This study presents a comprehensive impact analysis of the rotor angle stability of a proposed international connection between the Philippines and Sabah,Malaysia,as part of the Association of Southeast Asian Nations(...This study presents a comprehensive impact analysis of the rotor angle stability of a proposed international connection between the Philippines and Sabah,Malaysia,as part of the Association of Southeast Asian Nations(ASEAN)Power Grid.This study focuses on modeling and evaluating the dynamic performance of the interconnected system,considering the high penetration of renewable sources.Power flow,small signal stability,and transient stability analyses were conducted to assess the ability of the proposed linked power system models to withstand small and large disturbances,utilizing the Power Systems Analysis Toolbox(PSAT)software in MATLAB.All components used in the model are documented in the PSAT library.Currently,there is a lack of publicly available studies regarding the implementation of this specific system.Additionally,the study investigates the behavior of a system with a high penetration of renewable energy sources.Based on the findings,this study concludes that a system is generally stable when interconnection is realized,given its appropriate location and dynamic component parameters.Furthermore,the critical eigenvalues of the system also exhibited improvement as the renewable energy sources were augmented.展开更多
As the critical milestone for China’s Nationally Determined Contributions(NDCs)[1],2030 is a pivotal benchmark year for the transformation of China’s power system.From now to 2030,the rapid growth in installed capac...As the critical milestone for China’s Nationally Determined Contributions(NDCs)[1],2030 is a pivotal benchmark year for the transformation of China’s power system.From now to 2030,the rapid growth in installed capacity and power generation of wind and solar power will lead to profound changes in the stability mechanisms and balancing characteristics of power systems[[2],[3],[4],[5]],posing new challenges to system security and reliability.展开更多
With the high penetration of renewable energy and the rapid development of AC/DC(Alternating Current/Direct Current)hybrid power grid,the power grid is confronted with challenges such as frequent voltage fluctuations ...With the high penetration of renewable energy and the rapid development of AC/DC(Alternating Current/Direct Current)hybrid power grid,the power grid is confronted with challenges such as frequent voltage fluctuations and insufficient dynamic reactive power reserves.Full utilization of unified power flow controller(UPFC)in dynamic voltage regulation is of great significance for mitigating voltage excursions of the power grid.This paper proposes a double-time-scale dynamic reactive power optimization method for the AC/DC hybrid power grid with UPFC.A control framework for reactive power optimization of slow-time-scale and fast-time-scale is constructed incorporating the LCC-HVDC and UPFC.In this method,the slow-time-scale aims to improve the voltage profiles and reduce the system cost by setting the voltage regulation weight coefficients based on trajectory sensitivity to preserve reactive power regulation capability.The fast-time-scale adopts an adaptive feedback control mechanism.When slowtime-scale optimization is insufficient to keep the voltage within a safe range,it adjusts the real-time reactive power output of the UPFC,and damps rapid voltage swings accordingly.By implementing the additional fast-time-scale control method,the frequent variations of both the Photovoltaic(PV)and load are managed for the reactive power compensation.Case studies on a modified IEEE-30 bus system demonstrate that compared with the conventional control method,the proposed method reduces the maximum voltage deviation by 3.17%compared to the baseline,while ensuring the economic efficiency.展开更多
With the global drive toward carbon neutrality,the deep integration of variable renewable energy sources(VRES)and energy storage systems(ESS)has rendered traditional static carbon accounting methods insufficient to ca...With the global drive toward carbon neutrality,the deep integration of variable renewable energy sources(VRES)and energy storage systems(ESS)has rendered traditional static carbon accounting methods insufficient to capture the spatiotemporal dynamics of carbon flows in power grids,highlighting the critical need for accurate tracking and equitable allocation of carbon responsibility.This paper proposes a dynamic carbon emission flow tracking framework tailored to the Jibei power grid in China,integrating a dynamic generator carbon intensity model and power transfer distribution factor(PTDF)enhanced network tracking.The framework also includes an optimal carbon allocation matrix and a predictive ESS scheduling model that links the carbon intensity during charging periods to emissions during discharging.Validated using a modified IEEE 30-bus system representing five cities in the Jibei region,results show that the dynamic model achieves a 15.2%higher accuracy than static methods,optimal ESS scheduling reduces system-wide emissions by 8.7%,and the framework maintains over 93%tracking accuracy under extreme uncertainties.Moreover,the framework quantifies inter-city carbon transfers and allocates responsibilities among grid participants,thus enabling real-time monitoring.It provides a robust foundation for carbon-aware dispatch and nodal carbon pricing,supporting the transition toward carbon-neutral power systems.展开更多
Power system faults can trigger a massive influx of complex alarm signals to the operation and maintenance center,posing significant challenges for dispatchers in accurately identifying the underlying faults.To addres...Power system faults can trigger a massive influx of complex alarm signals to the operation and maintenance center,posing significant challenges for dispatchers in accurately identifying the underlying faults.To address the issues of sample imbalance and low accuracy in traditional power grid monitoring alarm event identification methods,a power grid monitoring alarm event identification method based on BERT large language model is proposed.Firstly,information entropy is employed to filter effective monitoring alarm signals,and the k-means clustering algorithm is used to group all alarm signals into different event types,forming the initial power grid monitoring alarm event samples.Then,to mitigate the issue of sample imbalance in power grid monitoring alarm events,a pre-trained SimBERT model is proposed to augment minority class samples,thereby reducing the imbalance ratio.Finally,the augmented samples of power grid monitoring alarm events are used to fine-tune the bidirectional encoder representation from transformer(BERT)model.A mix-training optimization strategy is adopted during fine-tuning to ultimately obtain the power grid monitoring alarm event identification model.Case study results demonstrate that the proposed model in this paper achieves superior identification precision of power grid monitoring alarm events compared to traditional deep learning methods.展开更多
Renewable energy is gaining momentum and is set to become the world’s largest source of electricity in 2025,overtaking coal for the first time.This fundamental shift-combined with rapid advances in artificial intelli...Renewable energy is gaining momentum and is set to become the world’s largest source of electricity in 2025,overtaking coal for the first time.This fundamental shift-combined with rapid advances in artificial intelligence(AI)-is accelerating the clean energy transition.However,it is also creating new challenges for the centuries-old electricity grid.AI and big data can help address these challenges,but significant hurdles remain.展开更多
In December 2025,the ASEAN Centre for Energy(ACE)convened the third ASEAN Power Grid Partnership Meeting,bringing partners together for consultations on key issues.After more than two decades of planning and explorati...In December 2025,the ASEAN Centre for Energy(ACE)convened the third ASEAN Power Grid Partnership Meeting,bringing partners together for consultations on key issues.After more than two decades of planning and exploration,the ASEAN Power Grid is now entering a new phase—shifting from predominantly bilateral,one-way connections toward a multilateral,multidirectional network.展开更多
This paper investigates the structural robustness of power grids against cascading failures from a geometric perspective based on the Ollivier-Ricci curvature.A curvature metric based on the grid’s admittance matrix ...This paper investigates the structural robustness of power grids against cascading failures from a geometric perspective based on the Ollivier-Ricci curvature.A curvature metric based on the grid’s admittance matrix is proposed,based on which structurally fragile sub-networks,transmission lines,or buses can be identified without relying on power flow calculations.Then a method is proposed to strengthen the structural robustness of the grid by adding new transmission lines in order to increase the values of the most negative curvatures.Furthermore,the connection between the proposed admittance-based Ollivier-Ricci curvature and edge betweenness centrality index is shown.Experimental results for benchmark power grids including IEEE 118-and 145-bus systems demon-strate the effective performance of the proposed curvature metric and the grid hardening method in capturing and enhancing the structural robustness of power grids.展开更多
To improve the efficiency of power grid emergency response after disasters,this study proposes a multi-modal risk profiling-driven power grid disaster emergency response strategy and dynamic resource synergy optimizat...To improve the efficiency of power grid emergency response after disasters,this study proposes a multi-modal risk profiling-driven power grid disaster emergency response strategy and dynamic resource synergy optimization model.A risk assessment model is constructed by integrating equipment health status,real-time failure rate,and power grid topology importance to generate equipment risk profiles for identifying key nodes.A two-stage optimization mechanism is then designed,the first stage achieves priority coverage of high-risk equipment and minimization of inspection costs through multi-objective path planning.The second stage adopts a mixed-integer programming model to coordinate personnel scheduling and material allocation under resource constraints.A rolling optimization framework is introduced to dynamically respond to sudden failures and resource changes,ensuring the adaptability of scheduling schemes.To verify the model’s effectiveness,three typical scenarios,”no sudden failures”,“equipment risk escalation”,and“personnel working hour constraints”,are simulated.Compared with traditional strategies,the model significantly improves the rationality and dynamic adaptability of resource scheduling,providing new ideas and engineering practice support for enhancing the resilience of smart grid disaster emergency response.展开更多
With the global economy integration and progress in energy transformation,it has become a general trend to surpass national boundaries to achieve wider and optimal energy resource allocations.Consequently,there is a c...With the global economy integration and progress in energy transformation,it has become a general trend to surpass national boundaries to achieve wider and optimal energy resource allocations.Consequently,there is a critical n eed to adopt scie ntific approaches in assessi ng cross-border power grid interconnection projects.First,con sidering the promotion of large-scale renewable energy resources and improvements in system adequacy,a comprehensive assessment index system,including costs,socio-economic benefits,environmental benefits,and technical benefits,is established in this study.Second,a synthetic assessment framework is proposed for cross-border power grid interconnection projects based on the index system comprising cost-benefit analysis,with market and network simulations,iterative methods for indicator weight evaluation,and technique for order preferenee by similarity to an ideal solution(TOPSIS)method for the project rankings.Fin ally,by assessi ng and comparing three cross-border projects betwee n Europe and Asia,the proposed index system and assessment framework have been proved to be effective and feasible;the results of this system can thus support investment decision-making related to such projects in the future.展开更多
The intelligent operation management of distribution services is crucial for the stability of power systems.Integrating the large language model(LLM)with 6G edge intelligence provides customized management solutions.H...The intelligent operation management of distribution services is crucial for the stability of power systems.Integrating the large language model(LLM)with 6G edge intelligence provides customized management solutions.However,the adverse effects of false data injection(FDI)attacks on the performance of LLMs cannot be overlooked.Therefore,we propose an FDI attack detection and LLM-assisted resource allocation algorithm for 6G edge intelligenceempowered distribution power grids.First,we formulate a resource allocation optimization problem.The objective is to minimize the weighted sum of the global loss function and total LLM fine-tuning delay under constraints of long-term privacy entropy and energy consumption.Then,we decouple it based on virtual queues.We utilize an LLM-assisted deep Q network(DQN)to learn the resource allocation strategy and design an FDI attack detection mechanism to ensure that fine-tuning remains on the correct path.Simulations demonstrate that the proposed algorithm has excellent performance in convergence,delay,and security.展开更多
This paper reports a new project - the poloidal field (PF) grid power supply system to replace the ac flywheel generator power supply system on the basis of the present running parameters of the HT-7 poloidal field ...This paper reports a new project - the poloidal field (PF) grid power supply system to replace the ac flywheel generator power supply system on the basis of the present running parameters of the HT-7 poloidal field and the short-circuit capacity of our transformer substation. The designed parameters of the PF grid power supply system have been verified to meet the requirements of the heating field (HF) and the vertical field (VF). In the meantime, in order to reduce the disturbance to the local power grid, the device of reactive power and harmonic current compensation has been added. Experimental results have confirmed the feasibility of the PF grid power supply system. Compared with the ac flywheel generator, the PF grid power supply system has the advantages of lower noise, precise control, convenient maintenance, simple operation and cost savings.展开更多
The paper introduces some technology for training, simulation, restoration expert system of power grid, the structure of the system including function composition, hardware and software composition are discussed, know...The paper introduces some technology for training, simulation, restoration expert system of power grid, the structure of the system including function composition, hardware and software composition are discussed, knowledge representation and the method to establish device graphical library for expert system are given, the fault setting and diagnosis for training and simulation as well as restoration technology with deep first searching arithmetic and heuristic inference are presented. The research provides a good base for developing the training, simulation, restoration system of power companies.展开更多
With the accelerating urbanization process,the load demand of urban power grids is constantly increasing,giving rise to a batch of ultra-large urban power grids featuring large electricity demand,dense load distributi...With the accelerating urbanization process,the load demand of urban power grids is constantly increasing,giving rise to a batch of ultra-large urban power grids featuring large electricity demand,dense load distribution,and tight construction land constraints.This paper establishes a network planning method for urban power grids based on series reactors and MMC-MTEDC,focusing on four aspects:short-circuit current suppression,accommodation of external power supply,flexible inter-regional power support,and voltage stability enhancement in load centers.It proposes key indicators including node short-circuit current margin,line thermal stability margin,maximum fault-induced regional power loss,and voltage recovery time,thereby constructing an evaluation system for MMT-MTEDC network planning in urban power grids.Based on the Shenzhen power grid planning data,simulations using DSP software reveal that series reactors reduce short-circuit current by up to 5.0%,while the MMC-MTEDC system enhances node short-circuit margins by 4.212.9%and shortens voltage recovery time by 19.8%.Additionally,the MMC-MTEDC system maintains 3.34-6.76 percentage points higher thermal stability margins than conventional AC systems and enables complete avoidance of external power curtailment during N-2 faults via power reallocation between terminals.Compared with traditional AC or point-to-point HVDC schemes,the proposed hybrid planning method better adapts to the spatial and reliability demands of ultra-large receiving-end grids.This methodology provides practical insights into coordinated AC/DC development under high load density and strong external power reliance.Future work will extend the approach to include electromagnetic transient constraints and lightweight MMC station designs for urban applications.展开更多
False Data Injection Attacks(FDIAs)pose a critical security threat to modern power grids,corrupting state estimation and enabling malicious control actions that can lead to severe consequences,including cascading fail...False Data Injection Attacks(FDIAs)pose a critical security threat to modern power grids,corrupting state estimation and enabling malicious control actions that can lead to severe consequences,including cascading failures,large-scale blackouts,and significant economic losses.While detecting attacks is important,accurately localizing compromised nodes or measurements is even more critical,as it enables timely mitigation,targeted response,and enhanced system resilience beyond what detection alone can offer.Existing research typically models topological features using fixed structures,which can introduce irrelevant information and affect the effectiveness of feature extraction.To address this limitation,this paper proposes an FDIA localization model with adaptive neighborhood selection,which dynamically captures spatial dependencies of the power grid by adjusting node relationships based on data-driven similarities.The improved Transformer is employed to pre-fuse global spatial features of the graph,enriching the feature representation.To improve spatio-temporal correlation extraction for FDIA localization,the proposed model employs dilated causal convolution with a gating mechanism combined with graph convolution to capture and fuse long-range temporal features and adaptive topological features.This fully exploits the temporal dynamics and spatial dependencies inherent in the power grid.Finally,multi-source information is integrated to generate highly robust node embeddings,enhancing FDIA detection and localization.Experiments are conducted on IEEE 14,57,and 118-bus systems,and the results demonstrate that the proposed model substantially improves the accuracy of FDIA localization.Additional experiments are conducted to verify the effectiveness and robustness of the proposed model.展开更多
Due to the complex structural hierarchy,with deeply nested associative relations between entities such as equipment,specifications,and business processes,intelligent power grid engineering is challenging.Meanwhile,lim...Due to the complex structural hierarchy,with deeply nested associative relations between entities such as equipment,specifications,and business processes,intelligent power grid engineering is challenging.Meanwhile,limited by the fragmented data and loss of contextual information,the generated reports are prone to the problems such as content redundancy and omission of critical information,failing to meet the demands of efficient decision-making and accurate management in modern power systems.To address these issues,this paper proposes a knowledge graph(KG)-enhanced framework to automatically generate electric power engineering reports.In the KG construction phase,a feature-fused entity recognition model named BERT-BiLSTM-CRF is adopted to improve the accuracy of entity recognition in scenarios involving power engineering professional terminology,thereby solving the problem of ambiguous entity boundaries in traditional models;then a BERT-attention relation extraction model is proposed to enhance the completeness of extracting complex hierarchical and implicit relations in power grid data.In the report generation phase,an improved Transformer architecture is adopted to accurately transform structured knowledge into natural language reports that comply with engineering specifications,addressing the issue of semantic inconsistency caused by the loss of structural information in existing models.By validating with real-world projects,the results show that the proposed framework significantly outperforms existing baseline models in entity recognition,confirming its superiority and applicability in practical engineering.展开更多
To address the issues of high costs and low component utilization caused by the independent configuration of hybrid DC circuit breakers(HCBs)and DC power flow controllers(DCPFCs)at each port in existing DC distributio...To address the issues of high costs and low component utilization caused by the independent configuration of hybrid DC circuit breakers(HCBs)and DC power flow controllers(DCPFCs)at each port in existing DC distribution networks,this paper adopts a component sharing mechanism to propose a composite multi-port hybrid DC circuit breaker(CM-HCB)with DC power flow and fault current limitation abilities,as well as reduced component costs.The proposed CM-HCB topology enables the sharing of the main breaker branch(MB)and the energy dissipation branch,while the load commutation switches(LCSs)in the main branch are reused as power flow control components,enabling flexible regulation of power flow in multiple lines.Meanwhile,by reconstructing the current path during the fault process,the proposed CM-HCB can utilize the internal coupled inductor to limit the current rise rate at the initial stage of the fault,significantly reducing the requirement for breaking current.A detailed study on the topological structure,steady-state power flow regulation mechanism,transient fault isolation mechanism,control strategy and characteristic analysis of the proposed CM-HCB is presented.Then,a Matlab/Simulink-based meshed three-terminal DC grid simulation platform with the proposed CM-HCB is built.The results indicate that the proposed CM-HCB can not only achieve flexible power flow control during steady-state operation,but also obtain current rise limitation and fault isolation abilities under short-circuit fault conditions,verifying its correctness and effectiveness.Finally,a comparative economic analysis is conducted between the proposed CM-HCB and the other two existing solutions,confirming that its component sharing mechanism can significantly reduce the number of components,lower system costs,and improve component utilization.展开更多
The acceleration grid power supply(AGPS) is a crucial part of the Negative-ion Neutral Beam Injection system in the China Fusion Engineering Test Reactor,which includes a 3-phase passive(diode) rectifier.To diagnose a...The acceleration grid power supply(AGPS) is a crucial part of the Negative-ion Neutral Beam Injection system in the China Fusion Engineering Test Reactor,which includes a 3-phase passive(diode) rectifier.To diagnose and localize faults in the rectifier,this paper proposes a frequencydomain analysis-based fault diagnosis algorithm for the rectifier in AGPS.First,time-domain expressions and spectral characteristics of the output voltage of the TPTL-NPC inverter-based power supply are analyzed.Then,frequency-domain analysis-based fault diagnosis and frequency-domain analysis-based sub-fault diagnosis algorithms are proposed to diagnose open circuit(OC) faults of diode(s),which benefit from the analysis of harmonics magnitude and phase-angle of the output voltage.Only a fundamental period is needed to diagnose and localize exact faults,and a strong Variable-duration Fault Detection Method is proposed to identify acceptable ripple from OC faults.Detailed simulations and experimental results demonstrate the effectiveness,quickness,and robustness of the proposed algorithms,and the diagnosis algorithms proposed in this article provide a significant method for the fault diagnosis of other rectifiers and converters.展开更多
The construction of island power grids is a systematic engineering task.To ensure the safe operation of power grid systems,optimizing the line layout of island power grids is crucial.Especially in the current context ...The construction of island power grids is a systematic engineering task.To ensure the safe operation of power grid systems,optimizing the line layout of island power grids is crucial.Especially in the current context of large-scale distributed renewable energy integration into the power grid,conventional island power grid line layouts can no longer meet actual demands.It is necessary to combine the operational characteristics of island power systems and historical load data to perform load forecasting,thereby generating power grid line layout paths.This article focuses on large-scale distributed renewable energy integration,summarizing optimization strategies for island power grid line layouts,and providing a solid guarantee for the safe and stable operation of island power systems.展开更多
The paper designs the urban-rural power grid dispatching fault diagnosis expert system which acquires fault information by SCADA system of automatic system of urban-rural power grid, and uses artificial intellegence m...The paper designs the urban-rural power grid dispatching fault diagnosis expert system which acquires fault information by SCADA system of automatic system of urban-rural power grid, and uses artificial intellegence method to analyze fault information and make fault diagnosis. The paper implements the core part of the fault expert system the design of knowledge base and fault inference engine.展开更多
摘要This study presents a comprehensive impact analysis of the rotor angle stability of a proposed international connection between the Philippines and Sabah,Malaysia,as part of the Association of Southeast Asian Nations(ASEAN)Power Grid.This study focuses on modeling and evaluating the dynamic performance of the interconnected system,considering the high penetration of renewable sources.Power flow,small signal stability,and transient stability analyses were conducted to assess the ability of the proposed linked power system models to withstand small and large disturbances,utilizing the Power Systems Analysis Toolbox(PSAT)software in MATLAB.All components used in the model are documented in the PSAT library.Currently,there is a lack of publicly available studies regarding the implementation of this specific system.Additionally,the study investigates the behavior of a system with a high penetration of renewable energy sources.Based on the findings,this study concludes that a system is generally stable when interconnection is realized,given its appropriate location and dynamic component parameters.Furthermore,the critical eigenvalues of the system also exhibited improvement as the renewable energy sources were augmented.
基金the Science and Technology Project of the State Grid Corporation of China“Research on China’s end-use energy consumption demand and grid development scenarios under the dual carbon goals”(1400-202455413A-3-5-YS).
摘要As the critical milestone for China’s Nationally Determined Contributions(NDCs)[1],2030 is a pivotal benchmark year for the transformation of China’s power system.From now to 2030,the rapid growth in installed capacity and power generation of wind and solar power will lead to profound changes in the stability mechanisms and balancing characteristics of power systems[[2],[3],[4],[5]],posing new challenges to system security and reliability.
基金Project Supported by Science and Technology Project of State Grid Jiangsu Electric Power Company:Research on Weak Node Identification and UPFC Response Strategy for AC/DC Hybrid Receiving Urban Power Grid(J2024013).
摘要With the high penetration of renewable energy and the rapid development of AC/DC(Alternating Current/Direct Current)hybrid power grid,the power grid is confronted with challenges such as frequent voltage fluctuations and insufficient dynamic reactive power reserves.Full utilization of unified power flow controller(UPFC)in dynamic voltage regulation is of great significance for mitigating voltage excursions of the power grid.This paper proposes a double-time-scale dynamic reactive power optimization method for the AC/DC hybrid power grid with UPFC.A control framework for reactive power optimization of slow-time-scale and fast-time-scale is constructed incorporating the LCC-HVDC and UPFC.In this method,the slow-time-scale aims to improve the voltage profiles and reduce the system cost by setting the voltage regulation weight coefficients based on trajectory sensitivity to preserve reactive power regulation capability.The fast-time-scale adopts an adaptive feedback control mechanism.When slowtime-scale optimization is insufficient to keep the voltage within a safe range,it adjusts the real-time reactive power output of the UPFC,and damps rapid voltage swings accordingly.By implementing the additional fast-time-scale control method,the frequent variations of both the Photovoltaic(PV)and load are managed for the reactive power compensation.Case studies on a modified IEEE-30 bus system demonstrate that compared with the conventional control method,the proposed method reduces the maximum voltage deviation by 3.17%compared to the baseline,while ensuring the economic efficiency.
摘要With the global drive toward carbon neutrality,the deep integration of variable renewable energy sources(VRES)and energy storage systems(ESS)has rendered traditional static carbon accounting methods insufficient to capture the spatiotemporal dynamics of carbon flows in power grids,highlighting the critical need for accurate tracking and equitable allocation of carbon responsibility.This paper proposes a dynamic carbon emission flow tracking framework tailored to the Jibei power grid in China,integrating a dynamic generator carbon intensity model and power transfer distribution factor(PTDF)enhanced network tracking.The framework also includes an optimal carbon allocation matrix and a predictive ESS scheduling model that links the carbon intensity during charging periods to emissions during discharging.Validated using a modified IEEE 30-bus system representing five cities in the Jibei region,results show that the dynamic model achieves a 15.2%higher accuracy than static methods,optimal ESS scheduling reduces system-wide emissions by 8.7%,and the framework maintains over 93%tracking accuracy under extreme uncertainties.Moreover,the framework quantifies inter-city carbon transfers and allocates responsibilities among grid participants,thus enabling real-time monitoring.It provides a robust foundation for carbon-aware dispatch and nodal carbon pricing,supporting the transition toward carbon-neutral power systems.
基金funded by Science and Technology Project of State Grid Jiangsu Electric Power Co.Ltd.(No.J2024172).
摘要Power system faults can trigger a massive influx of complex alarm signals to the operation and maintenance center,posing significant challenges for dispatchers in accurately identifying the underlying faults.To address the issues of sample imbalance and low accuracy in traditional power grid monitoring alarm event identification methods,a power grid monitoring alarm event identification method based on BERT large language model is proposed.Firstly,information entropy is employed to filter effective monitoring alarm signals,and the k-means clustering algorithm is used to group all alarm signals into different event types,forming the initial power grid monitoring alarm event samples.Then,to mitigate the issue of sample imbalance in power grid monitoring alarm events,a pre-trained SimBERT model is proposed to augment minority class samples,thereby reducing the imbalance ratio.Finally,the augmented samples of power grid monitoring alarm events are used to fine-tune the bidirectional encoder representation from transformer(BERT)model.A mix-training optimization strategy is adopted during fine-tuning to ultimately obtain the power grid monitoring alarm event identification model.Case study results demonstrate that the proposed model in this paper achieves superior identification precision of power grid monitoring alarm events compared to traditional deep learning methods.
摘要Renewable energy is gaining momentum and is set to become the world’s largest source of electricity in 2025,overtaking coal for the first time.This fundamental shift-combined with rapid advances in artificial intelligence(AI)-is accelerating the clean energy transition.However,it is also creating new challenges for the centuries-old electricity grid.AI and big data can help address these challenges,but significant hurdles remain.
摘要In December 2025,the ASEAN Centre for Energy(ACE)convened the third ASEAN Power Grid Partnership Meeting,bringing partners together for consultations on key issues.After more than two decades of planning and exploration,the ASEAN Power Grid is now entering a new phase—shifting from predominantly bilateral,one-way connections toward a multilateral,multidirectional network.
摘要This paper investigates the structural robustness of power grids against cascading failures from a geometric perspective based on the Ollivier-Ricci curvature.A curvature metric based on the grid’s admittance matrix is proposed,based on which structurally fragile sub-networks,transmission lines,or buses can be identified without relying on power flow calculations.Then a method is proposed to strengthen the structural robustness of the grid by adding new transmission lines in order to increase the values of the most negative curvatures.Furthermore,the connection between the proposed admittance-based Ollivier-Ricci curvature and edge betweenness centrality index is shown.Experimental results for benchmark power grids including IEEE 118-and 145-bus systems demon-strate the effective performance of the proposed curvature metric and the grid hardening method in capturing and enhancing the structural robustness of power grids.
摘要To improve the efficiency of power grid emergency response after disasters,this study proposes a multi-modal risk profiling-driven power grid disaster emergency response strategy and dynamic resource synergy optimization model.A risk assessment model is constructed by integrating equipment health status,real-time failure rate,and power grid topology importance to generate equipment risk profiles for identifying key nodes.A two-stage optimization mechanism is then designed,the first stage achieves priority coverage of high-risk equipment and minimization of inspection costs through multi-objective path planning.The second stage adopts a mixed-integer programming model to coordinate personnel scheduling and material allocation under resource constraints.A rolling optimization framework is introduced to dynamically respond to sudden failures and resource changes,ensuring the adaptability of scheduling schemes.To verify the model’s effectiveness,three typical scenarios,”no sudden failures”,“equipment risk escalation”,and“personnel working hour constraints”,are simulated.Compared with traditional strategies,the model significantly improves the rationality and dynamic adaptability of resource scheduling,providing new ideas and engineering practice support for enhancing the resilience of smart grid disaster emergency response.
基金the Science and Technology Project of Global Energy Interconnection Group Co.,Ltd.(No.524500180014).
摘要With the global economy integration and progress in energy transformation,it has become a general trend to surpass national boundaries to achieve wider and optimal energy resource allocations.Consequently,there is a critical n eed to adopt scie ntific approaches in assessi ng cross-border power grid interconnection projects.First,con sidering the promotion of large-scale renewable energy resources and improvements in system adequacy,a comprehensive assessment index system,including costs,socio-economic benefits,environmental benefits,and technical benefits,is established in this study.Second,a synthetic assessment framework is proposed for cross-border power grid interconnection projects based on the index system comprising cost-benefit analysis,with market and network simulations,iterative methods for indicator weight evaluation,and technique for order preferenee by similarity to an ideal solution(TOPSIS)method for the project rankings.Fin ally,by assessi ng and comparing three cross-border projects betwee n Europe and Asia,the proposed index system and assessment framework have been proved to be effective and feasible;the results of this system can thus support investment decision-making related to such projects in the future.
基金supported by the Science and Technology Project of State Grid Corporation of China under Grant Number 52094021N010(5400-202199534A-0-5-ZN).
摘要The intelligent operation management of distribution services is crucial for the stability of power systems.Integrating the large language model(LLM)with 6G edge intelligence provides customized management solutions.However,the adverse effects of false data injection(FDI)attacks on the performance of LLMs cannot be overlooked.Therefore,we propose an FDI attack detection and LLM-assisted resource allocation algorithm for 6G edge intelligenceempowered distribution power grids.First,we formulate a resource allocation optimization problem.The objective is to minimize the weighted sum of the global loss function and total LLM fine-tuning delay under constraints of long-term privacy entropy and energy consumption.Then,we decouple it based on virtual queues.We utilize an LLM-assisted deep Q network(DQN)to learn the resource allocation strategy and design an FDI attack detection mechanism to ensure that fine-tuning remains on the correct path.Simulations demonstrate that the proposed algorithm has excellent performance in convergence,delay,and security.
基金The project supported by the Meg-science Engineering Project of the Chinese Academy of Sciences
摘要This paper reports a new project - the poloidal field (PF) grid power supply system to replace the ac flywheel generator power supply system on the basis of the present running parameters of the HT-7 poloidal field and the short-circuit capacity of our transformer substation. The designed parameters of the PF grid power supply system have been verified to meet the requirements of the heating field (HF) and the vertical field (VF). In the meantime, in order to reduce the disturbance to the local power grid, the device of reactive power and harmonic current compensation has been added. Experimental results have confirmed the feasibility of the PF grid power supply system. Compared with the ac flywheel generator, the PF grid power supply system has the advantages of lower noise, precise control, convenient maintenance, simple operation and cost savings.
基金TheKeyProblemTacklingProjectinHunanProvince! (No .Izf 9831)
摘要The paper introduces some technology for training, simulation, restoration expert system of power grid, the structure of the system including function composition, hardware and software composition are discussed, knowledge representation and the method to establish device graphical library for expert system are given, the fault setting and diagnosis for training and simulation as well as restoration technology with deep first searching arithmetic and heuristic inference are presented. The research provides a good base for developing the training, simulation, restoration system of power companies.
基金Shenzhen Power SupplyCo.,Ltd.Grant number 090000KC24040028.
摘要With the accelerating urbanization process,the load demand of urban power grids is constantly increasing,giving rise to a batch of ultra-large urban power grids featuring large electricity demand,dense load distribution,and tight construction land constraints.This paper establishes a network planning method for urban power grids based on series reactors and MMC-MTEDC,focusing on four aspects:short-circuit current suppression,accommodation of external power supply,flexible inter-regional power support,and voltage stability enhancement in load centers.It proposes key indicators including node short-circuit current margin,line thermal stability margin,maximum fault-induced regional power loss,and voltage recovery time,thereby constructing an evaluation system for MMT-MTEDC network planning in urban power grids.Based on the Shenzhen power grid planning data,simulations using DSP software reveal that series reactors reduce short-circuit current by up to 5.0%,while the MMC-MTEDC system enhances node short-circuit margins by 4.212.9%and shortens voltage recovery time by 19.8%.Additionally,the MMC-MTEDC system maintains 3.34-6.76 percentage points higher thermal stability margins than conventional AC systems and enables complete avoidance of external power curtailment during N-2 faults via power reallocation between terminals.Compared with traditional AC or point-to-point HVDC schemes,the proposed hybrid planning method better adapts to the spatial and reliability demands of ultra-large receiving-end grids.This methodology provides practical insights into coordinated AC/DC development under high load density and strong external power reliance.Future work will extend the approach to include electromagnetic transient constraints and lightweight MMC station designs for urban applications.
基金supported by National Key Research and Development Plan of China(No.2022YFB3103304).
摘要False Data Injection Attacks(FDIAs)pose a critical security threat to modern power grids,corrupting state estimation and enabling malicious control actions that can lead to severe consequences,including cascading failures,large-scale blackouts,and significant economic losses.While detecting attacks is important,accurately localizing compromised nodes or measurements is even more critical,as it enables timely mitigation,targeted response,and enhanced system resilience beyond what detection alone can offer.Existing research typically models topological features using fixed structures,which can introduce irrelevant information and affect the effectiveness of feature extraction.To address this limitation,this paper proposes an FDIA localization model with adaptive neighborhood selection,which dynamically captures spatial dependencies of the power grid by adjusting node relationships based on data-driven similarities.The improved Transformer is employed to pre-fuse global spatial features of the graph,enriching the feature representation.To improve spatio-temporal correlation extraction for FDIA localization,the proposed model employs dilated causal convolution with a gating mechanism combined with graph convolution to capture and fuse long-range temporal features and adaptive topological features.This fully exploits the temporal dynamics and spatial dependencies inherent in the power grid.Finally,multi-source information is integrated to generate highly robust node embeddings,enhancing FDIA detection and localization.Experiments are conducted on IEEE 14,57,and 118-bus systems,and the results demonstrate that the proposed model substantially improves the accuracy of FDIA localization.Additional experiments are conducted to verify the effectiveness and robustness of the proposed model.
基金supported by State Grid Shanghai Economic Research Institute under Grant No.SGTYHT/23-JS-004.
摘要Due to the complex structural hierarchy,with deeply nested associative relations between entities such as equipment,specifications,and business processes,intelligent power grid engineering is challenging.Meanwhile,limited by the fragmented data and loss of contextual information,the generated reports are prone to the problems such as content redundancy and omission of critical information,failing to meet the demands of efficient decision-making and accurate management in modern power systems.To address these issues,this paper proposes a knowledge graph(KG)-enhanced framework to automatically generate electric power engineering reports.In the KG construction phase,a feature-fused entity recognition model named BERT-BiLSTM-CRF is adopted to improve the accuracy of entity recognition in scenarios involving power engineering professional terminology,thereby solving the problem of ambiguous entity boundaries in traditional models;then a BERT-attention relation extraction model is proposed to enhance the completeness of extracting complex hierarchical and implicit relations in power grid data.In the report generation phase,an improved Transformer architecture is adopted to accurately transform structured knowledge into natural language reports that comply with engineering specifications,addressing the issue of semantic inconsistency caused by the loss of structural information in existing models.By validating with real-world projects,the results show that the proposed framework significantly outperforms existing baseline models in entity recognition,confirming its superiority and applicability in practical engineering.
基金funded by Youth Talent Growth Project of Guizhou Provincial Department of Education(No.Qianjiaoji[2024]21)National Natural Science Foundation of China(No.62461008 and No.52507211)Guizhou Provincial Key Technology R&D Program(No.[2024]General 049).
摘要To address the issues of high costs and low component utilization caused by the independent configuration of hybrid DC circuit breakers(HCBs)and DC power flow controllers(DCPFCs)at each port in existing DC distribution networks,this paper adopts a component sharing mechanism to propose a composite multi-port hybrid DC circuit breaker(CM-HCB)with DC power flow and fault current limitation abilities,as well as reduced component costs.The proposed CM-HCB topology enables the sharing of the main breaker branch(MB)and the energy dissipation branch,while the load commutation switches(LCSs)in the main branch are reused as power flow control components,enabling flexible regulation of power flow in multiple lines.Meanwhile,by reconstructing the current path during the fault process,the proposed CM-HCB can utilize the internal coupled inductor to limit the current rise rate at the initial stage of the fault,significantly reducing the requirement for breaking current.A detailed study on the topological structure,steady-state power flow regulation mechanism,transient fault isolation mechanism,control strategy and characteristic analysis of the proposed CM-HCB is presented.Then,a Matlab/Simulink-based meshed three-terminal DC grid simulation platform with the proposed CM-HCB is built.The results indicate that the proposed CM-HCB can not only achieve flexible power flow control during steady-state operation,but also obtain current rise limitation and fault isolation abilities under short-circuit fault conditions,verifying its correctness and effectiveness.Finally,a comparative economic analysis is conducted between the proposed CM-HCB and the other two existing solutions,confirming that its component sharing mechanism can significantly reduce the number of components,lower system costs,and improve component utilization.
基金supported by the National Key R&D Program of China(No.2017YFE0300104)National Natural Science Foundation of China(No.51821005)
摘要The acceleration grid power supply(AGPS) is a crucial part of the Negative-ion Neutral Beam Injection system in the China Fusion Engineering Test Reactor,which includes a 3-phase passive(diode) rectifier.To diagnose and localize faults in the rectifier,this paper proposes a frequencydomain analysis-based fault diagnosis algorithm for the rectifier in AGPS.First,time-domain expressions and spectral characteristics of the output voltage of the TPTL-NPC inverter-based power supply are analyzed.Then,frequency-domain analysis-based fault diagnosis and frequency-domain analysis-based sub-fault diagnosis algorithms are proposed to diagnose open circuit(OC) faults of diode(s),which benefit from the analysis of harmonics magnitude and phase-angle of the output voltage.Only a fundamental period is needed to diagnose and localize exact faults,and a strong Variable-duration Fault Detection Method is proposed to identify acceptable ripple from OC faults.Detailed simulations and experimental results demonstrate the effectiveness,quickness,and robustness of the proposed algorithms,and the diagnosis algorithms proposed in this article provide a significant method for the fault diagnosis of other rectifiers and converters.
摘要The construction of island power grids is a systematic engineering task.To ensure the safe operation of power grid systems,optimizing the line layout of island power grids is crucial.Especially in the current context of large-scale distributed renewable energy integration into the power grid,conventional island power grid line layouts can no longer meet actual demands.It is necessary to combine the operational characteristics of island power systems and historical load data to perform load forecasting,thereby generating power grid line layout paths.This article focuses on large-scale distributed renewable energy integration,summarizing optimization strategies for island power grid line layouts,and providing a solid guarantee for the safe and stable operation of island power systems.
摘要The paper designs the urban-rural power grid dispatching fault diagnosis expert system which acquires fault information by SCADA system of automatic system of urban-rural power grid, and uses artificial intellegence method to analyze fault information and make fault diagnosis. The paper implements the core part of the fault expert system the design of knowledge base and fault inference engine.