INTRODUCTION: Grid-Forming Energy Storage Converter (GFM-ESC) is a key interface equipment for the coordinated regulation of source and network in new power systems. However, the dynamic coupling mechanism between its multi-topology structures such as direct-mounted, string-type, and centralized types and large disturbance scenarios (new energy power fluctuations, power grid transient shocks) has not yet been clarified. OBJECTIVES: Existing robust control methods do not embed topological feature constraints and are difficult to ensure the system stability margin under large disturbances under multi-topology. This theoretical gap limits the scene adaptability of GFM-ESC. In response to the above scientific issues, this paper focuses on Robust Stability Control Theory and Characteristics Analysis of Networked Energy Storage Converters under Large Disturbance Scenarios. METHODS: First, a large disturbance dynamic model of multi-topology GFM-ESC was established. By analyzing the mapping relationship among wiring topology, component parameters and system state matrix, the energy flow mechanism and eigenvalue trajectory instability inducements of GFM-ESC under different topologies were revealed during large disturbances, and the influence of topological parameters on the system was quantified. Secondly, grounded on H∞ robust control theory, a robust stable control method for topology adaptation was proposed, a closed-loop control law embedded with topological features was derived, and Lyapunov stability theory was used to prove the robust convergence of this control method under large disturbances and topological parameter perturbation scenarios. Finally, through small signal analysis and large disturbance numerical simulation, the performance of the developed theory and method was verified. RESULTS: Findings showed that the developed dynamic model can accurately describe the large disturbance characteristics of multi-topology GFM-ESC, and the corresponding robust control method can increase the system stability margin by 42%, and can still maintain the asymptotic stability of the closed-loop system when the topological parameters were perturbed by 15%. CONCLUSION: The results of this study enhance the theoretical system for controlling large disturbances in the multi-topology GFM-ESC, providing a foundation for the collaborative design of GFM-ESC topologies in new power systems.
INTRODUCTION: Day-ahead electricity prices exhibit pronounced volatility, nonlinearity, and temporal dependence. Training models on all available historical observations may introduce irrelevant information and reduce forecasting reliability. OBJECTIVES: This study proposes a hybrid forecasting framework that integrates same-period similar-scenario retrieval with intelligent hyperparameter optimization to improve the forecasting performance of day-ahead market-clearing prices. By refining the composition of the training dataset and optimizing the network configuration, the proposed framework enhances the model’s ability to learn the underlying dynamics of historical electricity prices. METHODS: First, similarity measures are used to evaluate historical electricity price sequences from corresponding periods. Historical observations that are highly relevant to the target forecasting period are then selected to construct a tailored training dataset. Subsequently, a hybrid CNN–BiLSTM–AM forecasting model is developed. Within this architecture, the convolutional neural network (CNN) extracts local patterns and salient features from the input data, while the bidirectional long short-term memory network (BiLSTM) captures long-term temporal dependencies in both forward and backward directions. The attention mechanism (AM) adaptively assigns weights to the learned representations, thereby emphasizing features that contribute more substantially to the final prediction. The dung beetle optimization (DBO) algorithm is further employed to optimize the key hyperparameters of the model. Finally, the effectiveness of the proposed method is evaluated using day-ahead market-clearing price data from the Miaojiaba Hydropower Station in the Bailong River Basin, Gansu Province, China. RESULTS: The empirical results demonstrate that the similarity-scenario-based sample reconstruction strategy effectively enhances the model’s ability to capture historical electricity price patterns. Taking a representative market price of 100 CNY/MWh as the reference, the proposed method reduces the standard deviation of forecasting errors by approximately 26 CNY/MWh compared with a conventional BiLSTM model without historical similar-sequence selection, thereby helping to mitigate potential revenue losses caused by electricity price forecasting deviations. CONCLUSION: The proposed framework effectively combines targeted sample selection, spatiotemporal feature learning, attention-based weighting, and hyperparameter optimization. It provides a reliable tool for day-ahead bidding decisions and supports efficient electricity resource allocation.
Accurate extraction of underlying features from electrical loads is crucial for intelligent microgrid management.To address the heterogeneous characteristics and microscopic nonstationary properties of industrial loads, a shunt-cooperative feature extraction framework relying on MSE is proposed in this work. Different from traditional methods that use a single feature extraction or clustering model to process the entire sequence, MSE is introduced to quantify the dynamic complexity of load sequences, and effective classification is performed for loads with strong and weak time-series characteristics. For strong time-series loads, a multi-view Variational AutoEncoder (VAE) deep clustering model with adaptive dual-distance metrics fused with Euclidean distance and LB_Keogh distance is constructed to accurately extract macroscopic typical power consumption patterns. For weak time-series loads, a “coarse screening-fine classification” hybrid decomposition architecture based on CEEMDAN-NGO-VMD is proposed, where the complexity index (LZC) is introduced to adaptively strip low-frequency trends and Northern Goshawk Optimization (NGO) is used to optimize VMD and suppress high-frequency mode aliasing. Simulation results show that, compared with the CEEMDAN-only method and the NGO-VMD-only algorithm, the proposed method achieves accurate extraction of multi-scale time-frequency features and effectively overcomes the mode aliasing problem of traditional decomposition methods in terms of clustering performance. Finally, complex loads are reconstructed into multi-modal feature components with clear physical meanings, providing a reliable feature basis for subsequent identification of multi-modal power consumption behaviors in industrial microgrids.
Accurate joint forecasting of hydro-wind-photovoltaic bases is difficult because hydropower regulation, wind randomness and photovoltaic intermittency interact through both temporal complementarity and spatial-electrical coupling. This study aims to improve source-level and bundled-power forecasting by embedding the complementary mechanism of heterogeneous renewable sources into both representation learning and model training. A hierarchical complementary-prior regularized multi-scale seasonal-trend decoupled heterogeneous graph Transformer, denoted MSTD-HGFormer-HCPR, is proposed. The model first separates the historical multi-source sequence into low-frequency trend and high-frequency fluctuation components through learnable multi-scale moving-average kernels. The two components are then encoded by parallel heterogeneous graph Transformer branches using temporal patch attention and a static-dynamic fused adjacency that combines physical topology, historical correlation and learnable latent relations. A gated fusion module produces the final forecast, while a composite loss introduces capacity-weighted system- level and correlation-aware topology-level complementary-prior constraints. Experiments on a real 17-node hydro-wind-photovoltaic base show that the proposed method reduces rRMSE by 12.9–50.6% against seven baselines, improves the correlation coefficient by 0.011–0.013 over the strongest baseline, and keeps the forecasting accuracy at or above 96.2% for hydro, wind, photovoltaic and aggregate outputs. A second, 23-node cascade-radial base with five-year records is further examined under a rolling-origin and season- stratified protocol; the aggregate rRMSE is reduced by 13.2–44.0%, and the pooled accuracies remain 96.0% for hydropower, 96.0% for wind, 96.4% for photovoltaic and 96.2% for aggregate outputs. The proposed regularized joint forecaster provides stable and accurate spatiotemporal prediction for complementary renewable bases and reduces the accumulation of source-level errors in bundled output forecasting.
INTRODUCTION: The increasing complexity of modern digital power grids demands intelligent and reliable fault detection and predictive maintenance solutions to ensure operational stability, resilience, and efficient asset management. Integrating cyber–physical systems with advanced deep learning techniques enables accurate monitoring and proactive maintenance of power transmission networks. OBJECTIVES: This study proposes a unified GRU-based cyber–physical framework for intelligent fault detection, fault classification, fault localization, and risk-based predictive maintenance in power transmission systems, while improving diagnostic accuracy, interpretability, and maintenance decision-making. METHODS: The proposed framework integrates multi-parametric voltage and current measurements from the physical layer with a gated recurrent unit (GRU) model in the cyber layer to capture the temporal dynamics of fault evolution. Domain-informed electrical features, including voltage deviation, phase imbalance index, and current severity index, are incorporated to improve physical interpretability. A multi-task learning strategy is employed to simultaneously detect faults, classify fault types, identify faulted transmission lines, estimate fault locations, and generate a risk-based maintenance index for proactive maintenance prioritization. RESULTS: The proposed framework achieved a fault classification accuracy of 98.61%, with precision of 0.9864, recall of 0.9861, and F1-score of 0.9861. Fault localization was performed with a low mean absolute error (MAE) of 0.0303, demonstrating high localization accuracy. The risk-based maintenance index effectively supported proactive maintenance prioritization for transmission assets. CONCLUSION: The proposed GRU-based cyber–physical framework provides an effective and scalable solution for intelligent power grid monitoring by integrating accurate fault detection, precise fault localization, and predictive maintenance within a unified architecture. The framework enhances operational reliability and supports data-driven maintenance strategies for next-generation digital power grids.
