International Journal of Electrical Power & Energy Systems最新文献_第8页

An enhanced substation equipment detection method based on distributed federated learning

IF 5 2区工程技术

International Journal of Electrical Power & Energy Systems Pub Date : 2025-03-03 DOI: 10.1016/j.ijepes.2025.110547

Zhuyun Li , Qiutong Qin , Yingyi Yang , Xiaoming Mai , Yuya Ieiri , Osamu Yoshie

{"title":"An enhanced substation equipment detection method based on distributed federated learning","authors":"Zhuyun Li , Qiutong Qin , Yingyi Yang , Xiaoming Mai , Yuya Ieiri , Osamu Yoshie","doi":"10.1016/j.ijepes.2025.110547","DOIUrl":"10.1016/j.ijepes.2025.110547","url":null,"abstract":"<div><div>The inefficiency of manual inspections in substations struggles to meet increasing workloads amid power grid expansion, necessitating intelligent solutions for equipment monitoring. This study addresses two key challenges: detecting diverse equipment under scale variations, occlusions, and real-time constraints, and ensuring data privacy given geographically dispersed, sensitive substation data. We propose CWA-YOLO, a detection framework integrating multi-scale feature fusion and an enhanced small-object detection head into YOLOv8 to improve accuracy across variable conditions. Additionally, a federated learning (FL) system tailored for substations enables collaborative model training without centralized data sharing, addressing privacy concerns and data heterogeneity. The framework’s novelty lies in its dual focus: optimizing detection performance through architectural enhancements and ensuring secure, efficient distributed learning. CWA-YOLO achieves mAP scores of 0.918 ([email protected]) and 0.623 ([email protected]:0.95), surpassing YOLOv8l and YOLOv7l by 6.5% and 7.49%, respectively, in accuracy. For FL, the Federated Adaptive (FedAdp) algorithm reduces communication rounds by 62% compared to Federated Averaging (FedAvg), maintaining near-centralized accuracy while preserving data locality. These results confirm the method’s effectiveness in improving substation equipment recognition securely and efficiently.</div></div>","PeriodicalId":50326,"journal":{"name":"International Journal of Electrical Power & Energy Systems","volume":"166 ","pages":"Article 110547"},"PeriodicalIF":5.0,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143529794","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Fault detection and classification of bipolar DC system with dedicated metallic return based on TF-ENSR

IF 5 2区工程技术

International Journal of Electrical Power & Energy Systems Pub Date : 2025-03-01 DOI: 10.1016/j.ijepes.2025.110574

Bo Ren, Niancheng Zhou, Qianggang Wang

{"title":"Fault detection and classification of bipolar DC system with dedicated metallic return based on TF-ENSR","authors":"Bo Ren, Niancheng Zhou, Qianggang Wang","doi":"10.1016/j.ijepes.2025.110574","DOIUrl":"10.1016/j.ijepes.2025.110574","url":null,"abstract":"<div><div>Fast and accurate fault diagnosis is necessary for continuous power delivery. In bipolar DC systems with dedicated metallic return (DMR), accurately distinguishing between pole-to-ground and pole-to-DMR faults is challenging. To address this, this paper proposes a data-driven protection method based on feature learning. Specifically, time-series feature extraction based on scalable hypothesis tests (Tsfresh) is utilized to automatically extract the feature set with clear physical interpretations from fault voltage signals. To ensure that the feature set is sufficiently concise while fully describing the fault state, the Feature-selector is integrated to efficiently eliminate redundant features. Additionally, an improved elastic network softmax regression (ENSR) model is employed to establish an accurate mapping between the selected features and fault types. Offline simulations in PSCAD/EMTDC and hardware-in-the-loop testing with real-time digital simulators (RTDS) demonstrate that the proposed method effectively detects and distinguishes between fault types. Comparative studies with other protection methods highlight the advantages of the proposed approach, including its robustness to high transition resistances and strong noise interference, adaptability to changes in sampling environments and current-limiting reactors, and low online computational burden.</div></div>","PeriodicalId":50326,"journal":{"name":"International Journal of Electrical Power & Energy Systems","volume":"166 ","pages":"Article 110574"},"PeriodicalIF":5.0,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143519985","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An Improved YOLOv8-XGBoost load rapid identification method based on multi-feature fusion

IF 5 2区工程技术

International Journal of Electrical Power & Energy Systems Pub Date : 2025-03-01 DOI: 10.1016/j.ijepes.2025.110573

JianYuan Wang, Long Cheng

{"title":"An Improved YOLOv8-XGBoost load rapid identification method based on multi-feature fusion","authors":"JianYuan Wang, Long Cheng","doi":"10.1016/j.ijepes.2025.110573","DOIUrl":"10.1016/j.ijepes.2025.110573","url":null,"abstract":"<div><div>Existing non-intrusive load monitoring (NILM) approaches face challenges including limited identification accuracy, computationally intensive architectures, and constrained generalization performance. To address these issues, this paper proposes an Improved YOLOv8-XGBoost rapid load identification method based on multi-feature fusion. First, the temporal features of load current data are extracted using the Markov Transition Field (MTF) algorithm through image encoding methods. Additionally, the Fast Fourier Transform (FFT) is employed to extract the maximum frequency component and average frequency amplitude as corresponding frequency-domain features. Subsequently, the Improved YOLOv8 network is utilized for preliminary recognition of temporal domain images. Finally, to resolve the low discriminability issue of similar loads, the recognition results of the Improved YOLOv8 network are fused with selected frequency-domain features using the eXtreme Gradient Boosting (XGBoost) algorithm for training to achieve the final identification results. Validation on both high-frequency and low-frequency datasets demonstrates that the proposed method exhibits strong generalization capability, achieving an identification accuracy of over 99%.</div></div>","PeriodicalId":50326,"journal":{"name":"International Journal of Electrical Power & Energy Systems","volume":"166 ","pages":"Article 110573"},"PeriodicalIF":5.0,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143527444","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Cost-efficient multiport DC circuit breaker with integrated power flow control for HVDC grids

IF 5 2区工程技术

International Journal of Electrical Power & Energy Systems Pub Date : 2025-03-01 DOI: 10.1016/j.ijepes.2025.110571

Yunfeng Huang, Huangqing Xiao

{"title":"Cost-efficient multiport DC circuit breaker with integrated power flow control for HVDC grids","authors":"Yunfeng Huang, Huangqing Xiao","doi":"10.1016/j.ijepes.2025.110571","DOIUrl":"10.1016/j.ijepes.2025.110571","url":null,"abstract":"<div><div>To address the technical challenges of fast DC fault interruption and power flow control in DC grids, this paper proposes a multiport DC circuit breaker (CB) topology with power flow control (PFC) capability and designs two control strategies: a PFC mode and a CB mode. The proposed circuit topology integrates both functions through topological similarity, resulting in high reuse of power electronic devices and superior economic efficiency. The control strategy for the PFC mode independently regulates the capacitor voltage and the current of each line, solving the issue of poor applicability of conventional power flow control methods in multiport scenarios. The control strategy for the CB mode ensures fast mode switching and timely fault interruption. A four-terminal DC grid simulation model was built in PSCAD/EMTDC to validate various operating conditions. The results demonstrate that the proposed multiport DC CB with PFC capability can rapidly and accurately track the reference value of the line power flow under normal operation using the PFC mode. In the event of a fault, it quickly switches to the CB mode to clear the fault, and after fault interruption, it can restart the PFC mode to regulate the power flow of the healthy lines.</div></div>","PeriodicalId":50326,"journal":{"name":"International Journal of Electrical Power & Energy Systems","volume":"166 ","pages":"Article 110571"},"PeriodicalIF":5.0,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143527385","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Nested Bi-level scheduling strategy for energy storage systems in hybrid microgrid considering uncertainties of battery dynamic performances

IF 5 2区工程技术

International Journal of Electrical Power & Energy Systems Pub Date : 2025-03-01 DOI: 10.1016/j.ijepes.2025.110575

Jiazhi Lei , Zhao Liu

{"title":"Nested Bi-level scheduling strategy for energy storage systems in hybrid microgrid considering uncertainties of battery dynamic performances","authors":"Jiazhi Lei , Zhao Liu","doi":"10.1016/j.ijepes.2025.110575","DOIUrl":"10.1016/j.ijepes.2025.110575","url":null,"abstract":"<div><div>This paper proposed a nested bi-Level scheduling strategy for energy storage systems in hybrid microgrid considering uncertainties of battery dynamic performances. Firstly, the uncertainties in dynamic performances caused by fitting error including efficiencies, self-discharge rate, cycle life and capacity fading were modeled by interval method and probability distribution method. Simultaneously, the significant influences of battery dynamic performances on power outputs of battery were specially quantized by direct physical influence, direct electric quantity influence and indirect state influence. Then, a nested bi-level optimization model was developed for specifying the scheduling strategy of energy storage systems. Inner layer optimization was applied for realizing the operation strategy optimization of battery ESSs and outer layer optimization was applied for realizing the battery performance optimization. Case studies based on multi-scene generation mode verified the effectiveness of the proposed nested bi-level scheduling strategy. With the increase of battery dynamic performances uncertainties, more economic benefits are brought by energy storage battery, but the battery dynamic performances continuously decline. Compared with single layer optimization, nested bi-level optimization scheduling model slightly reduced the total benefits, but the battery dynamic performances <em>f</em><sub>1</sub> is significantly improved by about 20%.</div></div>","PeriodicalId":50326,"journal":{"name":"International Journal of Electrical Power & Energy Systems","volume":"166 ","pages":"Article 110575"},"PeriodicalIF":5.0,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143527445","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

High-efficiency BLDC motor regenerative braking system with new single-switched transistor control algorithm

IF 5 2区工程技术

International Journal of Electrical Power & Energy Systems Pub Date : 2025-03-01 DOI: 10.1016/j.ijepes.2025.110565

Sławomir Karyś, Paweł Stawczyk

引用次数: 0

Large-scale electric vehicle charging coordination for cost-effectiveness and fairness under peak power constraints

IF 5 2区工程技术

International Journal of Electrical Power & Energy Systems Pub Date : 2025-02-27 DOI: 10.1016/j.ijepes.2025.110539

Hyeonu Lee , Junghyun Kim , Hosung Park

{"title":"Large-scale electric vehicle charging coordination for cost-effectiveness and fairness under peak power constraints","authors":"Hyeonu Lee , Junghyun Kim , Hosung Park","doi":"10.1016/j.ijepes.2025.110539","DOIUrl":"10.1016/j.ijepes.2025.110539","url":null,"abstract":"<div><div>Electric vehicles (EVs) are merging as a feasible alternative to existing gasoline-based vehicles to mitigate climate change and greenhouse gas emission. As the number of EVs is increasing, uncoordinated large-scale EV charging behaviors may lead to power grid instability, extra electricity fee and cost unfairness among EV owners. In this paper, we propose a large-scale EV charging coordination framework that enhances cost-effectiveness, cost fairness and target state-of-charge (SoC) level satisfaction. A simple and effective scheduling algorithm, called low-price pursuit algorithm (LPPA), is proposed to minimize the charging costs by considering three-level time-of-use (TOU) periods. Under low peak power constraints, LPPA may lead to challenges, such as EVs not being fully charged or overcharged at high-priced periods. To address these challenges, a novel selective extra charging algorithm (SECA) is proposed to identify problematic EVs through future demand forecasting and simulations, providing additional charging to ensure SoC satisfaction as well as cost-effectiveness. By dynamically incorporating LPPA and SECA, the proposed framework achieves the balance between cost-effectiveness and SoC satisfaction. In addition, we evaluate the fairness of charging costs for each EV by introducing individual cost gains as a performance measure. Simulation results show that the proposed framework achieves better performance than existing schemes across various scenarios, including TOU pricings, charging speeds and EV’s battery capacities.</div></div>","PeriodicalId":50326,"journal":{"name":"International Journal of Electrical Power & Energy Systems","volume":"166 ","pages":"Article 110539"},"PeriodicalIF":5.0,"publicationDate":"2025-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143509302","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Photovoltaic power prediction system based on dual-layer decomposition strategy and a novel dynamic grouping multi-objective coati optimization algorithm

IF 5 2区工程技术

International Journal of Electrical Power & Energy Systems Pub Date : 2025-02-27 DOI: 10.1016/j.ijepes.2025.110562

Xiaole Tang , Hao Lu , Yanting Kang , Wenjun Zhao

{"title":"Photovoltaic power prediction system based on dual-layer decomposition strategy and a novel dynamic grouping multi-objective coati optimization algorithm","authors":"Xiaole Tang , Hao Lu , Yanting Kang , Wenjun Zhao","doi":"10.1016/j.ijepes.2025.110562","DOIUrl":"10.1016/j.ijepes.2025.110562","url":null,"abstract":"<div><div>The substantial volatility of photovoltaic (PV) power output presents challenges to the stable operation of power grids. To improve the accuracy and stability of PV power prediction, this study proposes a PV power prediction system based on a dual-layer decomposition strategy and a dynamic grouping multi-objective Coati optimization algorithm (DGMOCOA). This system includes three core modules: data preprocessing, optimization, and prediction. The dual-layer decomposition strategy effectively utilizes high-frequency signal information, overcoming the limitations of single-layer methods. Additionally, the DGMOCOA employs a dynamic grouping strategy to balance exploration and exploitation, enhancing the system’s accuracy and stability. To validate the proposed strategy and hybrid model, extensive experiments were conducted. The results show that, compared to 11 benchmark models, the proposed model achieves higher prediction accuracy and greater stability. In interval prediction, it also demonstrates higher coverage and narrower intervals.</div></div>","PeriodicalId":50326,"journal":{"name":"International Journal of Electrical Power & Energy Systems","volume":"166 ","pages":"Article 110562"},"PeriodicalIF":5.0,"publicationDate":"2025-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143511481","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Mechanism analysis of subsynchronous control interactions between full-converter-interfaced generation and a series-compensated network

IF 5 2区工程技术

International Journal of Electrical Power & Energy Systems Pub Date : 2025-02-26 DOI: 10.1016/j.ijepes.2025.110525

Jiangfeng Zhang , Siqi Bu , Tao Xue , Jiebei Zhu , Ilhan Kocar

{"title":"Mechanism analysis of subsynchronous control interactions between full-converter-interfaced generation and a series-compensated network","authors":"Jiangfeng Zhang , Siqi Bu , Tao Xue , Jiebei Zhu , Ilhan Kocar","doi":"10.1016/j.ijepes.2025.110525","DOIUrl":"10.1016/j.ijepes.2025.110525","url":null,"abstract":"<div><div>Recent studies reveal that unstable subsynchronous control interactions (SSCIs) between full-converter-interfaced generation (FCIG) and the series-compensated transmission line may occur when high-bandwidth phase-locked loops (PLLs) and high series compensation level (SCL) are implemented. This paper proposes a damping contribution analysis (DCA) method to investigate the SSCI mechanisms involving an FCIG-based power plant connected to a series-compensated network. Analytical expressions of the damping contribution coefficients from the series-compensated network to the PLL and q-axis current control oscillation loops are first derived. These coefficients offer a clear physical explanation of how and why high PLL bandwidth and SCL will deteriorate the damping of the dominant oscillation mode, thus leading to system instability. Additionally, a new SSCI phenomenon is identified, where dynamic interactions between the series compensation and the inner q-axis current control loop with slow dynamics also pose SSCI risks. Furthermore, the damping contribution coefficient facilitates evaluating the impacts of changes in system operating parameters on the modal shift of the concerned oscillation mode. The theoretical findings and conclusions obtained through theDCA are validated using modal analysis and electromagnetic transient simulations.</div></div>","PeriodicalId":50326,"journal":{"name":"International Journal of Electrical Power & Energy Systems","volume":"166 ","pages":"Article 110525"},"PeriodicalIF":5.0,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143487166","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Small-Signal stability analysis of MMC-HVDC system with saturated transformer

IF 5 2区工程技术

International Journal of Electrical Power & Energy Systems Pub Date : 2025-02-26 DOI: 10.1016/j.ijepes.2025.110498

Hanwen Wang , Yang Wang , Xianyong Xiao , Yunzhu Chen , Shupeng Li , Zhijun Er , Zhenbin Li

{"title":"Small-Signal stability analysis of MMC-HVDC system with saturated transformer","authors":"Hanwen Wang , Yang Wang , Xianyong Xiao , Yunzhu Chen , Shupeng Li , Zhijun Er , Zhenbin Li","doi":"10.1016/j.ijepes.2025.110498","DOIUrl":"10.1016/j.ijepes.2025.110498","url":null,"abstract":"<div><div>Transformer saturation has a significant impact on the stability of HVDC systems. While traditional research has primarily focused on LCC-HVDC systems, studies on MMC systems remain limited. Given the anticipated dominance of MMC technology in the future, it is crucial to understand the instability risks MMC-HVDC systems face under transformer saturation. The key challenge lies in accurately modeling the harmonic coupling induced by the saturated transformer and analyzing its interaction with MMC-HVDC systems. To tackle this challenge, the harmonic state space (HSS) technique is employed in this paper to model the harmonic coupling in MMC-HVDC systems with saturated transformers. Initially, a saturable transformer model is developed, with the excitation curve fitted using a polynomial approach. This model is then interconnected with the MMC-HVDC system to establish a comprehensive HSS model for analysis. To facilitate the stability analysis, the HSS model is further transformed into a single-input–single-output impedance representation, enabling the effects of harmonic coupling to be observed through impedance curves. Finally, a Nyquist-based stability analysis is performed to explain why MMC-HVDC systems are more prone to instability under transformer saturation and to identify key factors contributing to this instability. Simulation and experimental results validate the theoretical analysis.</div></div>","PeriodicalId":50326,"journal":{"name":"International Journal of Electrical Power & Energy Systems","volume":"166 ","pages":"Article 110498"},"PeriodicalIF":5.0,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143487118","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0