Pub Date : 2025-06-06DOI: 10.1109/TSTE.2025.3577568
Xinquan Chen;Siqi Bu;Ilhan Kocar
The penetration of inverter-based resources (IBRs) into the grid is experiencing significant growth. Their control behavior during unbalanced grid conditions can impact system stability and protection. This paper evaluates the performance of prevalent grid-forming control-based IBRs (GFM-IBRs) under unbalanced grid conditions and proposes novel insights in a novel framework. First, we investigate the potential impacts of grid-forming control-based IBRs (GFM-IBRs) on system dynamics, protection, and fault ride-through (FRT) capability under unbalanced grid conditions based on extensive literature review and through EMT simulations in benchmark systems with IBRs. To discover these impacts and accommodate unbalanced grid conditions, we implement a generic control structure for full converter-based GFM-IBRs under FRT mode, then perform a comparative analysis of existing solutions that include sequence decomposition methods, positive sequence current-limiting methods, negative sequence controls, and current coordination methods, to identify their capabilities and limitations through literature review and EMT simulations in a large-scale power system. Finally, key challenges and solutions are discussed, highlighting prospects for future research.
{"title":"Grid-Forming IBRs Under Unbalanced Grid Conditions: Challenges, Solutions, and Prospects","authors":"Xinquan Chen;Siqi Bu;Ilhan Kocar","doi":"10.1109/TSTE.2025.3577568","DOIUrl":"https://doi.org/10.1109/TSTE.2025.3577568","url":null,"abstract":"The penetration of inverter-based resources (IBRs) into the grid is experiencing significant growth. Their control behavior during unbalanced grid conditions can impact system stability and protection. This paper evaluates the performance of prevalent grid-forming control-based IBRs (GFM-IBRs) under unbalanced grid conditions and proposes novel insights in a novel framework. First, we investigate the potential impacts of grid-forming control-based IBRs (GFM-IBRs) on system dynamics, protection, and fault ride-through (FRT) capability under unbalanced grid conditions based on extensive literature review and through EMT simulations in benchmark systems with IBRs. To discover these impacts and accommodate unbalanced grid conditions, we implement a generic control structure for full converter-based GFM-IBRs under FRT mode, then perform a comparative analysis of existing solutions that include sequence decomposition methods, positive sequence current-limiting methods, negative sequence controls, and current coordination methods, to identify their capabilities and limitations through literature review and EMT simulations in a large-scale power system. Finally, key challenges and solutions are discussed, highlighting prospects for future research.","PeriodicalId":452,"journal":{"name":"IEEE Transactions on Sustainable Energy","volume":"16 4","pages":"3031-3047"},"PeriodicalIF":10.0,"publicationDate":"2025-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145183965","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}
Pub Date : 2025-06-05DOI: 10.1109/TSTE.2025.3576928
Xuguang Wang;Wangjie Liu;Junhong Ni;Mi Zhang
Reliable short-term photovoltaic (PV) power forecasting is of crucial significance for the rational dispatching of power sources and the effective control of operating costs for the power grid. However, temporal misalignment and regression accuracy imbalance of PV power data pose significant challenges to the reliability of forecast results. In this study, multivariate PV power forecasting is investigated from the perspective of forecast model samples. Firstly, the extent of misalignment of a sample is parameterized by a time-delay vector. Subsequently, the sample-wise graph is defined to relate the time-delay vector with PV power data. Then, the time-delay vector is estimated by minimizing the smoothness metric of the sample-wise graph. Finally, a sample-wise graph-based sample weighting strategy is introduced to address the issue of regression accuracy imbalance. The efficiency of the proposed PV power forecasting scheme is validated through extensive experiments on real-world datasets. Comparison experiments suggest that the proposed scheme can achieve remarkably improved short-term PV power forecasting.
{"title":"Sample-Wise Graph-Based Multivariate Short-Term PV Power Forecasting","authors":"Xuguang Wang;Wangjie Liu;Junhong Ni;Mi Zhang","doi":"10.1109/TSTE.2025.3576928","DOIUrl":"https://doi.org/10.1109/TSTE.2025.3576928","url":null,"abstract":"Reliable short-term photovoltaic (PV) power forecasting is of crucial significance for the rational dispatching of power sources and the effective control of operating costs for the power grid. However, temporal misalignment and regression accuracy imbalance of PV power data pose significant challenges to the reliability of forecast results. In this study, multivariate PV power forecasting is investigated from the perspective of forecast model samples. Firstly, the extent of misalignment of a sample is parameterized by a time-delay vector. Subsequently, the sample-wise graph is defined to relate the time-delay vector with PV power data. Then, the time-delay vector is estimated by minimizing the smoothness metric of the sample-wise graph. Finally, a sample-wise graph-based sample weighting strategy is introduced to address the issue of regression accuracy imbalance. The efficiency of the proposed PV power forecasting scheme is validated through extensive experiments on real-world datasets. Comparison experiments suggest that the proposed scheme can achieve remarkably improved short-term PV power forecasting.","PeriodicalId":452,"journal":{"name":"IEEE Transactions on Sustainable Energy","volume":"16 4","pages":"3003-3014"},"PeriodicalIF":10.0,"publicationDate":"2025-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145183961","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}
Pub Date : 2025-06-03DOI: 10.1109/TSTE.2025.3575520
Razieh Rastgoo;Nima Amjady;Shunfu Lin;S. M. Muyeen
The unpredictable nature of solar power generation, largely influenced by fluctuating cloud cover, poses a challenge to the stability of renewable energy systems. Considering this, accurate forecasting of solar power can lead to better grid management and operation. With the advent of deep learning models, various models have been suggested to enhance the ultra-short-term solar power forecasting performance. Given that cloud images offer more direct and comprehensive information about cloud patterns compared to the numerical weather prediction data, analyzing cloud images allows for more precise and efficient cloud change predictions, leading to a more accurate ultra-short-term solar power forecasting. In this way, aiming to enhance the forecasting performance, in this paper, we introduce a deep learning-based model, including three main blocks. In the first block, a Multi-Stream Video Vision Transformer (MS-ViViT) model is proposed for extracting different types of spatio-temporal features from the input image sequences. The output features from the first block are input to the second block, Fused Improved Reformer (Fused I-Reformer), including three Improved Reformer (I-Reformer) models equipped with a Fused Encoder as well as a new loss function for sequence learning. Finally, an Attentive Residual Fully Connected (ARFC) model is proposed for solar power value prediction. The comparison results with 36 comparative models on six real-world datasets using seven evaluation metrics confirm the effectiveness of the proposed ultra-short-term solar power forecasting model.
{"title":"Ultra-Short-Term Solar Power Prediction Using Sky Image Sequences by a Residual Vision Reformer","authors":"Razieh Rastgoo;Nima Amjady;Shunfu Lin;S. M. Muyeen","doi":"10.1109/TSTE.2025.3575520","DOIUrl":"https://doi.org/10.1109/TSTE.2025.3575520","url":null,"abstract":"The unpredictable nature of solar power generation, largely influenced by fluctuating cloud cover, poses a challenge to the stability of renewable energy systems. Considering this, accurate forecasting of solar power can lead to better grid management and operation. With the advent of deep learning models, various models have been suggested to enhance the ultra-short-term solar power forecasting performance. Given that cloud images offer more direct and comprehensive information about cloud patterns compared to the numerical weather prediction data, analyzing cloud images allows for more precise and efficient cloud change predictions, leading to a more accurate ultra-short-term solar power forecasting. In this way, aiming to enhance the forecasting performance, in this paper, we introduce a deep learning-based model, including three main blocks. In the first block, a Multi-Stream Video Vision Transformer (MS-ViViT) model is proposed for extracting different types of spatio-temporal features from the input image sequences. The output features from the first block are input to the second block, Fused Improved Reformer (Fused I-Reformer), including three Improved Reformer (I-Reformer) models equipped with a Fused Encoder as well as a new loss function for sequence learning. Finally, an Attentive Residual Fully Connected (ARFC) model is proposed for solar power value prediction. The comparison results with 36 comparative models on six real-world datasets using seven evaluation metrics confirm the effectiveness of the proposed ultra-short-term solar power forecasting model.","PeriodicalId":452,"journal":{"name":"IEEE Transactions on Sustainable Energy","volume":"16 4","pages":"2972-2988"},"PeriodicalIF":10.0,"publicationDate":"2025-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145183407","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}
Pub Date : 2025-06-03DOI: 10.1109/TSTE.2025.3576153
Sujay A. Kaloti;Badrul H. Chowdhury
The widely reported increase in the frequency of high impact, low probability extreme weather events pose significant challenges to the resilient operation of electric power systems. This paper explores strategies to enhance operational resilience that addresses the distribution network’s ability to adapt to changing operating conditions. We introduce a novel Dual Agent-Based framework for optimizing the scheduling of distributed energy resources (DERs) within a networked microgrid (N-MG) using the deep reinforcement learning (DRL) paradigm. This framework focuses on minimizing operational and environmental costs during normal operations while enhancing critical load supply indices (CSI) under emergency conditions. Additionally, we introduce a multi-temporal dynamic reward shaping structure along with the incorporation of an error coefficient to enhance the learning process of the agents. To appropriately manage loads during emergencies, we propose a load flexibility classification system that categorizes loads based on its criticality index. The scalability of the proposed approach is demonstrated through running multiple case-studies on a modified IEEE 123-node benchmark distribution network. Furthermore, validation of the method is provided by means of comparisons with two metaheuristic algorithms namely particle swarm optimization (PSO) and genetic algorithm (GA).
{"title":"Dual Agent Framework for Scheduling Networked Microgrids Using DRL to Improve Resilience","authors":"Sujay A. Kaloti;Badrul H. Chowdhury","doi":"10.1109/TSTE.2025.3576153","DOIUrl":"https://doi.org/10.1109/TSTE.2025.3576153","url":null,"abstract":"The widely reported increase in the frequency of high impact, low probability extreme weather events pose significant challenges to the resilient operation of electric power systems. This paper explores strategies to enhance operational resilience that addresses the distribution network’s ability to adapt to changing operating conditions. We introduce a novel Dual Agent-Based framework for optimizing the scheduling of distributed energy resources (DERs) within a networked microgrid (N-MG) using the deep reinforcement learning (DRL) paradigm. This framework focuses on minimizing operational and environmental costs during normal operations while enhancing critical load supply indices (CSI) under emergency conditions. Additionally, we introduce a multi-temporal dynamic reward shaping structure along with the incorporation of an error coefficient to enhance the learning process of the agents. To appropriately manage loads during emergencies, we propose a load flexibility classification system that categorizes loads based on its criticality index. The scalability of the proposed approach is demonstrated through running multiple case-studies on a modified IEEE 123-node benchmark distribution network. Furthermore, validation of the method is provided by means of comparisons with two metaheuristic algorithms namely particle swarm optimization (PSO) and genetic algorithm (GA).","PeriodicalId":452,"journal":{"name":"IEEE Transactions on Sustainable Energy","volume":"16 4","pages":"2989-3002"},"PeriodicalIF":10.0,"publicationDate":"2025-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145183934","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}
Pub Date : 2025-06-02DOI: 10.1109/TSTE.2025.3575788
Jie Zhu;Yinliang Xu;Nengling Tai;Ye Guo;Hongbin Sun
This paper proposes a statistically feasible joint chance-constrained scheduling framework for integrated power distribution networks (PDN) and district heating systems (DHS). The proposed method constructs data-driven uncertainty sets directly from samples, eliminating the need for prior distribution assumptions. It integrates joint chance-constrained programming (JCCP) with robust optimization (RO) to reformulate the original problem. The resulting model is both tractable and computationally efficient. Additionally, we introduce a novel constraint-specific uncertainty set reconstruction technique. This technique refines the uncertainty set by incorporating optimization-relevant information. It significantly reduces conservatism while ensuring system violation probability requirements. Comparative studies with state-of-the-art uncertainty optimization methods demonstrate the advantages of our approach. The proposed method improves computational efficiency by two orders of magnitude. It also achieves more cost-effective solutions than the best-performing benchmark method.
{"title":"Statistically Feasible Joint Chance-Constrained Scheduling of Integrated Distribution Network and District Heating System","authors":"Jie Zhu;Yinliang Xu;Nengling Tai;Ye Guo;Hongbin Sun","doi":"10.1109/TSTE.2025.3575788","DOIUrl":"https://doi.org/10.1109/TSTE.2025.3575788","url":null,"abstract":"This paper proposes a statistically feasible joint chance-constrained scheduling framework for integrated power distribution networks (PDN) and district heating systems (DHS). The proposed method constructs data-driven uncertainty sets directly from samples, eliminating the need for prior distribution assumptions. It integrates joint chance-constrained programming (JCCP) with robust optimization (RO) to reformulate the original problem. The resulting model is both tractable and computationally efficient. Additionally, we introduce a novel constraint-specific uncertainty set reconstruction technique. This technique refines the uncertainty set by incorporating optimization-relevant information. It significantly reduces conservatism while ensuring system violation probability requirements. Comparative studies with state-of-the-art uncertainty optimization methods demonstrate the advantages of our approach. The proposed method improves computational efficiency by two orders of magnitude. It also achieves more cost-effective solutions than the best-performing benchmark method.","PeriodicalId":452,"journal":{"name":"IEEE Transactions on Sustainable Energy","volume":"16 4","pages":"2959-2971"},"PeriodicalIF":10.0,"publicationDate":"2025-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145183409","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}
Pub Date : 2025-04-24DOI: 10.1109/TSTE.2025.3564106
Haohui Ding;Qinran Hu;Yuze Wang;Cong Wang;Jia Su;Haizhou Liu
Fuel cell systems (FCS) are recognized as promising electric sources of power systems. However, existing FCS models are either nonconvex or inaccurate when the FCS is under heavy load. This letter proposes a mechanism-based FCS feasible operational area (FCSFOA) model, taking into account the decline in fuel cell efficiency and the dynamic power consumption of the auxiliary system. Therefore, the FCSFOA model is accurate both under light load and heavy load, and the average error is only 5.4% compared with the actual data. In contrast, the FCS linear model, the most commonly used in the dispatch of power systems, has an average error of 24.4% . Besides, the FCSFOA model is also convex, which is favorable for the dispatch of power systems.
{"title":"A Mechanism-Based Convex Model of Fuel Cell Systems Considering the Effect of Auxiliary System","authors":"Haohui Ding;Qinran Hu;Yuze Wang;Cong Wang;Jia Su;Haizhou Liu","doi":"10.1109/TSTE.2025.3564106","DOIUrl":"https://doi.org/10.1109/TSTE.2025.3564106","url":null,"abstract":"Fuel cell systems (FCS) are recognized as promising electric sources of power systems. However, existing FCS models are either nonconvex or inaccurate when the FCS is under heavy load. This letter proposes a mechanism-based FCS feasible operational area (FCSFOA) model, taking into account the decline in fuel cell efficiency and the dynamic power consumption of the auxiliary system. Therefore, the FCSFOA model is accurate both under light load and heavy load, and the average error is only 5.4% compared with the actual data. In contrast, the FCS linear model, the most commonly used in the dispatch of power systems, has an average error of 24.4% . Besides, the FCSFOA model is also convex, which is favorable for the dispatch of power systems.","PeriodicalId":452,"journal":{"name":"IEEE Transactions on Sustainable Energy","volume":"16 4","pages":"3124-3127"},"PeriodicalIF":10.0,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145183969","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}
Pub Date : 2025-03-29DOI: 10.1109/TSTE.2025.3574806
Hexiang Peng;Kai Liao;Jianwei Yang;Bo Pang;Zhengyou He
Coordinating Volt/Var control (VVC) across multiple timescales in distribution networks is challenging due to the diverse response characteristics of control devices. This paper proposes a novel bi-level data-driven multi-timescale VVC method to achieve coordinated control. The method integrates short-timescale control of continuous devices, such as photovoltaics, with longer-timescale control of discrete devices, including capacitor banks, and network reconfiguration. The VVC problem is formulated as a bi-level partially observable Markov decision process (POMDP). Inner-level control employs the Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm for continuous devices, while outer-level control uses the Deep Double Q-Network (DDQN) algorithm for discrete devices and network reconfiguration. Collaborative training is achieved by aligning reward signals and providing inner-level agent actions as state information to outer-level agents. To mitigate over-exploration caused by network reconfiguration, graph neural networks (GNNs) are utilized to identify representative topologies, simplifying the reconfiguration space. The proposed method is validated on the IEEE 33-bus and PG&E 69-bus systems, demonstrating superior VVC performance and enhanced robustness to topological variations.
{"title":"Deep Reinforcement Learning Based Multi-Timescale Volt/Var Control in Distribution Networks Considering Network Reconfiguration","authors":"Hexiang Peng;Kai Liao;Jianwei Yang;Bo Pang;Zhengyou He","doi":"10.1109/TSTE.2025.3574806","DOIUrl":"https://doi.org/10.1109/TSTE.2025.3574806","url":null,"abstract":"Coordinating Volt/Var control (VVC) across multiple timescales in distribution networks is challenging due to the diverse response characteristics of control devices. This paper proposes a novel bi-level data-driven multi-timescale VVC method to achieve coordinated control. The method integrates short-timescale control of continuous devices, such as photovoltaics, with longer-timescale control of discrete devices, including capacitor banks, and network reconfiguration. The VVC problem is formulated as a bi-level partially observable Markov decision process (POMDP). Inner-level control employs the Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm for continuous devices, while outer-level control uses the Deep Double Q-Network (DDQN) algorithm for discrete devices and network reconfiguration. Collaborative training is achieved by aligning reward signals and providing inner-level agent actions as state information to outer-level agents. To mitigate over-exploration caused by network reconfiguration, graph neural networks (GNNs) are utilized to identify representative topologies, simplifying the reconfiguration space. The proposed method is validated on the IEEE 33-bus and PG&E 69-bus systems, demonstrating superior VVC performance and enhanced robustness to topological variations.","PeriodicalId":452,"journal":{"name":"IEEE Transactions on Sustainable Energy","volume":"16 4","pages":"2948-2958"},"PeriodicalIF":10.0,"publicationDate":"2025-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145183964","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}
Pub Date : 2025-03-21DOI: 10.1109/TSTE.2025.3547404
{"title":"IEEE Transactions on Sustainable Energy Information for Authors","authors":"","doi":"10.1109/TSTE.2025.3547404","DOIUrl":"https://doi.org/10.1109/TSTE.2025.3547404","url":null,"abstract":"","PeriodicalId":452,"journal":{"name":"IEEE Transactions on Sustainable Energy","volume":"16 2","pages":"C4-C4"},"PeriodicalIF":8.6,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10936639","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143667580","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-21DOI: 10.1109/TSTE.2025.3547402
{"title":"IEEE Industry Applications Society Information","authors":"","doi":"10.1109/TSTE.2025.3547402","DOIUrl":"https://doi.org/10.1109/TSTE.2025.3547402","url":null,"abstract":"","PeriodicalId":452,"journal":{"name":"IEEE Transactions on Sustainable Energy","volume":"16 2","pages":"C3-C3"},"PeriodicalIF":8.6,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10936640","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143667743","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：