This paper proposes an interpretable optimization method for power grid outage scheduling based on reinforcement learning. An outage scheduling optimization model is proposed, considering the convergence of power flow calculation, voltage violations, and operational economic behavior as objectives, while considering constraints such as simultaneous outage constraints, mutually exclusive constraints, and maintenance windows. Key features of the outage schedule are selected based on Shapley values to construct a Markov optimization model for outage scheduling. A deep reinforcement learning agent is established to optimize the outage schedule. The proposed method is applied to the IEEE-39 and IEEE-118 bus system for validation. Experimental results show that the proposed method outperforms existing algorithms in terms of voltage violation, total power losses, and computational time. The proposed method eliminates all voltage violations and reduces active power losses up to 5.7% and computation time by 6.8 h compared to conventional heuristic algorithms.
To address the lack of effective risk-identification methods during the commissioning of new power grid equipment, we propose a knowledge graph construction approach for both scheme generation and risk identification. First, a gated attention mechanism fuses textual semantics with knowledge embeddings to enhance feature representation. Then, by introducing a global memory matrix with a decay-factor update mechanism, long-range dependencies across paragraphs are captured, yielding a domain-knowledge-augmentation universal information-extraction framework (DKA-UIE). Using the DKA-UIE, we learn high-dimensional mappings of commissioning-scheme entities and their labels, linking them according to equipment topology and risk-identification logic to build a commissioning knowledge graph for new equipment. Finally, we present an application that utilizes this knowledge graph for the automated generation of commissioning plans and risk identification. Experimental results show that our model achieves an average precision of 99.19%, recall of 99.47%, and an F1-score of 99.33%, outperforming existing methods. The resulting knowledge graph effectively supports both commissioning-plan generation and risk identification for new grid equipment.
To enhance online dispatch decision support capabilities for power grid outage planning, this study proposes a Universal Information Extraction (UIE)-based method for enhanced named entity recognition and event extraction from outage documents. First, a Structured Extraction Language (SEL) framework is developed that unifies the semantic modeling of outage information to generate standardized representations for dual-task parsing of events and entities. Subsequently, a trigger-centric event extraction model is developed through feature learning of outage plan triggers and syntactic pattern entities. Finally, the event extraction model is employed to identify operational objects and action triggers, while the entity recognition model detects seven critical equipment entities within these operational objects. Validated on real-world outage plans from a provincial-level power dispatch center, the methodology demonstrates reliable detection capabilities for both named entity recognition and event extraction. Relative to conventional techniques, the F1 score increases by 1.08% for event extraction and 2.48% for named entity recognition.
This research proposes a robustness analysis model for the frequency performance of grid-forming converter systems (GFMCS). Based on the derived sensitivity and complementary sensitivity functions, a system robustness identification framework is established. This framework includes two key frequency performance indices: sensitivity and robust stability. Sensitivity analysis is used to describe the system’s sensitivity to external disturbances. In addition, the judgment criterion is proposed to quantitatively and intuitively identify the robustness of the GFMCS. Furthermore, the influence mechanisms of the damping and inertia coefficients on robustness are examined comprehensively. This study finds that when the damping coefficient is small, and the inertia coefficient is large, the system is more prone to oscillatory instability, resulting in longer stability time as well as poorer robustness. Finally, the theoretical analysis is validated experimentally.
As a mainstream new energy generation technology, elucidating the grid-connected voltage stability mechanisms of permanent magnet synchronous generator (PMSG) is critical for ensuring stable integration of high-penetration renewable energy. Existing research on the voltage stability of grid-connected PMSG systems is confined to single-fault scenarios, failing to adequately account for the impacts of other significant internal grid disturbances, such as direct current blockings and increased renewable energy penetration. Moreover, the traditionally used simplified grid model with a voltage source in series with an impedance is overly idealized, making it difficult to comprehensively reveal the transient stability mechanisms of grid-connected PMSG systems under complex multi-disturbance conditions. To address this issue, this paper proposes a numerical analysis method to investigate the grid stability mechanisms of PMSG systems under various grid disturbance scenarios. First, an electromagnetic transient simulation model of the grid-connected PMSG system is established. Next, key parameters influencing the system’s voltage stability are identified using the global sensitivity Sobol method. Subsequently, a transient voltage stability assessment index and a method for revealing the grid stability patterns of PMSG systems are presented. Finally, the PMSG system is integrated into the CSEE standard test system on the CloudPSS platform for validation and analysis. The results demonstrate that the proposed method effectively reveals voltage stability mechanisms considering various internal grid disturbances, and the mechanistic characteristics it reveals differ significantly from conclusions drawn using a simplified grid model.
1 December 2023 in Journal of Physics: Conference Series
Transmission sections have great significance in modern power systems. Given the phenomenon of frequent power outages caused by the chain tripping of transmission sections, a method for transmission section search based on the variable-scale affinity propagation clustering algorithm is proposed. Considering only the connection relationship, the power system model can be simplified to a topological map in graph theory for analysis. So firstly the algorithm considers the importance of each line from the perspectives of the structure of the graph and the actual operation of the power flow and then uses the variable-scale affinity propagation clustering algorithm for the network based on this value with the change of the number of cluster centers. The network will be partitioned at different scales, then find out the partition contact line at different scales, and judge whether it is a transmission cross-section by the power flow direction and the number of contact lines. This method can search out as many potential transmission sections of the power network as possible to provide more monitored objects for the staff and reduce the probability of large power outages. Finally, simulation in the IEEE-118-bus system and the IEEE-39-bus system verifies the effectiveness of the proposed method.