methods often suffer from poor generalization, background interference, and inadequate real-time performance. To overcome these limitations, we developed an end-to-end defect recognition framework, structured as a three-stage process: blade localization using YOLOv5, robust feature extraction via the large vision model DINOv2, and defect classification using a Stochastic Configuration Network (SCN). Unlike conventional CNN-based approaches, the use of DINOv2 significantly improves the capability for representation under complex textures. The experimental results reveal that the proposed method achieved a classification accuracy of 97.8% and an average inference time of 19.65 ms per image, satisfying real-time requirements. Compared to traditional methods, this framework provides a more scalable, accurate, and efficient solution for the intelligent inspection and maintenance of wind turbine blades.

With the increasing share of renewable energy generation and the integration of large-scale electric vehicles (EVs) into the grid, the reasonable charging and discharging scheduling of electric vehicles is essential for the stable operation of power grid. Therefore, this paper proposes a bi-objective optimal scheduling strategy for microgrids based on the participation of electric vehicles in vehicle-to-grid technology (V2G) mode. Firstly, the system structure for electric vehicles participating in the charging and discharging schedule was established. Secondly, a bi-objective optimization model was formulated, considering load mean square error and user charging cost. A heuristic method was employed to handle constraints related to system energy balance and equipment output. Then, the Monte Carlo method was employed to simulate electric vehicle loads and to facilitate the generation of and reduction in scenario scenes. Finally, the model was solved using an improved multi-objective barebones particle swarm optimization algorithm. The simulation results show that the proposed scheduling strategy has a lower charging cost (CNY 11,032.4) and lower load mean square error (12.84 × 10⁵ kW²) than the strategy employed in the comparison experiment, which ensures the economic and stable operation of the microgrid.

State of health (SOH) estimation plays a vital role in ensuring the safe and stable operation of lithium-ion battery management systems (BMSs). Data-driven methods are widely used to estimate SOH; however, existing methods often suffer from fixed or excessively high feature dimensions, impacting the model’s adjustability and applicability. This study first proposed a layered knee point strategy based on the charging voltage curve, which reduced the complexity of feature extraction. Then, a new hybrid framework called the adaptive gated sequence network (AGSN) model was proposed. This model integrated independently recurrent neural network (IndRNN) layers, active state tracking long short-term memory (AST-LSTM) layers, and adaptive gating mechanism (AGM) layers. By integrating a multi-layered structure and an adaptive gating mechanism, the SOH prediction performance was significantly improved. Finally, batteries under different operating conditions were tested using the NASA battery dataset. The results show that the AGSN model demonstrated higher accuracy and robustness in battery SOH estimation, with estimation errors consistently within 1%.

Accurate short-term load forecasting is of great significance in improving the dispatching efficiency of power grids, ensuring the safe and reliable operation of power grids, and guiding power systems to formulate reasonable production plans and reduce waste of resources. However, the traditional short-term load forecasting method has limited nonlinear mapping ability and weak generalization ability to unknown data, and it is prone to the loss of time series information, further suggesting that its forecasting accuracy can still be improved. This study presents a short-term power load forecasting method based on Bagging-stochastic configuration networks (SCNs). First, the missing values in the original data are filled with the average values. Second, the influencing factors, such as the weather- and week-type data, are coded. Then, combined with the data of influencing factors after coding, the Bagging-SCNs integration algorithm is used to predict the short-term load. Finally, by taking the daily load data of Quanzhou City, Zhejiang Province as an example, the program of the abovementioned method is compiled in Python language and then compared with the long short-term memory neural network algorithm and the single-SCNs algorithm. Simulation results show that the proposed method for medium- and short-term load forecasting has a high forecasting accuracy and a significant effect on improving the accuracy of load forecasting.

Ultra-short-term power load forecasting (USTPLF) can provide strong support and guarantee the decisions on unit start-up, shutdown, and power adjustment. The ultra-short-term power load (USTPL) has strong non-smoothness and nonlinearity, and the time-series characteristics of the load data themselves are difficult to explore. Therefore, to fully exploit the intrinsic features of the USTPL, a stochastic configuration networks (SCNs) USTPLF method based on K-means clustering (K-means) and empirical mode decomposition (EMD) is proposed. First, the load data are decomposed into several intrinsic mode functions (i.e., IMFs) and residuals (i.e., Res) by EMD. Second, the IMFs are classified by K-means, and the IMF components of the same class are summed. Third, the SCNs is used to forecast the electric load on the basis of the classified data. Lastly, on the basis of the real load of Shenzhen City, the proposed method is applied for emulation authentication. The result verifies the efficiency of the proposed measure.

Electric-heat coupling characteristics of a cogeneration system and the operating mode of fixing electricity with heat are the main reasons for wind abandonment during the heating season in the Three North area. To improve the wind-power absorption capacity and operating economy of the system, the structure of the system is improved by adding a heat storage device and an electric boiler. First, aiming at the minimum operating cost of the system, the optimal scheduling model of the cogeneration system, including a heat storage device and electric boiler, is constructed. Second, according to the characteristics of the problem, a cultural gene algorithm program is compiled to simulate the calculation example. Finally, through the system improvement, the comparison between the conditions before and after and the simulation solutions of similar algorithms prove the effectiveness of the proposed scheme. The simulation results show that adding the heat storage device and electric boiler to the scheduling optimization process not only improves the wind power consumption capacity of the cogeneration system but also reduces the operating cost of the system by significantly reducing the coal consumption of the unit and improving the economy of the system operation. The cultural gene algorithm framework has both the global evolution process of the population and the local search for the characteristics of the problem, which has a better optimization effect on the solution.

The rigid constraint of using heat in determining electricity for thermal power units is eliminated to improve the absorption capacity of wind power. In this study, heat storage devices and electric boilers are added to the cogeneration system to alleviate the wind curtailment phenomenon. First, the main reasons for wind curtailment are analyzed according to the structural characteristics of the power supply in the northern part of China. Second, a scheduling model of a cogeneration system, including a heat storage device and an electric boiler, is constructed. An improved artificial bee colony algorithm program is also designed and compiled based on MATLAB. Finally, the feasibility of the proposed scheme is verified by simulation examples, and an economic analysis of wind power consumption is performed. Results show that adding electric boilers lessens coal consumption costs and improves economic benefits.