Photovoltaic power generation prediction constitutes a significant research area within the realm of power system artificial intelligence. Accurate prediction of future photovoltaic output is imperative for the optimal dispatchment and secure operation of the power grid. This study introduces a photovoltaic prediction model, termed ICEEMDAN-Bagging-XGBoost, aimed at enhancing the accuracy of photovoltaic power generation predictions. In this paper, the original photovoltaic power data initially undergo decomposition utilizing the Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN) algorithm, with each intrinsic mode function (IMF) derived from this decomposition subsequently reconstructed into high-frequency, medium-frequency, and low-frequency components. Targeting the high-frequency and medium-frequency components of photovoltaic power, a limiting gradient boosting tree (XGBoost) is employed as the foundational learner in the Bagging parallel ensemble learning method, with the incorporation of a sparrow search algorithm (SSA) to refine the hyperparameters of XGBoost, thereby facilitating more nuanced tracking of the changes in the photovoltaic power’s high-frequency and medium-frequency components. Regarding the low-frequency components, XGBoost-Linear is utilized to enable rapid and precise prediction. In contrast with the conventional superposition reconstruction approach, this study employs XGBoost for the reconstruction of the prediction output’s high-frequency, intermediate-frequency, and low-frequency components. Ultimately, the efficacy of the proposed methodology is substantiated by the empirical operation data from a photovoltaic power station in Hebei Province, China. Relative to integrated and traditional single models, this paper’s model exhibits a markedly enhanced prediction accuracy, thereby offering greater applicational value in scenarios involving short-term photovoltaic power prediction.

Accurate interval forecasting of wind power is crucial for ensuring the safe, stable, and cost-effective operation of power grids. In this paper, we propose a hybrid deep learning model for day-ahead wind power interval forecasting. The model begins by utilizing a Gaussian mixture model (GMM) to cluster daily data with similar distribution patterns. To optimize input features, a feature selection (FS) method is applied to remove irrelevant data. The empirical wavelet transform (EWT) is then employed to decompose both numerical weather prediction (NWP) and wind power data into frequency components, effectively isolating the high-frequency components that capture the inherent randomness and volatility of the data. A convolutional neural network (CNN) is used to extract spatial correlations and meteorological features, while the bidirectional gated recurrent unit (BiGRU) model captures temporal dependencies within the data sequence. To further enhance forecasting accuracy, a multi-head self-attention mechanism (MHSAM) is incorporated to assign greater weight to the most influential elements. This leads to the development of a day-ahead wind power interval forecasting model based on GMM-FS-EWT-CNN-BiGRU-MHSAM. The proposed model is validated through comparison with a benchmark forecasting model and demonstrates superior performance. Furthermore, a comparison with the interval forecasts generated using the NPKDE method shows that the new model achieves higher accuracy.

With the increasing prominence of the energy crisis and environmental problems, microgrid technology has received widespread attention as an important technical means to improve the stability and reliability of new energy access. Focusing on the latest development of microgrid operation control technology, this paper combs and summarizes the related research at home and abroad, including the key technologies of microgrid optimization operation, power prediction and virtual synchronous active support control technology, and points out their advantages and limitations. First, this review describes the concept and structure of microgrids, including components such as distributed power sources, energy storage devices, energy conversion devices and loads. Then, the microgrid optimization operation technologies are analyzed in detail, including energy management optimization algorithms for efficient use of energy and cost reduction. Focusing on microgrid power forecasting techniques, including wind energy and PV power forecasting and load forecasting, the contributions and impacts of different power forecasting methods are summarized. Furthermore, the inverter control strategies and the stability mechanism of the virtual synchronous generator (VSG) active support control technology are investigated. Finally, synthesizing domestic and international microgrid development experience, this review summarizes the current state-of-the-art technologies, analyzes the advantages and limitations of these key technologies (including optimization scheduling, power prediction and VSG-based active support control) and highlights the necessity of their continuous improvement to provide a solid foundation for promoting the widespread application and sustainable development of microgrid technology.

With the increasing proportion of renewable energy in power systems, the applications of mobile energy storage systems (MESSs) with better flexibility and controllability are becoming more widespread. To further explore the hybrid ESS optimization scheduling problem of MESS and SESS, this paper first quantifies parts of actual road topologies in Dali City, China, and combines the Dijkstra algorithm to obtain an MESS path optimization framework. Subsequently, a hybrid ESS optimization scheduling model combining MESS and SESS is constructed with the objective functions of maximizing the scheduling benefits of the hybrid ESS and minimizing system voltage deviation. Finally, the non-dominated sorting genetic algorithm III (NSGA-III) is used to solve the hybrid ESS optimization scheduling model. To verify the effectiveness of the proposed method, this paper selected typical daily load and renewable energy output data in winter in Dali for the case study. The final result shows that the total profit of the optimized scheduling of the hybrid ESS is CNY 578, of which the arbitrage income is CNY 1119.2 and the total cost is CNY 540.44. Meanwhile, the voltage distribution range and total power loss are optimized from [0.9616, 1.0105] to [0.9723, 1.0008] and 0.963 MW to 0.9134 MW, which indicates that the coordinated scheduling of hybrid ESS is the key to improving the reliability of distribution network operation, and the path optimization of MESS is crucial for enhancing its profitability.

Electric vehicles (EVs) and thermostatically controlled loads (TCLs) are key demand-side resources for load regulation in modern power systems. However, effective load regulation faces significant challenges due to the stochastic nature of EV travel times and environmental uncertainties, such as temperature and solar irradiation fluctuations affecting TCL performance. Additionally, load rebound effects, caused by TCLs increasing power consumption to restore preset indoor temperatures after regulation, may induce secondary demand peaks, thereby offsetting regulation benefits. To address these challenges, this study aims to meet regulation requirements under such uncertainties while mitigating rebound-induced peaks. A rolling-horizon co-optimization method for EV and TCL clusters is proposed, which explicitly considers both uncertainties, load rebound effects and economic losses. First, to address the limited regulation capacity of individual EVs and TCLs, a user clustering mechanism is developed based on willingness to participate in demand response across multiple time intervals. A load rebound evaluation model for TCL clusters is developed to characterize post-regulation load variations and assess the rebound intensity. Subsequently, a load rebound-aware co-optimization model is proposed and solved within a rolling-horizon optimization approach, which performs rolling optimization within each prediction horizon to determine the participating clusters and their regulation capacities for each execution time slot under uncertainties. Simulation results demonstrate that the proposed method, compared with conventional day-ahead and robust optimization, not only meets load regulation requirements under uncertainty, but also effectively mitigates rebound-induced secondary peaks while achieving economic benefits.