Hydrogen has drawn significant attention due to its long-term storage capability and wide industrial applications. How to efficiently utilize renewable energy to maximize hydrogen production of a group of spatially distributed electrolyzers is a fundamental problem urgently needed to be solved. This paper is the first to attempt to address the problem by proposing a hydrogen production dispatch (HPD) model for hydrogen-based microgrids with proton exchange membrane electrolyzers. Considering the limited communication and privacy requirement of distributed energy systems, a distributed hydrogen production dispatch framework is constructed. The original nonconvex optimization problem is transformed into a convex form. Furthermore, it is proven that the marginal hydrogen production benefit of each electrolyzer should be equal for the optimal hydrogen production dispatch via Lagrangian duality. By setting the marginal hydrogen production benefit as a consensus variable, a novel distributed consensus-based dispatch algorithm is developed, in which an event-triggered communication scheme is introduced to alleviate the communication burden. It is demonstrated that the proposed algorithm achieves linear convergence. Results of the case study indicate that the proposed strategy yields the optimal hydrogen production benefit, which is increased by 9.43% compared to on-site hydrogen production and demonstrates excellent solving efficiency especially for large-scale systems.
{"title":"Optimal Hydrogen Production Dispatch of Networked Hydrogen-Based Microgrids via a Distributed Method","authors":"Wangli He;Jiawei Yu;Chenxi Cao;Honggang Wang;Feng Qian","doi":"10.1109/TSTE.2025.3541097","DOIUrl":"https://doi.org/10.1109/TSTE.2025.3541097","url":null,"abstract":"Hydrogen has drawn significant attention due to its long-term storage capability and wide industrial applications. How to efficiently utilize renewable energy to maximize hydrogen production of a group of spatially distributed electrolyzers is a fundamental problem urgently needed to be solved. This paper is the first to attempt to address the problem by proposing a hydrogen production dispatch (HPD) model for hydrogen-based microgrids with proton exchange membrane electrolyzers. Considering the limited communication and privacy requirement of distributed energy systems, a distributed hydrogen production dispatch framework is constructed. The original nonconvex optimization problem is transformed into a convex form. Furthermore, it is proven that the marginal hydrogen production benefit of each electrolyzer should be equal for the optimal hydrogen production dispatch via Lagrangian duality. By setting the marginal hydrogen production benefit as a consensus variable, a novel distributed consensus-based dispatch algorithm is developed, in which an event-triggered communication scheme is introduced to alleviate the communication burden. It is demonstrated that the proposed algorithm achieves linear convergence. Results of the case study indicate that the proposed strategy yields the optimal hydrogen production benefit, which is increased by 9.43% compared to on-site hydrogen production and demonstrates excellent solving efficiency especially for large-scale systems.","PeriodicalId":452,"journal":{"name":"IEEE Transactions on Sustainable Energy","volume":"16 3","pages":"1919-1930"},"PeriodicalIF":8.6,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144331785","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}
Medium-term planning of cascaded hydropower (CHP) determines appropriate carryover storage levels in reservoirs to optimize the usage of available water resources. This optimization seeks to maximize the hydropower generated in the current period (i.e., immediate benefit) plus the potential hydropower generation in the future period (i.e., future value). Thus, in the medium-term planning, properly quantifying the future value deposited in carryover storage is essential to achieve a balanced trade-off between immediate benefit and future value. To this end, this paper presents a framework to quantify the future value of carryover storage, which consists of three major steps: i) constructing a deterministic model to calculate the maximum possible hydropower generation that a given level of carryover storage can deliver in the future period; ii) extracting the implicit locational marginal water value (LMWV) of carryover storage for each reservoir by applying a partition-then-extract algorithm to the constructed model; and iii) developing a set of analytical rules based on the extracted LMWV to effectively calculate the future value. These rules can be seamlessly integrated into medium-term CHP planning models as tractable mixed-integer linear constraints to quantify the future value properly, and can be easily visualized to offer valuable insights for CHP operators. Finally, numerical results on Portland General Electric's CHP demonstrate the effectiveness of the presented framework in aiding medium-term CHP planning to identify suitable carryover storage strategies.
{"title":"A Carryover Storage Valuation Framework for Medium-Term Cascaded Hydropower Planning: A Portland General Electric System Study","authors":"Xianbang Chen;Yikui Liu;Zhiming Zhong;Neng Fan;Zhechong Zhao;Lei Wu","doi":"10.1109/TSTE.2025.3540923","DOIUrl":"https://doi.org/10.1109/TSTE.2025.3540923","url":null,"abstract":"Medium-term planning of cascaded hydropower (CHP) determines appropriate carryover storage levels in reservoirs to optimize the usage of available water resources. This optimization seeks to maximize the hydropower generated in the current period (i.e., immediate benefit) plus the potential hydropower generation in the future period (i.e., future value). Thus, in the medium-term planning, properly quantifying the future value deposited in carryover storage is essential to achieve a balanced trade-off between immediate benefit and future value. To this end, this paper presents a framework to quantify the future value of carryover storage, which consists of three major steps: <italic>i)</i> constructing a deterministic model to calculate the maximum possible hydropower generation that a given level of carryover storage can deliver in the future period; <italic>ii)</i> extracting the implicit locational marginal water value (LMWV) of carryover storage for each reservoir by applying a partition-then-extract algorithm to the constructed model; and <italic>iii)</i> developing a set of analytical rules based on the extracted LMWV to effectively calculate the future value. These rules can be seamlessly integrated into medium-term CHP planning models as tractable mixed-integer linear constraints to quantify the future value properly, and can be easily visualized to offer valuable insights for CHP operators. Finally, numerical results on Portland General Electric's CHP demonstrate the effectiveness of the presented framework in aiding medium-term CHP planning to identify suitable carryover storage strategies.","PeriodicalId":452,"journal":{"name":"IEEE Transactions on Sustainable Energy","volume":"16 3","pages":"1903-1918"},"PeriodicalIF":8.6,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144331673","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 : 2025-02-11DOI: 10.1109/TSTE.2025.3540541
Guiyan Liu;Yajuan Zhang;Ping Zhang;Junhua Gu
Accurate and robust wind power forecasting plays a crucial role in ensuring the safety and stability of the power system. Hybrid spatiotemporal forecasting models based on graph convolutional networks have received widespread attention due to their advantages in spatial feature extraction. However, these methods are susceptible to the quality of the generated graph due to data noise and missing issues, resulting in suboptimal performance. In this paper, we propose a hybrid deep learning model based on spatiotemporal graph contrastive learning to address the above issues. Specifically, the model's encoder combines an adaptive graph convolutional network with LSTM to capture fine-grained spatiotemporal dependencies. To enhance the robustness of the encoder against data noise, we apply feature-level and topology-level data augmentation techniques to the model's input and design two contrastive learning auxiliary tasks from the temporal and spatial dimensions, respectively. Furthermore, to capture more comprehensive spatial correlations, we construct an adaptive graph by fusing the static graph with a learnable parameter matrix. Extensive experimental results on two real-world datasets demonstrate that our proposed model significantly outperforms other state-of-the-art methods.
{"title":"Spatiotemporal Graph Contrastive Learning for Wind Power Forecasting","authors":"Guiyan Liu;Yajuan Zhang;Ping Zhang;Junhua Gu","doi":"10.1109/TSTE.2025.3540541","DOIUrl":"https://doi.org/10.1109/TSTE.2025.3540541","url":null,"abstract":"Accurate and robust wind power forecasting plays a crucial role in ensuring the safety and stability of the power system. Hybrid spatiotemporal forecasting models based on graph convolutional networks have received widespread attention due to their advantages in spatial feature extraction. However, these methods are susceptible to the quality of the generated graph due to data noise and missing issues, resulting in suboptimal performance. In this paper, we propose a hybrid deep learning model based on spatiotemporal graph contrastive learning to address the above issues. Specifically, the model's encoder combines an adaptive graph convolutional network with LSTM to capture fine-grained spatiotemporal dependencies. To enhance the robustness of the encoder against data noise, we apply feature-level and topology-level data augmentation techniques to the model's input and design two contrastive learning auxiliary tasks from the temporal and spatial dimensions, respectively. Furthermore, to capture more comprehensive spatial correlations, we construct an adaptive graph by fusing the static graph with a learnable parameter matrix. Extensive experimental results on two real-world datasets demonstrate that our proposed model significantly outperforms other state-of-the-art methods.","PeriodicalId":452,"journal":{"name":"IEEE Transactions on Sustainable Energy","volume":"16 3","pages":"1889-1902"},"PeriodicalIF":8.6,"publicationDate":"2025-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144329507","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 : 2025-02-10DOI: 10.1109/TSTE.2025.3540599
Jiajie Xiao;Peiqiang Li;Zhiyu Mao;Chunming Tu
This paper presents a hierarchical coordinated con-trol strategy designed to enhance the overall performance of the energy storage system (ESS) in secondary frequency regulation (SFR). The strategy includes three layers: the system layer, the ESS operation layer, and the coordination control layer. In the system layer, a detailed frequency response model of the multi-area interconnected system is developed. The intrinsic mech-anisms of timing, depth, and the effect of ESS and conventional generating unit (CGU) in SFR are revealed through the sen-sitivity analysis of the power allocation factor. Furthermore, a sensitivity-based adaptive power allocation strategy for ESS and CGU is proposed, which improves the SFR effect while reducing the ESS power and maintaining the state of charge (SOC). In the ESS operation layer, the ESS is divided into two components for integration, employing a monotonic charge-discharge strategy to reduce lifetime degradation caused by frequent charging and discharging, thereby enhancing operational efficiency. In the coordination control layer, considering the power prediction and the ESS operating state, a SOC optimization strategy based on the double-input fuzzy control (DIFC) is proposed. It further dynamically corrects the power allocation factor based on fuzzy rules, optimizing the SOC level to ensure the bidirectional SFR capability of ESS under all conditions. The case studies validate the overall SFR performance of the proposed strategy with different scenarios.
{"title":"Hierarchical Coordinated Control Strategy for Enhanced Performance of Energy Storage System in Secondary Frequency Regulation","authors":"Jiajie Xiao;Peiqiang Li;Zhiyu Mao;Chunming Tu","doi":"10.1109/TSTE.2025.3540599","DOIUrl":"https://doi.org/10.1109/TSTE.2025.3540599","url":null,"abstract":"This paper presents a hierarchical coordinated con-trol strategy designed to enhance the overall performance of the energy storage system (ESS) in secondary frequency regulation (SFR). The strategy includes three layers: the system layer, the ESS operation layer, and the coordination control layer. In the system layer, a detailed frequency response model of the multi-area interconnected system is developed. The intrinsic mech-anisms of timing, depth, and the effect of ESS and conventional generating unit (CGU) in SFR are revealed through the sen-sitivity analysis of the power allocation factor. Furthermore, a sensitivity-based adaptive power allocation strategy for ESS and CGU is proposed, which improves the SFR effect while reducing the ESS power and maintaining the state of charge (SOC). In the ESS operation layer, the ESS is divided into two components for integration, employing a monotonic charge-discharge strategy to reduce lifetime degradation caused by frequent charging and discharging, thereby enhancing operational efficiency. In the coordination control layer, considering the power prediction and the ESS operating state, a SOC optimization strategy based on the double-input fuzzy control (DIFC) is proposed. It further dynamically corrects the power allocation factor based on fuzzy rules, optimizing the SOC level to ensure the bidirectional SFR capability of ESS under all conditions. The case studies validate the overall SFR performance of the proposed strategy with different scenarios.","PeriodicalId":452,"journal":{"name":"IEEE Transactions on Sustainable Energy","volume":"16 3","pages":"1874-1888"},"PeriodicalIF":8.6,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144331675","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 : 2025-02-10DOI: 10.1109/TSTE.2025.3540253
Lei Xu;Chunxia Dou;Dong Yue;Yudi Zhang;Bo Zhang;Houjun Li;Xiande Bu
The aggregation and control of massive electric vehicles (EVs) are crucial for grid frequency regulation (FR). However, challenges such as disordered charging, high computational and communication burdens need to be addressed. To this end, a hierarchical hybrid modeling and switching control method for EV aggregation (EVA) is proposed. For modeling, a hybrid state set for EVs comprising three discrete states and one dynamic state is established at the local level. The dynamic state's flexibility allows EVs to charge orderly while considering user demands. At the aggregation level, a Markov-based EVA state space model is designed, integrating the user's willingness-to-pay (WTP) index and hybrid state. It estimates the EVA's FR capacity (FRC) with a lower communication burden and reduces computational burden by simplifying control dimensions. For control, a model predictive control (MPC)-based state switching method is designed at the aggregation level, considering user's FR willingness and power cancellation issue. Furthermore, a predictive compensation mechanism is designed to address model parameter errors resulting from asynchronous control cycles. At the local level, a probabilistic response method is proposed for responding to dispatched control signals, which reduces battery degradation through the state of charge (SOC) based response probability generation. Simulation results validate the method's effectiveness.
{"title":"Hybrid Modeling and Switching Control of Electric Vehicle Aggregation for Frequency Regulation","authors":"Lei Xu;Chunxia Dou;Dong Yue;Yudi Zhang;Bo Zhang;Houjun Li;Xiande Bu","doi":"10.1109/TSTE.2025.3540253","DOIUrl":"https://doi.org/10.1109/TSTE.2025.3540253","url":null,"abstract":"The aggregation and control of massive electric vehicles (EVs) are crucial for grid frequency regulation (FR). However, challenges such as disordered charging, high computational and communication burdens need to be addressed. To this end, a hierarchical hybrid modeling and switching control method for EV aggregation (EVA) is proposed. For modeling, a hybrid state set for EVs comprising three discrete states and one dynamic state is established at the local level. The dynamic state's flexibility allows EVs to charge orderly while considering user demands. At the aggregation level, a Markov-based EVA state space model is designed, integrating the user's willingness-to-pay (WTP) index and hybrid state. It estimates the EVA's FR capacity (FRC) with a lower communication burden and reduces computational burden by simplifying control dimensions. For control, a model predictive control (MPC)-based state switching method is designed at the aggregation level, considering user's FR willingness and power cancellation issue. Furthermore, a predictive compensation mechanism is designed to address model parameter errors resulting from asynchronous control cycles. At the local level, a probabilistic response method is proposed for responding to dispatched control signals, which reduces battery degradation through the state of charge (SOC) based response probability generation. Simulation results validate the method's effectiveness.","PeriodicalId":452,"journal":{"name":"IEEE Transactions on Sustainable Energy","volume":"16 3","pages":"1860-1873"},"PeriodicalIF":8.6,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144331636","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}
In this letter, a novel coordinated control is proposed to achieve integrated power generation of solid oxide fuel cell-gas turbine (SOFC-GT) systems. The integrated system is equipped with both grid following (GFL) and grid forming (GFM) capabilities, which represent an extended controllability compared with the conventional SOFC/GT that operates independently. Further, an adaptive power allocation strategy is developed to regulate the Hydrogen-Electricity conversion that couples the operation of SOFC and GT, which ensures the system's safe and efficient operation under various scenarios. Detailed control algorithms and validations are provided.
{"title":"Coordinated Control of the Integrated SOFC-GT Generation System for Microgrid Applications","authors":"Hanbin Dang;Changyue Li;Yuhua Du;Zhipeng Li;Fei Gao;Yigeng Huangfu","doi":"10.1109/TSTE.2025.3539894","DOIUrl":"https://doi.org/10.1109/TSTE.2025.3539894","url":null,"abstract":"In this letter, a novel coordinated control is proposed to achieve integrated power generation of solid oxide fuel cell-gas turbine (SOFC-GT) systems. The integrated system is equipped with both grid following (GFL) and grid forming (GFM) capabilities, which represent an extended controllability compared with the conventional SOFC/GT that operates independently. Further, an adaptive power allocation strategy is developed to regulate the Hydrogen-Electricity conversion that couples the operation of SOFC and GT, which ensures the system's safe and efficient operation under various scenarios. Detailed control algorithms and validations are provided.","PeriodicalId":452,"journal":{"name":"IEEE Transactions on Sustainable Energy","volume":"16 3","pages":"2259-2262"},"PeriodicalIF":8.6,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144331634","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 : 2025-02-05DOI: 10.1109/TSTE.2025.3538682
Xinyu Liu;Jierui Huang;Di Zheng;Huanhai Xin;Tianshu Bi
Temporary overvoltage (TOV) severely restricts the development and utilization of renewable power resources (RPRs), especially when RPRs are delivered through the line commutated converter-based high voltage direct current (LCC-HVDC) system. To reveal the TOV mechanism for the sending system during commutation failures (CFs), the transient process of the system is partitioned into different stages, where the evolution of the system trajectories is analyzed. On this basis, the variation of AC voltage and DC current considering complex dynamic interactions between LCC-HVDC and renewable energy Plants (REPs) during repetitive CFs (RCFs) is clearly quantified. After revealing the impact of control parameters of both REPs and the LCC-HVDC on the TOV during RCFs, a collaborative optimization method for control parameters is proposed for TOV suppression. Moreover, when the blocking after the RCF tends to be inevitable, the optimal blocking moment is determined to inhibit the TOV caused by HVDC blocking. The accuracy and effectiveness of the proposed methods are verified with EMT simulations of a typical benchmark system.
{"title":"Analysis and Suppression for Temporary Overvoltage Considering Dynamic Interactions Between LCC-HVDC and Renewable Energy Plants","authors":"Xinyu Liu;Jierui Huang;Di Zheng;Huanhai Xin;Tianshu Bi","doi":"10.1109/TSTE.2025.3538682","DOIUrl":"https://doi.org/10.1109/TSTE.2025.3538682","url":null,"abstract":"Temporary overvoltage (TOV) severely restricts the development and utilization of renewable power resources (RPRs), especially when RPRs are delivered through the line commutated converter-based high voltage direct current (LCC-HVDC) system. To reveal the TOV mechanism for the sending system during commutation failures (CFs), the transient process of the system is partitioned into different stages, where the evolution of the system trajectories is analyzed. On this basis, the variation of AC voltage and DC current considering complex dynamic interactions between LCC-HVDC and renewable energy Plants (REPs) during repetitive CFs (RCFs) is clearly quantified. After revealing the impact of control parameters of both REPs and the LCC-HVDC on the TOV during RCFs, a collaborative optimization method for control parameters is proposed for TOV suppression. Moreover, when the blocking after the RCF tends to be inevitable, the optimal blocking moment is determined to inhibit the TOV caused by HVDC blocking. The accuracy and effectiveness of the proposed methods are verified with EMT simulations of a typical benchmark system.","PeriodicalId":452,"journal":{"name":"IEEE Transactions on Sustainable Energy","volume":"16 3","pages":"1849-1859"},"PeriodicalIF":8.6,"publicationDate":"2025-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144331631","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 : 2025-02-03DOI: 10.1109/TSTE.2025.3537622
Shoji Nishikata;Fujio Tatsuta
The output power of a wind farm composed of current-source series-connected wind turbine/generators with thyristor rectifier circuits that does not require offshore substation is studied. The steady-state operating characteristics for a single wind turbine/generator are examined first for the IEA 15MW offshore reference wind turbine. Then, dynamic performances for a single wind turbine/generator as well as for a wind farm (WF) consisting of 36 wind turbines are simulated for an average wind speed of 8.65 m/s considering offshore wind turbulence. The simulation results show that the ratio of the standard deviation of the output fluctuation to the average output of single wind turbine is 39.38%, while that of WF is 6.24%, confirming that output leveling effect is achieved.
{"title":"Study on Output Power of Wind Farm Composed of Current-Source Series-Connected Wind Turbines","authors":"Shoji Nishikata;Fujio Tatsuta","doi":"10.1109/TSTE.2025.3537622","DOIUrl":"https://doi.org/10.1109/TSTE.2025.3537622","url":null,"abstract":"The output power of a wind farm composed of current-source series-connected wind turbine/generators with thyristor rectifier circuits that does not require offshore substation is studied. The steady-state operating characteristics for a single wind turbine/generator are examined first for the IEA 15MW offshore reference wind turbine. Then, dynamic performances for a single wind turbine/generator as well as for a wind farm (WF) consisting of 36 wind turbines are simulated for an average wind speed of 8.65 m/s considering offshore wind turbulence. The simulation results show that the ratio of the standard deviation of the output fluctuation to the average output of single wind turbine is 39.38%, while that of WF is 6.24%, confirming that output leveling effect is achieved.","PeriodicalId":452,"journal":{"name":"IEEE Transactions on Sustainable Energy","volume":"16 3","pages":"1827-1836"},"PeriodicalIF":8.6,"publicationDate":"2025-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144331778","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 : 2025-02-03DOI: 10.1109/TSTE.2025.3534589
Feihu Hu;Xuan Feng;Huaiwen Xu;Xinhao Liang;Xuanyuan Wang
Taking into account the orientation and distance characteristics of wind turbine stations in wind farms can improve the accuracy of wind power prediction. This paper proposed a deep learning spatio-temporal prediction method named orthogonal wind direction transformation spatio-temporal gradient Regression Activation Mapping (OWT-STGrad-RAM) for wind speed prediction. The model encodes the wind farm using an image, and each wind turbine is encoded as a point in the image. The spatio-temporal data related to wind turbines, such as wind speed, temperature, and air pressure, are integrated into fusion features through spatio-temporal fusion convolutional networks model for pre training to obtain a feature dataset. OWT is used to eliminate the effects of different prevailing winds, and STGrad-RAM is used to characterize the orientation and distance between wind turbine nodes and make the spatial features interpretable. The feature dataset is used for wind speed prediction. The experimental results show that the proposed method has achieved a significant improvement in wind speed prediction accuracy compared to the comparative models.
{"title":"Ultra-Short-Term Spatio-Temporal Wind Speed Prediction Based on OWT-STGradRAM","authors":"Feihu Hu;Xuan Feng;Huaiwen Xu;Xinhao Liang;Xuanyuan Wang","doi":"10.1109/TSTE.2025.3534589","DOIUrl":"https://doi.org/10.1109/TSTE.2025.3534589","url":null,"abstract":"Taking into account the orientation and distance characteristics of wind turbine stations in wind farms can improve the accuracy of wind power prediction. This paper proposed a deep learning spatio-temporal prediction method named orthogonal wind direction transformation spatio-temporal gradient Regression Activation Mapping (OWT-STGrad-RAM) for wind speed prediction. The model encodes the wind farm using an image, and each wind turbine is encoded as a point in the image. The spatio-temporal data related to wind turbines, such as wind speed, temperature, and air pressure, are integrated into fusion features through spatio-temporal fusion convolutional networks model for pre training to obtain a feature dataset. OWT is used to eliminate the effects of different prevailing winds, and STGrad-RAM is used to characterize the orientation and distance between wind turbine nodes and make the spatial features interpretable. The feature dataset is used for wind speed prediction. The experimental results show that the proposed method has achieved a significant improvement in wind speed prediction accuracy compared to the comparative models.","PeriodicalId":452,"journal":{"name":"IEEE Transactions on Sustainable Energy","volume":"16 3","pages":"1816-1826"},"PeriodicalIF":8.6,"publicationDate":"2025-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144331735","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 : 2025-02-03DOI: 10.1109/TSTE.2025.3537612
Shoujiang Li;Jianzhou Wang;Hui Zhang;Yong Liang
Accurate and reliable solar photovoltaic (PV) power forecasting are crucial for cost-effective resource planning and stable operation of smart grids. However, current methods are affected by the intermittent, non-stationary and stochastic nature of solar energy and thus cannot satisfy the requirement of high-precision forecasting. To this end, we propose a fuzzy cognitive map (FCM) forecasting method based on bubble entropy and smoothly clipped absolute deviation (SCAD) regularization, called BesFCM. This method first utilizes bubble entropy to fuse two mode decomposition methods to improve the representation of PV data to capture effective features with significant stability and discriminative ability, then employs a FCM with a combination of fuzzy logic, neural networks, and expert systems to model solar PV power generation, and finally develops a high order FCM learning method based on SCAD regularization to alleviate the overfitting problem, enhancing the robustness and generalization ability of forecasting. Experimental results demonstrate that the BesFCM achieves the best overall performance on PV power datasets from multiple sampling intervals in multiple regions of Belgium compared to multiple state-of-the-art baselines, validating the effectiveness for solar power generation forecasting, providing support and reference for improving the quality of smart grid dispatch and reducing spare capacity reserves.
{"title":"Learning a Robust Fuzzy Cognitive Map Based on Bubble Entropy Fusion With SCAD Regularization for Solar Power Generation","authors":"Shoujiang Li;Jianzhou Wang;Hui Zhang;Yong Liang","doi":"10.1109/TSTE.2025.3537612","DOIUrl":"https://doi.org/10.1109/TSTE.2025.3537612","url":null,"abstract":"Accurate and reliable solar photovoltaic (PV) power forecasting are crucial for cost-effective resource planning and stable operation of smart grids. However, current methods are affected by the intermittent, non-stationary and stochastic nature of solar energy and thus cannot satisfy the requirement of high-precision forecasting. To this end, we propose a fuzzy cognitive map (FCM) forecasting method based on bubble entropy and smoothly clipped absolute deviation (SCAD) regularization, called BesFCM. This method first utilizes bubble entropy to fuse two mode decomposition methods to improve the representation of PV data to capture effective features with significant stability and discriminative ability, then employs a FCM with a combination of fuzzy logic, neural networks, and expert systems to model solar PV power generation, and finally develops a high order FCM learning method based on SCAD regularization to alleviate the overfitting problem, enhancing the robustness and generalization ability of forecasting. Experimental results demonstrate that the BesFCM achieves the best overall performance on PV power datasets from multiple sampling intervals in multiple regions of Belgium compared to multiple state-of-the-art baselines, validating the effectiveness for solar power generation forecasting, providing support and reference for improving the quality of smart grid dispatch and reducing spare capacity reserves.","PeriodicalId":452,"journal":{"name":"IEEE Transactions on Sustainable Energy","volume":"16 3","pages":"1837-1848"},"PeriodicalIF":8.6,"publicationDate":"2025-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144329500","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}
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：