IEEE Transactions on Smart Grid最新文献_第8页

Optimization-Based Data Recovery After False Data Injection Attacks on State Estimators Using Measurements Inertia and Calibrated Predictions 基于测量惯性和校准预测的状态估计器虚假数据注入攻击后的优化数据恢复

IF 9.8 1区工程技术

IEEE Transactions on Smart Grid Pub Date : 2026-03-01 Epub Date: 2025-12-30 DOI: 10.1109/TSG.2025.3649519

Elham Ommani;Hamed Delkhosh;Hossein Seifi

{"title":"Optimization-Based Data Recovery After False Data Injection Attacks on State Estimators Using Measurements Inertia and Calibrated Predictions","authors":"Elham Ommani;Hamed Delkhosh;Hossein Seifi","doi":"10.1109/TSG.2025.3649519","DOIUrl":"10.1109/TSG.2025.3649519","url":null,"abstract":"Information and communication technology brings better operation capabilities for the power grids at the cost of vulnerability against cyber-attacks. The false data injection attack (FDIA) on the state estimator (SE) is one of the intelligent cyber threats, for which different detection and mitigation methods are proposed. Nevertheless, data recovery after the FDIAs as one of the mitigative actions has received less attention in the literature. This paper proposes a data recovery scheme based on optimization to maintain the consistency among recovered variables. Also, the attack region is localized in an enhanced way so that the non-attacked variables will be preserved as much as possible. The optimization combines two important sources of information for accurate data recovery, i.e., measurement data inertia (MDI) and prediction data calibration (PDC). MDI and PDC are formed using machine learning methods (respectively regression and XGBoost) based on online training using recent (e.g., two weeks) power grid data. Such training is demonstrated to be fast enough (less than the data acquisition rate) to provide adaptable accurate data recovery considering different conditions. Extensive experiments are implemented on the IEEE 118-bus test system to verify the correctness and effectiveness of the proposed method.","PeriodicalId":13331,"journal":{"name":"IEEE Transactions on Smart Grid","volume":"17 3","pages":"2438-2448"},"PeriodicalIF":9.8,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145893869","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Clean-ET: A Novel Electricity Theft Method Based on Clean Backdoor Attack Clean- et：一种基于Clean后门攻击的新型电盗窃方法

IF 9.8 1区工程技术

IEEE Transactions on Smart Grid Pub Date : 2026-03-01 Epub Date: 2025-12-31 DOI: 10.1109/TSG.2025.3649821

Yingzhi Zhang;Feng Wu;Shouyue Sun;Lei Cui;Longxiang Gao;Shui Yu

{"title":"Clean-ET: A Novel Electricity Theft Method Based on Clean Backdoor Attack","authors":"Yingzhi Zhang;Feng Wu;Shouyue Sun;Lei Cui;Longxiang Gao;Shui Yu","doi":"10.1109/TSG.2025.3649821","DOIUrl":"10.1109/TSG.2025.3649821","url":null,"abstract":"As an efficient energy management system, the smart grid has been widely adopted in areas such as power system dispatch optimization and energy internet development. However, false data injection attacks (FDIA) represent a major security challenge for electricity theft detection (ETD) models by manipulating data to mislead system decisions. Existing FDIA methods lack transferability, so the attack becomes ineffective once the defender changes the ETD model. Moreover, FDIA methods significantly degrade the classification performance of ETD models, increasing the risk of exposure and reducing stealth, complicating the demonstration of the potential threat of electricity theft (ET). In this paper, we propose a Novel Electricity Theft Method Based on Clean Backdoor Attack (Clean-ET) to highlight potential threats further. Clean-ET leverages inherent statistical differences in electricity consumption patterns and temporal periodic characteristics to stealthily embed a backdoor into the ETD model, facilitating covert electricity theft with strong cross-model transferability. Specifically, Clean-ET leverages the statistical differences in electricity usage between normal users and electricity thieves by incorporating Gaussian noise and temporal periodic cycle patterns. Moreover, we design triggers that seamlessly blend into the natural distribution of electricity data. This allows the backdoored ETD model to maintain high classification accuracy under normal conditions while misclassifying electricity theft cases under trigger conditions, enabling a long-term stealthy attack. Consequently, regardless of the specific ETD model used by the defender, our attack remains effective as long as the trigger samples are included in the ETD model training, highlighting the transferability of our attack. Experimental results demonstrate that under various parameter settings, our method attains an attack success rate (ASR) consistently above 80%, reaching up to 94%, while minimally impacting the classification performance of clean samples.","PeriodicalId":13331,"journal":{"name":"IEEE Transactions on Smart Grid","volume":"17 3","pages":"2449-2462"},"PeriodicalIF":9.8,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145893860","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Neural Network-Based Adaptive LFC Approach for Multi-Area Power Systems Vulnerable to Hybrid Attacks 基于神经网络的多区域电力系统混合攻击自适应LFC方法

IF 9.8 1区工程技术

IEEE Transactions on Smart Grid Pub Date : 2026-03-01 Epub Date: 2026-01-12 DOI: 10.1109/TSG.2026.3653032

Xin Wang;Ju H. Park;Jiangfeng Wang;Dan Zhang

{"title":"Neural Network-Based Adaptive LFC Approach for Multi-Area Power Systems Vulnerable to Hybrid Attacks","authors":"Xin Wang;Ju H. Park;Jiangfeng Wang;Dan Zhang","doi":"10.1109/TSG.2026.3653032","DOIUrl":"10.1109/TSG.2026.3653032","url":null,"abstract":"Due to the open communication architecture and the ever-expanding network connections of modern power systems, cybersecurity has become increasingly important. For this reason, this paper tackles the load frequency control (LFC) problem in multi-area power systems (MAPSs) that are vulnerable to both time-constrained denial-of-service (DoS) attacks and unknown false-data-injection (FDI) attacks. First, unlike existing research that relies on randomly generated DoS attacks, this paper proposes a detection algorithm aimed at identifying DoS attacks based on network traffic analysis. Moreover, to address unknown FDI attack, we employ neural networks (NNs) to learn the characteristics of the attack signals and construct an approximation model. Then, an NN-based attack compensation controller is developed to mitigate or eliminate the negative impact of unknown maliciously FDI information on system performance. By carefully constructing Lyapunov functional, the exponential asymptotically stability condition with an <inline-formula> <tex-math>${mathcal {H}}_{infty }$ </tex-math></inline-formula> performance index is derived under hybrid attacks. We also determined the relationship between the performance index of the compromised LFC system and the minimum allowable sleep time and maximum allowable active time under DoS attacks. Finally, a simulation example is illustrated to substantiate the validity of the proposed approach.","PeriodicalId":13331,"journal":{"name":"IEEE Transactions on Smart Grid","volume":"17 3","pages":"2480-2489"},"PeriodicalIF":9.8,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145955407","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Dynamic Self-Triggered Load Frequency Control for Multi-Area Power Systems Under Non-Ideal Communication Environments 非理想通信环境下多区域电力系统的动态自触发负荷频率控制

IF 9.8 1区工程技术

IEEE Transactions on Smart Grid Pub Date : 2026-03-01 Epub Date: 2026-01-12 DOI: 10.1109/TSG.2025.3649018

Qian Wan;Yan-Wu Wang;Xiao-Kang Liu;Andrew D. Syrmakesis;Nikos D. Hatziargyriou

引用次数: 0

Risk-Aware Prediction-Optimization Integrated Method for Day-Ahead Microgrid Operation 微电网日前运行风险感知预测优化集成方法

IF 9.8 1区工程技术

IEEE Transactions on Smart Grid Pub Date : 2026-03-01 Epub Date: 2026-03-05 DOI: 10.1109/TSG.2026.3671086

Hongzhang Sheng;Yan Xu;Dunjian Xie

引用次数: 0

LLM and Bayesian Network Integrated Simulation Framework for Electric Vehicle User Charging Behaviorals 电动汽车用户充电行为的LLM与贝叶斯网络集成仿真框架

IF 9.8 1区工程技术

IEEE Transactions on Smart Grid Pub Date : 2026-03-01 Epub Date: 2026-01-16 DOI: 10.1109/TSG.2026.3654823

Yi Xiong;Jiamin Ge;Liang Che

{"title":"LLM and Bayesian Network Integrated Simulation Framework for Electric Vehicle User Charging Behaviorals","authors":"Yi Xiong;Jiamin Ge;Liang Che","doi":"10.1109/TSG.2026.3654823","DOIUrl":"10.1109/TSG.2026.3654823","url":null,"abstract":"Electric vehicle (EV) users’ behaviors are influenced by users’ willingness, which is not directly observable. Emerging large language models (LLMs) have advantages in handling this problem. However, existing studies usually use LLM to directly output EV users’ behaviors, which is limited by the LLM’s inherent issues: “randomness” and “hallucination”. To address these issues, this study proposes an LLM-Bayesian network (BN) integrated simulation framework. First, LLM is used to extract and label EV users’ willingness. Second, LLM generates an explicit causal structure and prior probability, which constructs a BN. Finally, Bayesian inference updates the BN’s prior probability. The BN outputs EV users’ charging behaviors. Experimental results show that in few-shot scenarios, LLM-BN achieves a 20.3% to 27.5% improvement in predictive accuracy compared to pure LLM methods. Moreover, LLM-BN addresses “randomness” and “hallucination” issues, and effectively suppresses violations of physical constraints and the generation of fake information. In practical applications, peak shaving and valley filling are achieved through electricity price adjustments, reducing peak demand by 25% and increasing off-peak demand by 30%.","PeriodicalId":13331,"journal":{"name":"IEEE Transactions on Smart Grid","volume":"17 3","pages":"2618-2621"},"PeriodicalIF":9.8,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145993243","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Blank Page 空白页

IF 9.8 1区工程技术

IEEE Transactions on Smart Grid Pub Date : 2026-03-01 Epub Date: 2026-04-22 DOI: 10.1109/TSG.2026.3682093

引用次数: 0

Multivariate Power Load Forecasting Model Considering Meteorological Feature-Load Dynamic Forward Lag and Turning Points 考虑气象特征、负荷动态前滞后和拐点的多变量负荷预测模型

IF 9.8 1区工程技术

IEEE Transactions on Smart Grid Pub Date : 2026-03-01 Epub Date: 2025-12-09 DOI: 10.1109/TSG.2025.3642111

Yunbo Niu;Pei Yong;Juan Yu;Zhifang Yang

引用次数: 0

Design of Flexible DC-SOP Toward Four-Quadrant Power Flow Control in Bipolar Distribution Networks 面向双极配电网四象限潮流控制的柔性DC-SOP设计

IF 9.8 1区工程技术

IEEE Transactions on Smart Grid Pub Date : 2026-03-01 Epub Date: 2026-01-12 DOI: 10.1109/TSG.2026.3651935

Chengjia Zhang;Xiaodong Yang;Lijian Ding;Yue Yang;Helong Li;Zhiqing Yang;Qiuwei Wu;Jinyu Wen

引用次数: 0

A Physics-Informed-Neural-Network-Based State Estimator for Low Voltage Distribution Systems 基于物理信息的低压配电系统状态估计器

IF 9.8 1区工程技术

IEEE Transactions on Smart Grid Pub Date : 2026-03-01 Epub Date: 2025-12-26 DOI: 10.1109/TSG.2025.3648864

Elio El Semaan;Alessio Iovine;Trung Dung Le;Philippe Dessante;Mouna Rifi;Dominique Croteau

{"title":"A Physics-Informed-Neural-Network-Based State Estimator for Low Voltage Distribution Systems","authors":"Elio El Semaan;Alessio Iovine;Trung Dung Le;Philippe Dessante;Mouna Rifi;Dominique Croteau","doi":"10.1109/TSG.2025.3648864","DOIUrl":"10.1109/TSG.2025.3648864","url":null,"abstract":"Due to the rising penetration of distributed energy resources and electric vehicles charging stations, Distribution System Operators (DSOs) are facing higher challenges to effectively manage low voltage (LV) grids. To enhance their voltage magnitudes’ real-time monitoring, distribution system state estimators (DSSEs) are the targeted solution. However, the application of conventional techniques for state estimation to LV grids is challenged by their unbalanced nature and the limited access to real-time measurements, while on the other hand state estimators (SEs) based on classical machine learning techniques are limited by a lack of knowledge of the physical aspect of the electrical systems. To address these issues, this paper proposes a physics-informed neural network (PINN) based LV DSSE using Graph Neural Networks (GNN). The proposed SE incorporates information about the grid’s topology and parameters while proposing a three-phase four-wire graph representation suitable for LV grids characteristics. Moreover, an unsupervised training is proposed with the aim of training the model in respect to the physical equations, among which the power flow equations. Tests are conducted on various grids generated from open data and evaluate the performance of the GNN-based SE while comparing it to classical machine learning based techniques as autoencoders (AE). The generalizability of the proposed SE in terms of training on a subset of grids and applying to others is investigated.","PeriodicalId":13331,"journal":{"name":"IEEE Transactions on Smart Grid","volume":"17 3","pages":"2544-2554"},"PeriodicalIF":9.8,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145844682","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0