IEEE Transactions on Smart Grid最新文献_第9页

Global-Decision-Focused Neural ODEs for Proactive Grid Resilience Management 面向全局决策的神经ode主动电网弹性管理

IF 9.8 1区工程技术

IEEE Transactions on Smart Grid Pub Date : 2026-03-01 Epub Date: 2025-12-10 DOI: 10.1109/TSG.2025.3642407

Shuyi Chen;Ferdinando Fioretto;Feng Qiu;Shixiang Zhu

{"title":"Global-Decision-Focused Neural ODEs for Proactive Grid Resilience Management","authors":"Shuyi Chen;Ferdinando Fioretto;Feng Qiu;Shixiang Zhu","doi":"10.1109/TSG.2025.3642407","DOIUrl":"10.1109/TSG.2025.3642407","url":null,"abstract":"Extreme hazard events such as wildfires and hurricanes increasingly threaten power systems, causing widespread outages and disrupting critical services. To mitigate these risks, grid operators must act proactively—pre-positioning crews and resources or scheduling hardening activities—guided by forecasts that directly support operational objectives. Traditionally, utilities and agencies have followed a predict-then-optimize paradigm: first generating impact forecasts, then using them to inform response planning. However, this two-step approach inherently separates forecasting from decision-making, overlooking how forecast errors propagate into downstream actions and often producing misaligned or suboptimal plans. We address this gap with predict-all-then-optimize-globally (PATOG), a framework that unifies outage prediction with globally optimized interventions. At its core, our global-decision-focused (<monospace>GDF</monospace>) Neural ODE model jointly captures outage dynamics and optimizes pre-event resilience strategies in a decision-aware manner. Unlike conventional methods, our approach ensures spatially and temporally coherent decisions, enhancing both predictive accuracy and operational efficiency. Evaluations on synthetic and real-world data show that <monospace>GDF</monospace> reduces decision regret by up to 75% compared to two-stage baselines, enabling more effective proactive planning.","PeriodicalId":13331,"journal":{"name":"IEEE Transactions on Smart Grid","volume":"17 3","pages":"2506-2516"},"PeriodicalIF":9.8,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145717693","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

Reinforcement Learning-Based Multi-UAV Deployment for Power Corridor Monitoring With Satellite Internet 基于强化学习的多无人机卫星互联网电力走廊监控部署

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.2025.3641925

Keren He;Quan Zhou;Zhaoyue Xia;Sen Yuan;Qian Zhou;Chenhao Sun;Xiangjun Li;Zhikang Shuai

{"title":"Reinforcement Learning-Based Multi-UAV Deployment for Power Corridor Monitoring With Satellite Internet","authors":"Keren He;Quan Zhou;Zhaoyue Xia;Sen Yuan;Qian Zhou;Chenhao Sun;Xiangjun Li;Zhikang Shuai","doi":"10.1109/TSG.2025.3641925","DOIUrl":"10.1109/TSG.2025.3641925","url":null,"abstract":"Uncrewed Aerial Vehicle (UAV)-assisted communication offers a solution for monitoring remote power corridors, but existing methods struggle to balance heterogeneous monitoring demands and UAV resource constraints, limiting efficiency in large-scale operations. To address these challenges, this paper proposes a reinforcement learning-based multi-UAV deployment for power corridor monitoring with satellite internet. First, an integrated UAV-satellite monitoring framework is developed to enhance communication stability, ensuring seamless data transmission and continuous monitoring in large-scale scenarios. Second, a risk-aware monitoring demand quantification model is introduced to handle spatially heterogeneous risks by using a data-driven risk-weighted prioritization mechanism to dynamically allocate sensor resources under multi-risk conditions. Third, a contextual Multi-Armed Bandit (MAB)-based UAV deployment algorithm is proposed to balance energy efficiency and data collection performance, ensuring sustainable UAV operations and Advanced Metering Infrastructure (AMI)-compatible monitoring. Simulation results demonstrate that the proposed approach achieves superior energy efficiency, data collection performance, and convergence speed compared to existing methods, validating its feasibility for large-scale UAV-based power corridor monitoring and AMI-enabled grid intelligence.","PeriodicalId":13331,"journal":{"name":"IEEE Transactions on Smart Grid","volume":"17 3","pages":"2570-2581"},"PeriodicalIF":9.8,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145717695","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

Identification of Cyberattacks Targeting Poorly-Damped Modes in Wind-Integrated Grids 针对风力集成电网低阻尼模式的网络攻击识别

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.2026.3652933

Mostafa Ansari;Mohsen Ghafouri;Amir Ameli;Hassan Haes Alhelou

{"title":"Identification of Cyberattacks Targeting Poorly-Damped Modes in Wind-Integrated Grids","authors":"Mostafa Ansari;Mohsen Ghafouri;Amir Ameli;Hassan Haes Alhelou","doi":"10.1109/TSG.2026.3652933","DOIUrl":"10.1109/TSG.2026.3652933","url":null,"abstract":"In a wind power plant (WPP), cyberattacks are possible due to existing vulnerabilities in communication protocols, multi-level control loops, extensive data transfers, and the remote locations of wind turbines (WTs). The physical impacts of such threats against WPP can propagate into the wide-area grid and result in a blackout. This paper introduces a novel attack model in which adversaries exploit cybersecurity vulnerabilities in wind power plants (WPPs) to conduct false data injection (FDI) attacks. By using sinusoidal signals, these attacks can destabilize poorly damped modes (PDMs) within bulk power grids, posing a risk of widespread blackouts even with low WPP integration. We propose a model-based detection method that analyzes spectral data from WPP control centers, in compliance with IEC 61400-25. A detection threshold is established using power spectrum density (PSD) distributions, and a fuzzy logic controller (FLC) is incorporated to manage operational uncertainties. Validation on the New England 39-bus and Simplified 16-Generator Australian Power System confirms the effectiveness of the proposed detection approach in the presence of either Gaussian or non-Gaussian noises and coordinated attacks.","PeriodicalId":13331,"journal":{"name":"IEEE Transactions on Smart Grid","volume":"17 3","pages":"2463-2479"},"PeriodicalIF":9.8,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145955410","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

Region-Driven Two-Layer Refined Scheduling for Multi-stack-integrated Alkaline Electrolyzer in Wind-Hydrogen System 风氢系统多堆集成碱性电解槽区域驱动双层精细化调度

IF 9.6 1区工程技术

IEEE Transactions on Smart Grid Pub Date : 2026-02-27 DOI: 10.1109/tsg.2026.3668984

Aobo Guan, Suyang Zhou, Wei Gu, Haiquan Liu, Mingyang Gao, Bo Zhao, Hongkun Lv, Jiaying Chen

引用次数: 0

Bayesian-Optimized Deep Learning for Adaptive Real-Time FDIA Detection in Smart Grid Demand Response Systems 基于贝叶斯优化深度学习的智能电网需求响应系统自适应实时FDIA检测

IF 9.6 1区工程技术

IEEE Transactions on Smart Grid Pub Date : 2026-02-27 DOI: 10.1109/tsg.2026.3668905

Aschalew Tirulo, Siddhartha Chauhan, Biju Issac, Lukas Gebremariam, Athanasios Vasilakos, Miadreza Shafie-khah

引用次数: 0

Mixed Competitive—Cooperative Pricing for EV Charging Stations: A Multi-Agent Reinforcement Learning Approach with Heterogeneous Hierarchical Attention 电动汽车充电站混合竞争-合作定价：一种具有异构层次关注的多智能体强化学习方法

IF 9.6 1区工程技术

IEEE Transactions on Smart Grid Pub Date : 2026-02-27 DOI: 10.1109/tsg.2026.3669058

Yujing Li, Qiang Xing, Si Lv, Zening Li

引用次数: 0

Modeling and Impact Assessment of Load-Altering Attacks In TSO-DSO Coordinated Power Systems TSO-DSO协调电力系统负荷改变攻击建模与影响评估

IF 9.6 1区工程技术

IEEE Transactions on Smart Grid Pub Date : 2026-02-26 DOI: 10.1109/tsg.2026.3668376

Yang Gao, Subhash Lakshminarayana, Iason-Iraklis Avramidis, Charalambos Konstantinou

引用次数: 0

TD3-Enhanced Adaptive Active Disturbance Rejection Control for Bidirectional DC-DC Converter in Photovoltaic-Battery Hybrid Microgrids 光电-电池混合微电网双向DC-DC变换器的td3增强自适应自抗扰控制

IF 9.6 1区工程技术

IEEE Transactions on Smart Grid Pub Date : 2026-02-26 DOI: 10.1109/tsg.2026.3668083

Yuhong Zhang, Xiuhui Peng

引用次数: 0

Distributed Adaptive Unified Fault-Tolerant Control Scheme for Multiple VSGs in Islanded Microgrids 孤岛微电网多vgs分布式自适应统一容错控制方案

IF 9.6 1区工程技术

IEEE Transactions on Smart Grid Pub Date : 2026-02-26 DOI: 10.1109/tsg.2026.3668491

Shujin Chen, Hua Han, Zhenxi Wu, Hongfei Wang, Yao Sun, Chi K. Tse

引用次数: 0

An End-to-End Learning Model with Quantization Technology for Dynamic Prediction-Decision Joint-Making in Active Distribution Networks 基于量化技术的主动配电网动态预测-决策联合决策端到端学习模型

IF 9.6 1区工程技术

IEEE Transactions on Smart Grid Pub Date : 2026-02-26 DOI: 10.1109/tsg.2026.3668484

Fenglin Cai, Zhiming Dong, Xiaodong Yang, Jie Li, Zhixiang Hao, Yaoyao He, Helong Li

引用次数: 0