Global Energy Interconnection最新文献_第2页

Real-time dispatch strategy for microgrid considering source‒load uncertainty: a tailored TD3 reinforcement learning approach 考虑源负荷不确定性的微电网实时调度策略：一种定制TD3强化学习方法

IF 2.6 Q4 ENERGY & FUELS

Global Energy Interconnection

Pub Date : 2025-12-01 DOI: 10.1016/j.gloei.2025.10.003

Shenpeng Xiang , Mohan Lin , Zhe Chen , Pingliang Zeng , Xiangjin Wang , Diyang Gong

The integration of large-scale-distributed new energy resources has led to heightened source‒load uncertainty. As energy prosumers, microgrids urgently require enhanced real-time regulation capabilities over controllable resources amid uncertain environments, rendering real-time and rapid decision-making a critical issue. This paper proposes a tailored twin delayed deep deterministic policy gradient (TD3) reinforcement learning algorithm that explicitly accounts for source‒load uncertainty. First, following an expert experience-based methodology, Gaussian process regression was implemented using the radial basis function covariance with historical source and load data. The parameters were adaptively adjusted by maximum likelihood estimation to generate the expected curves of demand and wind‒solar power generation, along with their 95% confidence regions, which were treated as representative uncertainty scenarios. Second, the traditional scheduling model was transformed into a deep reinforcement learning (DRL) environment through a Markov process. To minimize the total operational cost of the microgrid, the tailored TD3 algorithm was applied to formulate rapid intraday scheduling decisions. Finally, simulations were conducted using real historical data from an actual region in Zhejiang province, China, to verify the efficacy of the proposed method. The results demonstrate the potential of the algorithm for achieving economic scheduling for microgrids.

大规模分布式新能源的整合导致了电力负荷不确定性的增加。微电网作为能源的生产者，迫切需要在不确定环境下增强对可控资源的实时调控能力，实时快速决策成为关键问题。本文提出了一种定制的双延迟深度确定性策略梯度（TD3）强化学习算法，该算法明确地考虑了源负载的不确定性。首先，采用基于专家经验的方法，利用径向基函数协方差与历史源和负荷数据实现高斯过程回归。通过最大似然估计对参数进行自适应调整，生成需求和风能-太阳能发电的期望曲线及其95%置信区间，并将其作为代表性不确定性情景。其次，通过马尔可夫过程将传统调度模型转化为深度强化学习（DRL）环境。为了使微电网的总运行成本最小化，应用定制TD3算法制定快速的日内调度决策。最后，利用中国浙江省某地区的真实历史数据进行了仿真，验证了所提方法的有效性。结果表明，该算法具有实现微电网经济调度的潜力。

{"title":"Real-time dispatch strategy for microgrid considering source‒load uncertainty: a tailored TD3 reinforcement learning approach","authors":"Shenpeng Xiang , Mohan Lin , Zhe Chen , Pingliang Zeng , Xiangjin Wang , Diyang Gong","doi":"10.1016/j.gloei.2025.10.003","DOIUrl":"10.1016/j.gloei.2025.10.003","url":null,"abstract":"<div><div>The integration of large-scale-distributed new energy resources has led to heightened source‒load uncertainty. As energy prosumers, microgrids urgently require enhanced real-time regulation capabilities over controllable resources amid uncertain environments, rendering real-time and rapid decision-making a critical issue. This paper proposes a tailored twin delayed deep deterministic policy gradient (TD3) reinforcement learning algorithm that explicitly accounts for source‒load uncertainty. First, following an expert experience-based methodology, Gaussian process regression was implemented using the radial basis function covariance with historical source and load data. The parameters were adaptively adjusted by maximum likelihood estimation to generate the expected curves of demand and wind‒solar power generation, along with their 95% confidence regions, which were treated as representative uncertainty scenarios. Second, the traditional scheduling model was transformed into a deep reinforcement learning (DRL) environment through a Markov process. To minimize the total operational cost of the microgrid, the tailored TD3 algorithm was applied to formulate rapid intraday scheduling decisions. Finally, simulations were conducted using real historical data from an actual region in Zhejiang province, China, to verify the efficacy of the proposed method. The results demonstrate the potential of the algorithm for achieving economic scheduling for microgrids.</div></div>","PeriodicalId":36174,"journal":{"name":"Global Energy Interconnection","volume":"8 6","pages":"Pages 905-917"},"PeriodicalIF":2.6,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145792276","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Digital twin topology modelling method of new-type distribution network based on CIM specifications and spectral clustering 基于CIM规范和谱聚类的新型配电网数字孪生拓扑建模方法

IF 2.6 Q4 ENERGY & FUELS

Global Energy Interconnection

Pub Date : 2025-12-01 DOI: 10.1016/j.gloei.2025.05.012

Zhimin He , Hai Yu , Lin Peng , Aihua Zhou , He Wang , Jin Xu

Regard to the real-time dynamic digital twin modelling problem of a new-type distribution network that includes distributed resources such as distributed photovoltaic, energy storage, charging pile, and electric vehicle, a new-type distribution network digital twin topology modeling method based on Common Information Model (CIM) specifications and spectral clustering is proposed. Firstly, according to the specifications of the CIM standard, the digital twin topology models of distributed resources are extended and established. Secondly, based on the digital twin topology models of distributed resources, a digital twin aggregation modelling method for new-type distribution network is proposed based on spectral clustering. Furthermore, an online linked update strategy for the digital twin model of new-type distribution network that integrates real-time topology states is proposed. Finally, a case study is conducted on a distribution network in a certain demonstration area in China, and the results verify the practicability and effectiveness of the method proposed in this paper. This lays the foundation for the application of electrical network twin analysis, such as power flow calculation, optimal power flow, economic dispatch, and safety check, in a new-type distribution network that includes diversified distributed resources.

针对包含分布式光伏、储能、充电桩、电动汽车等分布式资源的新型配电网的实时动态数字孪生建模问题，提出了一种基于通用信息模型（CIM）规范和频谱聚类的新型配电网数字孪生拓扑建模方法。首先，根据CIM标准的规范，扩展并建立了分布式资源的数字孪生拓扑模型。其次，在分布式资源数字孪生拓扑模型的基础上，提出了一种基于谱聚类的新型配电网数字孪生聚合建模方法。在此基础上，提出了一种集成实时拓扑状态的新型配电网数字孪生模型在线链接更新策略。最后，以国内某示范区配电网为例进行了分析，结果验证了本文方法的实用性和有效性。这为潮流计算、最优潮流、经济调度、安全校核等网络孪生分析在分布式资源多样化的新型配电网中的应用奠定了基础。

{"title":"Digital twin topology modelling method of new-type distribution network based on CIM specifications and spectral clustering","authors":"Zhimin He , Hai Yu , Lin Peng , Aihua Zhou , He Wang , Jin Xu","doi":"10.1016/j.gloei.2025.05.012","DOIUrl":"10.1016/j.gloei.2025.05.012","url":null,"abstract":"<div><div>Regard to the real-time dynamic digital twin modelling problem of a new-type distribution network that includes distributed resources such as distributed photovoltaic, energy storage, charging pile, and electric vehicle, a new-type distribution network digital twin topology modeling method based on Common Information Model (CIM) specifications and spectral clustering is proposed. Firstly, according to the specifications of the CIM standard, the digital twin topology models of distributed resources are extended and established. Secondly, based on the digital twin topology models of distributed resources, a digital twin aggregation modelling method for new-type distribution network is proposed based on spectral clustering. Furthermore, an online linked update strategy for the digital twin model of new-type distribution network that integrates real-time topology states is proposed. Finally, a case study is conducted on a distribution network in a certain demonstration area in China, and the results verify the practicability and effectiveness of the method proposed in this paper. This lays the foundation for the application of electrical network twin analysis, such as power flow calculation, optimal power flow, economic dispatch, and safety check, in a new-type distribution network that includes diversified distributed resources.</div></div>","PeriodicalId":36174,"journal":{"name":"Global Energy Interconnection","volume":"8 6","pages":"Pages 947-958"},"PeriodicalIF":2.6,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145792231","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A multi-model management approach for power system transient stability assessment based on multi-moment feature clustering 基于多矩特征聚类的电力系统暂态稳定评估多模型管理方法

IF 2.6 Q4 ENERGY & FUELS

Global Energy Interconnection

Pub Date : 2025-10-01 DOI: 10.1016/j.gloei.2025.01.009

Xiaoyu Han , Tao Liu , Defu Cai , Rusi Chen , Erxi Wang , Jinfu Chen

Transient stability assessment (TSA) based on artificial intelligence typically has two distinct model management approaches: a unified management approach for all faulted lines and a separate management approach for each faulted line. To address the shortcomings of the aforementioned approaches, namely accuracy, training time, and model management complexity, a multi-model management approach for power system TSA based on multi-moment feature clustering has been proposed. First, the steady-state and transient features present under fault conditions were obtained through a transient simulation of line faults. The input sample set was then constructed using the aforementioned multi-moment electrical features and the embedded faulty line numbers. Subsequently, K-means clustering was conducted on each line based on the similarity of their electrical features, employing t-SNE dimensionality reduction. The PSO-CNN model was trained separately for each cluster to generate several independent TSA models. Finally, a model effectiveness evaluation system consisting of five metrics was established, and the effect of the sample imbalance ratio on the model effectiveness was investigated. The model effectiveness was evaluated using the IEEE 39-bus system algorithm. The results showed that the multi-model management strategy based on multi-moment feature clustering can effectively combine the two advantages of superior evaluation performance and streamlined model management by fully extracting system features. Moreover, this approach allows for more flexible adjustments to line topology changes.

基于人工智能的暂态稳定评估（TSA）通常有两种不同的模型管理方法：对所有故障线的统一管理方法和对每条故障线的单独管理方法。针对上述方法在准确率、训练时间和模型管理复杂性等方面的不足，提出了一种基于多矩特征聚类的电力系统TSA多模型管理方法。首先，通过对线路故障的暂态仿真，得到了故障条件下的稳态和暂态特征。然后使用上述多矩电特征和嵌入的故障行号构建输入样本集。随后，利用t-SNE降维方法，基于电特征的相似性对每条线进行K-means聚类。对每个聚类分别训练PSO-CNN模型，生成多个独立的TSA模型。最后，建立了由5个指标组成的模型有效性评价体系，并考察了样本失衡率对模型有效性的影响。采用IEEE 39总线系统算法对模型的有效性进行了评价。结果表明，基于多矩特征聚类的多模型管理策略可以通过充分提取系统特征，有效地将评估性能优越和模型管理精简两大优势结合起来。此外，这种方法允许对线路拓扑变化进行更灵活的调整。

{"title":"A multi-model management approach for power system transient stability assessment based on multi-moment feature clustering","authors":"Xiaoyu Han , Tao Liu , Defu Cai , Rusi Chen , Erxi Wang , Jinfu Chen","doi":"10.1016/j.gloei.2025.01.009","DOIUrl":"10.1016/j.gloei.2025.01.009","url":null,"abstract":"<div><div>Transient stability assessment (TSA) based on artificial intelligence typically has two distinct model management approaches: a unified management approach for all faulted lines and a separate management approach for each faulted line. To address the shortcomings of the aforementioned approaches, namely accuracy, training time, and model management complexity, a multi-model management approach for power system TSA based on multi-moment feature clustering has been proposed. First, the steady-state and transient features present under fault conditions were obtained through a transient simulation of line faults. The input sample set was then constructed using the aforementioned multi-moment electrical features and the embedded faulty line numbers. Subsequently, K-means clustering was conducted on each line based on the similarity of their electrical features, employing t-SNE dimensionality reduction. The PSO-CNN model was trained separately for each cluster to generate several independent TSA models. Finally, a model effectiveness evaluation system consisting of five metrics was established, and the effect of the sample imbalance ratio on the model effectiveness was investigated. The model effectiveness was evaluated using the IEEE 39-bus system algorithm. The results showed that the multi-model management strategy based on multi-moment feature clustering can effectively combine the two advantages of superior evaluation performance and streamlined model management by fully extracting system features. Moreover, this approach allows for more flexible adjustments to line topology changes.</div></div>","PeriodicalId":36174,"journal":{"name":"Global Energy Interconnection","volume":"8 5","pages":"Pages 847-857"},"PeriodicalIF":2.6,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145365806","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Optimizing off-grid energy solutions: a hybrid approach leveraging solar, wind, and biomass for sustainable development 优化离网能源解决方案：利用太阳能、风能和生物质能促进可持续发展的混合方法

IF 2.6 Q4 ENERGY & FUELS

Global Energy Interconnection

Pub Date : 2025-10-01 DOI: 10.1016/j.gloei.2025.05.008

Anouar Makhoukh, Abdelbari Redouane, Norddine Oubouch, Abdennebi El Hasnaoui

In this study, we analyzed the untapped energy potential of remote mountainous regions in eastern Morocco, thereby addressing the research gap on sustainable electrification in such areas. We proposed a hybrid energy system corresponding to the local conditions and integrated the solar, wind, and biomass energy using batteries and green hydrogen as storage systems, considering the grid as a backup. Simulations conducted using HOMER Pro indicate an annual energy output of 5.6 GWh from solar, 6.9 GWh from wind, and 1 GWh from biomass, thereby ensuring 100% renewable self-sufficiency. The system is highly cost-effective and achieves a levelized cost of energy of 0.024 $/kWh while significantly reducing the greenhouse gas emissions by over 99% for CO₂ and 100% for SO₂. This study presents a sustainable, reliable, and economically viable solution for rural electrification, which concurs with SDG 7.

在这项研究中，我们分析了摩洛哥东部偏远山区未开发的能源潜力，从而解决了这些地区可持续电气化的研究差距。我们提出了一个符合当地条件的混合能源系统，将太阳能、风能和生物质能结合起来，使用电池和绿色氢作为存储系统，考虑电网作为备用。使用HOMER Pro进行的模拟表明，太阳能的年发电量为5.6 GWh，风能为6.9 GWh，生物质能为1 GWh，从而确保100%的可再生能源自给自足。该系统具有很高的成本效益，实现了0.024美元/千瓦时的能源成本，同时显著减少了99%以上的二氧化碳和100%的二氧化硫的温室气体排放。本研究提出了一种可持续、可靠、经济可行的农村电气化解决方案，符合可持续发展目标7。

引用次数: 0

Forecasting electricity prices in the spot market utilizing wavelet packet decomposition integrated with a hybrid deep neural network 基于小波包分解和混合深度神经网络的现货市场电价预测

IF 2.6 Q4 ENERGY & FUELS

Global Energy Interconnection

Pub Date : 2025-10-01 DOI: 10.1016/j.gloei.2025.03.003

Heping Jia , Yuchen Guo , Xiaobin Zhang , Qianxin Ma , Zhenglin Yang , Yaxian Zheng , Dan Zeng , Dunnan Liu

Accurate forecasting of electricity spot prices is crucial for market participants in formulating bidding strategies. However, the extreme volatility of electricity spot prices, influenced by various factors, poses significant challenges for forecasting. To address the data uncertainty of electricity prices and effectively mitigate gradient issues, overfitting, and computational challenges associated with using a single model during forecasting, this paper proposes a framework for forecasting spot market electricity prices by integrating wavelet packet decomposition (WPD) with a hybrid deep neural network. By ensuring accurate data decomposition, the WPD algorithm aids in detecting fluctuating patterns and isolating random noise. The hybrid model integrates temporal convolutional networks (TCN) and long short-term memory (LSTM) networks to enhance feature extraction and improve forecasting performance. Compared to other techniques, it significantly reduces average errors, decreasing mean absolute error (MAE) by 27.3%, root mean square error (RMSE) by 66.9%, and mean absolute percentage error (MAPE) by 22.8%. This framework effectively captures the intricate fluctuations present in the time series, resulting in more accurate and reliable predictions.

准确预测电力现货价格对市场参与者制定竞价策略至关重要。然而，受各种因素的影响，电力现货价格的剧烈波动给预测带来了重大挑战。为了解决电价数据的不确定性，并有效缓解在预测过程中使用单一模型所带来的梯度问题、过拟合和计算挑战，本文提出了一个将小波包分解（WPD）与混合深度神经网络相结合的现货市场电价预测框架。通过确保准确的数据分解，WPD算法有助于检测波动模式和隔离随机噪声。该混合模型将时间卷积网络（TCN）和长短期记忆网络（LSTM）相结合，增强了特征提取，提高了预测性能。与其他技术相比，它显著降低了平均误差，平均绝对误差（MAE）降低了27.3%，均方根误差（RMSE）降低了66.9%，平均绝对百分比误差（MAPE）降低了22.8%。该框架有效地捕捉时间序列中存在的复杂波动，从而产生更准确和可靠的预测。

{"title":"Forecasting electricity prices in the spot market utilizing wavelet packet decomposition integrated with a hybrid deep neural network","authors":"Heping Jia , Yuchen Guo , Xiaobin Zhang , Qianxin Ma , Zhenglin Yang , Yaxian Zheng , Dan Zeng , Dunnan Liu","doi":"10.1016/j.gloei.2025.03.003","DOIUrl":"10.1016/j.gloei.2025.03.003","url":null,"abstract":"<div><div>Accurate forecasting of electricity spot prices is crucial for market participants in formulating bidding strategies. However, the extreme volatility of electricity spot prices, influenced by various factors, poses significant challenges for forecasting. To address the data uncertainty of electricity prices and effectively mitigate gradient issues, overfitting, and computational challenges associated with using a single model during forecasting, this paper proposes a framework for forecasting spot market electricity prices by integrating wavelet packet decomposition (WPD) with a hybrid deep neural network. By ensuring accurate data decomposition, the WPD algorithm aids in detecting fluctuating patterns and isolating random noise. The hybrid model integrates temporal convolutional networks (TCN) and long short-term memory (LSTM) networks to enhance feature extraction and improve forecasting performance. Compared to other techniques, it significantly reduces average errors, decreasing mean absolute error (MAE) by 27.3%, root mean square error (RMSE) by 66.9%, and mean absolute percentage error (MAPE) by 22.8%. This framework effectively captures the intricate fluctuations present in the time series, resulting in more accurate and reliable predictions.</div></div>","PeriodicalId":36174,"journal":{"name":"Global Energy Interconnection","volume":"8 5","pages":"Pages 874-890"},"PeriodicalIF":2.6,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145365809","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Mechanical performance of key components in floating photovoltaic systems: technological advances and application prospects 浮式光伏系统关键部件力学性能：技术进展与应用前景

IF 2.6 Q4 ENERGY & FUELS

Global Energy Interconnection

Pub Date : 2025-10-01 DOI: 10.1016/j.gloei.2025.07.001

Kai Feng , Shuaiqi Li , Lin Fu , Yingjiu Zhao , Bin Zhang , Sombel Diaham , Chatchai Putson , Fouad Belhora , Abdelowahed Hajjaji , Yahia Boughaleb , Jiawei Zhang

Floating photovoltaic (FPV) technology is emerging as a highly promising approach to accelerate decarbonization of the global economy, due to its higher power generation efficiency and lower land occupation. With the rapid development of FPV technology, the mechanical performance degradation of key components caused by the harsh marine environment has become a pressing issue, as it significantly contributes to failure behavior observed in FPV systems. A comprehensive compilation of the mechanical performance of key components in FPV systems is also currently unavailable. Here, the mechanical behavior of each structural component in FPV systems under harsh marine environments is systematically reviewed. It further emphasizes the synergistic effects of mechanical performance degradation among different components on the overall system. The drop-off rate (v) of normalized elongation at break (EAB) of polymer under the synergistic effect of various environmental factors increases from 7.5 × 10⁻⁴ h⁻¹ to 21.8 × 10⁻⁴ h⁻¹ compared with the single environmental stress. Moreover, the development of novel materials and innovative mechanical structures applied in FPV systems to enhance mechanical performance is discussed. The novel flexible PV modules applied in FPV systems minimize the loads acting on the mooring lines by 80% and increase power generation by 5%. Notably, this paper provides a theoretical foundation for developing standards of FPV systems, especially the establishment of standards related to the synergistic effects of the mechanical performance degradation of different key components on FPV systems.

浮动光伏（FPV）技术由于其更高的发电效率和更低的土地占用，正在成为一种极有前途的加速全球经济脱碳的方法。随着FPV技术的快速发展，恶劣海洋环境导致的关键部件力学性能下降已成为一个紧迫的问题，因为它对FPV系统的失效行为有重要影响。FPV系统中关键部件的机械性能的综合汇编目前也无法获得。在这里，系统地回顾了FPV系统在恶劣海洋环境下每个结构部件的力学行为。它进一步强调了不同部件之间的机械性能退化对整个系统的协同效应。在不同环境因素的协同作用下，聚合物的归一化断裂伸长率（EAB）下降率(v)由7.5 × 10−4 h−1增加到21.8 × 10−4 h−1。此外，还讨论了新型材料和创新机械结构在FPV系统中的应用，以提高机械性能。应用于FPV系统的新型柔性光伏组件将作用在系泊线上的负载减少了80%，并将发电量增加了5%。值得注意的是，本文为FPV系统标准的制定，特别是不同关键部件力学性能退化对FPV系统的协同效应相关标准的建立提供了理论基础。

{"title":"Mechanical performance of key components in floating photovoltaic systems: technological advances and application prospects","authors":"Kai Feng , Shuaiqi Li , Lin Fu , Yingjiu Zhao , Bin Zhang , Sombel Diaham , Chatchai Putson , Fouad Belhora , Abdelowahed Hajjaji , Yahia Boughaleb , Jiawei Zhang","doi":"10.1016/j.gloei.2025.07.001","DOIUrl":"10.1016/j.gloei.2025.07.001","url":null,"abstract":"<div><div>Floating photovoltaic (FPV) technology is emerging as a highly promising approach to accelerate decarbonization of the global economy, due to its higher power generation efficiency and lower land occupation. With the rapid development of FPV technology, the mechanical performance degradation of key components caused by the harsh marine environment has become a pressing issue, as it significantly contributes to failure behavior observed in FPV systems. A comprehensive compilation of the mechanical performance of key components in FPV systems is also currently unavailable. Here, the mechanical behavior of each structural component in FPV systems under harsh marine environments is systematically reviewed. It further emphasizes the synergistic effects of mechanical performance degradation among different components on the overall system. The drop-off rate (<em>v</em>) of normalized elongation at break (EAB) of polymer under the synergistic effect of various environmental factors increases from 7.5 × 10<sup>−4</sup> h<sup>−1</sup> to 21.8 × 10<sup>−4</sup> h<sup>−1</sup> compared with the single environmental stress. Moreover, the development of novel materials and innovative mechanical structures applied in FPV systems to enhance mechanical performance is discussed. The novel flexible PV modules applied in FPV systems minimize the loads acting on the mooring lines by 80% and increase power generation by 5%. Notably, this paper provides a theoretical foundation for developing standards of FPV systems, especially the establishment of standards related to the synergistic effects of the mechanical performance degradation of different key components on FPV systems.</div></div>","PeriodicalId":36174,"journal":{"name":"Global Energy Interconnection","volume":"8 5","pages":"Pages 719-731"},"PeriodicalIF":2.6,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145365815","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A review on high-frequency electromagnetic interference induced by power electronics in new electric power systems 新型电力系统中电力电子设备引起的高频电磁干扰研究进展

IF 2.6 Q4 ENERGY & FUELS

Global Energy Interconnection

Pub Date : 2025-10-01 DOI: 10.1016/j.gloei.2025.05.011

Yundong Hu , Xing Lei , Xizhou Du , Ting Ye , Hongning Song , Hao Li

New electric power systems characterized by a high proportion of renewable energy and power electronics equipment face significant challenges due to high-frequency (HF) electromagnetic interference from the high-speed switching of power converters. To address this situation, this paper offers an in-depth review of HF interference problems and challenges originating from power electronic devices. First, the root cause of HF electromagnetic interference, i.e., the resonant response of the parasitic parameters of the system to high-speed switching transients, is analyzed, and various scenarios of HF interference in power systems are highlighted. Next, the types of HF interference are summarized, with a focus on common-mode interference in grounding systems. This paper thoroughly reviews and compares various suppression methods for conducted HF interference. Finally, the challenges involved and suggestions for addressing emerging HF interference problems from the perspective of both power electronics equipment and power systems are discussed. This review aims to offer a structured understanding of HF interference problems and their suppression techniques for researchers and practitioners.

以可再生能源和电力电子设备占高比例为特征的新型电力系统面临着来自电力变换器高速开关的高频（HF）电磁干扰的重大挑战。为了解决这一问题，本文对电力电子设备产生的高频干扰问题和挑战进行了深入的综述。首先，分析了高频电磁干扰产生的根本原因，即系统寄生参数对高速开关暂态的谐振响应，重点介绍了电力系统中高频干扰的各种场景。其次，总结了高频干扰的类型，重点介绍了接地系统中的共模干扰。本文对传导高频干扰的各种抑制方法进行了全面的综述和比较。最后，从电力电子设备和电力系统的角度讨论了高频干扰所涉及的挑战和解决新出现的高频干扰问题的建议。本文旨在为研究人员和从业人员提供高频干扰问题及其抑制技术的结构化理解。

{"title":"A review on high-frequency electromagnetic interference induced by power electronics in new electric power systems","authors":"Yundong Hu , Xing Lei , Xizhou Du , Ting Ye , Hongning Song , Hao Li","doi":"10.1016/j.gloei.2025.05.011","DOIUrl":"10.1016/j.gloei.2025.05.011","url":null,"abstract":"<div><div>New electric power systems characterized by a high proportion of renewable energy and power electronics equipment face significant challenges due to high-frequency (HF) electromagnetic interference from the high-speed switching of power converters. To address this situation, this paper offers an in-depth review of HF interference problems and challenges originating from power electronic devices. First, the root cause of HF electromagnetic interference, i.e., the resonant response of the parasitic parameters of the system to high-speed switching transients, is analyzed, and various scenarios of HF interference in power systems are highlighted. Next, the types of HF interference are summarized, with a focus on common-mode interference in grounding systems. This paper thoroughly reviews and compares various suppression methods for conducted HF interference. Finally, the challenges involved and suggestions for addressing emerging HF interference problems from the perspective of both power electronics equipment and power systems are discussed. This review aims to offer a structured understanding of HF interference problems and their suppression techniques for researchers and practitioners.</div></div>","PeriodicalId":36174,"journal":{"name":"Global Energy Interconnection","volume":"8 5","pages":"Pages 804-820"},"PeriodicalIF":2.6,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145365765","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Bayesian optimized support vector regression with a Gaussian kernel for accurate prediction of the state of health of lithium-ion batteries used for electric vehicle applications 基于高斯核的贝叶斯优化支持向量回归用于电动汽车锂离子电池健康状态的准确预测

IF 2.6 Q4 ENERGY & FUELS

Global Energy Interconnection

Pub Date : 2025-10-01 DOI: 10.1016/j.gloei.2025.02.003

Selvaraj Vedhanayaki , Vairavasundaram Indragandhi

The state of health SoH of lithium ion batteries plays a predominant role in ensuring the safe and reliable operation of electric vehicles. In this, a novel SoH estimation approach using support vector regression with a Gaussian kernel optimized using the Bayesian optimization technique (BO-SVR with a Gaussian kernel) was proposed. Unlike, traditional approaches that use the internal resistance, and battery capacity as input parameters, this study utilized the equivalent discharging voltage difference interval and equivalent charging voltage difference interval, as they capture the dynamic voltage characteristics associated with the battery degradation. The model was simulated using MATLAB 2023a. The mean absolute error, R², root mean squared error, and mean squared error were considered as performance indicators. The simulation results indicated that the proposed BO-SVR with a Gaussian kernel model had superior performance to other kernel SVR and Gaussian Process Regression models, with a reduced RMSE of 0.0082, thus demonstrating its potential to predict the SoH more accurately.

锂离子电池的健康SoH状态对保证电动汽车的安全可靠运行起着举足轻重的作用。在此基础上，提出了一种利用贝叶斯优化技术优化高斯核支持向量回归的SoH估计方法（BO-SVR with a Gaussian kernel）。与使用内阻和电池容量作为输入参数的传统方法不同，本研究使用了等效放电电压差间隔和等效充电电压差间隔，因为它们捕获了与电池退化相关的动态电压特性。利用MATLAB 2023a对模型进行仿真。以平均绝对误差、R2、均方根误差和均方误差作为性能指标。仿真结果表明，基于高斯核模型的BO-SVR性能优于其他核支持向量回归模型和高斯过程回归模型，RMSE降低至0.0082，显示了其对SoH预测的准确性。

{"title":"Bayesian optimized support vector regression with a Gaussian kernel for accurate prediction of the state of health of lithium-ion batteries used for electric vehicle applications","authors":"Selvaraj Vedhanayaki , Vairavasundaram Indragandhi","doi":"10.1016/j.gloei.2025.02.003","DOIUrl":"10.1016/j.gloei.2025.02.003","url":null,"abstract":"<div><div>The state of health SoH of lithium ion batteries plays a predominant role in ensuring the safe and reliable operation of electric vehicles. In this, a novel SoH estimation approach using support vector regression with a Gaussian kernel optimized using the Bayesian optimization technique (BO-SVR with a Gaussian kernel) was proposed. Unlike, traditional approaches that use the internal resistance, and battery capacity as input parameters, this study utilized the equivalent discharging voltage difference interval and equivalent charging voltage difference interval, as they capture the dynamic voltage characteristics associated with the battery degradation. The model was simulated using MATLAB 2023a. The mean absolute error, R<sup>2</sup>, root mean squared error, and mean squared error were considered as performance indicators. The simulation results indicated that the proposed BO-SVR with a Gaussian kernel model had superior performance to other kernel SVR and Gaussian Process Regression models, with a reduced RMSE of 0.0082, thus demonstrating its potential to predict the SoH more accurately.</div></div>","PeriodicalId":36174,"journal":{"name":"Global Energy Interconnection","volume":"8 5","pages":"Pages 891-904"},"PeriodicalIF":2.6,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145365810","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Coordinated control strategy for multi-DG DC microgrid based on two-layer fuzzy neural network 基于双层模糊神经网络的多dg直流微电网协调控制策略

IF 2.6 Q4 ENERGY & FUELS

Global Energy Interconnection

Pub Date : 2025-10-01 DOI: 10.1016/j.gloei.2025.04.006

Hao Pan , Limin Jia

Conventional coordinated control strategies for DC bus voltage signal (DBS) in islanded DC microgrids (IDCMGs) struggle with coordinating multiple distributed generators (DGs) and cannot effectively incorporate state of charge (SOC) information of the energy storage system, thereby reducing the system flexibility. In this study, we propose an adaptive coordinated control strategy that employs a two-layer fuzzy neural network controller (FNNC) to adapt to varying operating conditions in an IDCMG with multiple PV and battery energy storage system (BESS) units. The first-layer FNNC generates optimal operating mode commands for each DG, thereby avoiding the requirement for complex operating modes based on SOC segmentation. An optimal switching sequence logic prioritizes the most appropriate units during mode transitions. The second-layer FNNC dynamically adjusts the droop power to overcome power distribution challenges among DG groups. This helps in preventing the PV power from exceeding the limits and mitigating the risk of BESS overcharging or over-discharging. The simulation results indicate that the proposed strategy enhances the coordinated operation of multi-DG IDCMGs, thereby ensuring the efficient and safe utilization of PV and BESS.

传统的孤岛直流微电网直流母线电压信号协调控制策略难以协调多个分布式发电机，且不能有效地吸收储能系统的荷电状态信息，降低了系统的灵活性。在本研究中，我们提出了一种自适应协调控制策略，该策略采用双层模糊神经网络控制器（FNNC）来适应具有多个光伏和电池储能系统（BESS）单元的IDCMG的不同运行条件。第一层FNNC为每个DG生成最优的工作模式命令，从而避免了基于SOC分割的复杂工作模式的需求。在模式转换期间，最优切换序列逻辑优先考虑最合适的单元。第二层FNNC动态调整下垂功率，以克服DG组之间的功率分配挑战。这有助于防止光伏功率超过限制，减轻BESS过充电或过放电的风险。仿真结果表明，该策略增强了多dg idcmg的协同运行，从而保证了光伏和BESS的高效安全利用。

{"title":"Coordinated control strategy for multi-DG DC microgrid based on two-layer fuzzy neural network","authors":"Hao Pan , Limin Jia","doi":"10.1016/j.gloei.2025.04.006","DOIUrl":"10.1016/j.gloei.2025.04.006","url":null,"abstract":"<div><div>Conventional coordinated control strategies for DC bus voltage signal (DBS) in islanded DC microgrids (IDCMGs) struggle with coordinating multiple distributed generators (DGs) and cannot effectively incorporate state of charge (SOC) information of the energy storage system, thereby reducing the system flexibility. In this study, we propose an adaptive coordinated control strategy that employs a two-layer fuzzy neural network controller (FNNC) to adapt to varying operating conditions in an IDCMG with multiple PV and battery energy storage system (BESS) units. The first-layer FNNC generates optimal operating mode commands for each DG, thereby avoiding the requirement for complex operating modes based on SOC segmentation. An optimal switching sequence logic prioritizes the most appropriate units during mode transitions. The second-layer FNNC dynamically adjusts the droop power to overcome power distribution challenges among DG groups. This helps in preventing the PV power from exceeding the limits and mitigating the risk of BESS overcharging or over-discharging. The simulation results indicate that the proposed strategy enhances the coordinated operation of multi-DG IDCMGs, thereby ensuring the efficient and safe utilization of PV and BESS.</div></div>","PeriodicalId":36174,"journal":{"name":"Global Energy Interconnection","volume":"8 5","pages":"Pages 732-746"},"PeriodicalIF":2.6,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145365811","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A review of research on intelligent fault detection of power equipment based on infrared and voiceprint: methods, applications and challenges 基于红外声纹和声纹的电力设备智能故障检测研究综述：方法、应用和挑战

IF 2.6 Q4 ENERGY & FUELS

Global Energy Interconnection

Pub Date : 2025-10-01 DOI: 10.1016/j.gloei.2025.08.001

Xizhou Du , Xing Lei , Ting Ye , Yingzhou Sun , Zewen Shang , Zhiqiang Liu , Tianyi Xu

As modern power systems grow in complexity, accurate and efficient fault detection has become increasingly important. While many existing reviews focus on a single modality, this paper presents a comprehensive survey from a dual-modality perspective-infrared imaging and voiceprint analysis-two complementary, non-contact techniques that capture different fault characteristics. Infrared imaging excels at detecting thermal anomalies, while voiceprint signals provide insight into mechanical vibrations and internal discharge phenomena. We review both traditional signal processing and deep learning-based approaches for each modality, categorized by key processing stages such as feature extraction and classification. The paper highlights how these modalities address distinct fault types and how they may be fused to improve robustness and accuracy. Representative datasets are summarized, and practical challenges such as noise interference, limited fault samples, and deployment constraints are discussed. By offering a cross-modal, comparative analysis, this work aims to bridge fragmented research and guide future development in intelligent fault detection systems. The review concludes with research trends including multimodal fusion, lightweight models, and self-supervised learning.

随着现代电力系统的日益复杂，准确、高效的故障检测变得越来越重要。虽然许多现有的评论都集中在单一模式上，但本文从双模式的角度进行了全面的调查-红外成像和声纹分析-两种互补的非接触式技术，可捕获不同的故障特征。红外成像在检测热异常方面表现出色，而声纹信号则可以深入了解机械振动和内部放电现象。我们回顾了每种模式的传统信号处理和基于深度学习的方法，并按关键处理阶段（如特征提取和分类）进行了分类。本文重点介绍了这些模式如何处理不同的故障类型，以及它们如何融合以提高鲁棒性和准确性。总结了代表性数据集，并讨论了噪声干扰、有限故障样本和部署约束等实际挑战。通过提供跨模式的比较分析，这项工作旨在弥合碎片化的研究，并指导智能故障检测系统的未来发展。总结了多模态融合、轻量化模型和自监督学习等研究趋势。

{"title":"A review of research on intelligent fault detection of power equipment based on infrared and voiceprint: methods, applications and challenges","authors":"Xizhou Du , Xing Lei , Ting Ye , Yingzhou Sun , Zewen Shang , Zhiqiang Liu , Tianyi Xu","doi":"10.1016/j.gloei.2025.08.001","DOIUrl":"10.1016/j.gloei.2025.08.001","url":null,"abstract":"<div><div>As modern power systems grow in complexity, accurate and efficient fault detection has become increasingly important. While many existing reviews focus on a single modality, this paper presents a comprehensive survey from a dual-modality perspective-infrared imaging and voiceprint analysis-two complementary, non-contact techniques that capture different fault characteristics. Infrared imaging excels at detecting thermal anomalies, while voiceprint signals provide insight into mechanical vibrations and internal discharge phenomena. We review both traditional signal processing and deep learning-based approaches for each modality, categorized by key processing stages such as feature extraction and classification. The paper highlights how these modalities address distinct fault types and how they may be fused to improve robustness and accuracy. Representative datasets are summarized, and practical challenges such as noise interference, limited fault samples, and deployment constraints are discussed. By offering a cross-modal, comparative analysis, this work aims to bridge fragmented research and guide future development in intelligent fault detection systems. The review concludes with research trends including multimodal fusion, lightweight models, and self-supervised learning.</div></div>","PeriodicalId":36174,"journal":{"name":"Global Energy Interconnection","volume":"8 5","pages":"Pages 821-846"},"PeriodicalIF":2.6,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145365808","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0