{"title":"Online identification of cascading event sequences in power systems using deep learning","authors":"Georgios A. Nakas , Panagiotis N. Papadopoulos","doi":"10.1016/j.ijepes.2025.110717","DOIUrl":"10.1016/j.ijepes.2025.110717","url":null,"abstract":"<div><div>The framework proposed in this paper focuses on the online identification of the reason of cascading event sequences in power systems with renewable generation. Cascading events involve highly complex dynamic phenomena and can in some cases severely compromise the security of modern power systems, leading even to blackouts. The proposed framework takes into account uncertainties associated with network operating conditions, contingencies and renewable generation. By utilizing measurement data, the methods within the proposed framework can predict in close to real time the reason of upcoming cascading events, as defined by the action of protection devices capturing dynamic phenomena related to voltage, frequency or transient instability. The framework is evaluated on a modified version of the IEEE-39 bus model, augmented with renewable generation and protection devices. The results demonstrate that the proposed method can successfully predict the reason of cascading events as they appear in a sequence with a mean accuracy of 97.4% with an online computation time of 1.09ms on average. The scalability of the method is showcased on a modified version of the IEEE-118 bus system.</div></div>","PeriodicalId":50326,"journal":{"name":"International Journal of Electrical Power & Energy Systems","volume":"169 ","pages":"Article 110717"},"PeriodicalIF":5.0,"publicationDate":"2025-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144099494","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Zhongyu Sun , Bingyin Xu , Wei Wang , Tony Yip , Fan Li
{"title":"Distributed earth fault detection method for low voltage distribution networks using phase voltage synchronization","authors":"Zhongyu Sun , Bingyin Xu , Wei Wang , Tony Yip , Fan Li","doi":"10.1016/j.ijepes.2025.110771","DOIUrl":"10.1016/j.ijepes.2025.110771","url":null,"abstract":"<div><div>The existing earth fault detection methods for low-voltage distribution networks demonstrate poor adaptability to faults with fault resistance. To address this problem, the composition of residual current during non-fault states and its impact on earth fault detection are analysed. A distributed earth fault detection method is then proposed. This method divides a low-voltage distribution network into multiple protection zones and uses the differential residual current of each protection zone to identify earth faults, effectively reducing the impact of residual current during non-fault states. Furthermore, a time synchronization technique using phase voltage as a reference is proposed, which achieves low-cost time synchronization without relying on external clocks. The effectiveness of the proposed method is verified by simulations and field tests in an actual low-voltage platform. Compared with conventional approaches, the proposed method exhibits significant enhancements in both sensitivity and reliability.</div></div>","PeriodicalId":50326,"journal":{"name":"International Journal of Electrical Power & Energy Systems","volume":"169 ","pages":"Article 110771"},"PeriodicalIF":5.0,"publicationDate":"2025-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144099326","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Wanqi Zhang , Shaobing Yang , Tingting He , Dylan Dah-Chuan Lu , Mingli Wu
{"title":"A data-driven power consumption estimation algorithm of catenary for electrified railway","authors":"Wanqi Zhang , Shaobing Yang , Tingting He , Dylan Dah-Chuan Lu , Mingli Wu","doi":"10.1016/j.ijepes.2025.110737","DOIUrl":"10.1016/j.ijepes.2025.110737","url":null,"abstract":"<div><div>Power consumption for electrified railway not only reflects the power supply capacity, energy supply efficiency and energy saving level, but also indicates potential defects and risks. However, due to the complexity of the traction network and the randomness of trains, there is a challenge to estimate the power consumption accurately and economically. This paper proposes a data-driven power consumption estimation algorithm of catenary and trains for electrified railway. The unit impedance of catenary is identified via a one-train condition based on the simultaneous real-time electrical data of traction substation and section post. The underdetermined issue of multi-train condition can be converted into a problem within a finite solution domain, depending on either the average speed, speed limit, or both. Considering the time dependence and the displacement continuity of trains, the power consumption can be obtained for conditions with different number of trains operating in a power supply section. Finally, the proposed method is validated by field test and simulation data from traction and power supply calculations. Taking the field test as a reference, the identified result is accurate with an error of −0.75 % compared to the conventional method. No extra monitoring devices and computing power are required in the algorithm.</div></div>","PeriodicalId":50326,"journal":{"name":"International Journal of Electrical Power & Energy Systems","volume":"169 ","pages":"Article 110737"},"PeriodicalIF":5.0,"publicationDate":"2025-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144106791","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Stator temperature rise of synchronous condenser affected by temperature variation at rotor airflow outlet","authors":"Guorui Xu , Yin Wang , Zhiqiang Li , Yang Xiao","doi":"10.1016/j.ijepes.2025.110772","DOIUrl":"10.1016/j.ijepes.2025.110772","url":null,"abstract":"<div><div>The fluid and temperature distributions of the large air-cooled Synchronous Condenser (SC) are very complex, thereby the interaction of the stator and rotor airflows is often neglected in the previous study of the temperature field. In order to calculate the precise temperature rise of the SC under different operating conditions, this paper studies the effect of the temperature variation at the rotor airflow outlet on the stator temperature distribution. The loss, fluid and temperature distributions of a 300-MVar air-cooled SC are calculated based on the electromagnetic, fluid and heat transfer models. The temperature variation at the rotor airflow outlet along with the operating condition is revealed, and its effect on the stator temperature rise is analyzed. Further, it is studied that the variation laws of the stator and rotor maximum temperatures along with the air volume allocation, and the optimal air volume allocation is determined. The results can provide the reference for the accurate temperature calculation and the optimization design of the cooling systems for the large air-cooled SCs.</div></div>","PeriodicalId":50326,"journal":{"name":"International Journal of Electrical Power & Energy Systems","volume":"169 ","pages":"Article 110772"},"PeriodicalIF":5.0,"publicationDate":"2025-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144099497","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Tariq Limouni , Reda Yaagoubi , Khalid Bouziane , Khalid Guissi , El Houssain Baali
{"title":"Intelligent real time control strategy and power management based on MPC and LSTM-TCN model for standalone DC microgrid with energy storage","authors":"Tariq Limouni , Reda Yaagoubi , Khalid Bouziane , Khalid Guissi , El Houssain Baali","doi":"10.1016/j.ijepes.2025.110761","DOIUrl":"10.1016/j.ijepes.2025.110761","url":null,"abstract":"<div><div>Standalone microgrids powered by renewable energy face major challenges of stability and reliability due to the intermittent nature of those energy sources and fast load shifting. To mitigate these challenges, an effective control strategy and power management are required to ensure power balancing and minimizing fluctuations. This paper presents a novel intelligent control and power management strategy for standalone DC microgrids. The primary objectives of this control strategy are real-time voltage regulation and power balancing, as well as preventing the energy storage system from overcharging and over discharging. The microgrid contains a PV system with energy storage systems, including a battery and supercapacitor. The proposed control strategy is based on a LSTM-TCN model and model predictive control (MPC). The LSTM-TCN model forecasts the microgrid disturbances including environmental conditions (irradiance and temperature) and the load demand. To effectively integrate the forecasted values in the MPC architecture, the sigmoid function is applied, enabling a smooth transition between the actual system states and predicted ones especially during high variation of the disturbances. Performance evaluation of the proposed control strategy conducted through comparisons with established control methods under the variation of environmental conditions and load demand. Results show that the proposed control approach provides excellent voltage stability, fast response time, and low overshoot, performing better than other control strategies, especially during high load variation.</div></div>","PeriodicalId":50326,"journal":{"name":"International Journal of Electrical Power & Energy Systems","volume":"169 ","pages":"Article 110761"},"PeriodicalIF":5.0,"publicationDate":"2025-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144099496","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Design-Oriented transient stability analysis of LCC-HVDC inverter with DC voltage control under grid fault","authors":"Zhiwei Lei, Junpeng Ma, Shunliang Wang, Ning Jiao, Tianqi Liu, Ruiting Xu","doi":"10.1016/j.ijepes.2025.110765","DOIUrl":"10.1016/j.ijepes.2025.110765","url":null,"abstract":"<div><div>Subsequent commutation failure (SCF) is an inherent issue for the line-commutated-converter based high voltage direct current (LCC-HVDC) in the receiving end. Nonlinear natures of LCC, such as the DC-AC conversion, commutation overlaps, relation between the transmitted power and grid voltage, etc. complicate the modeling and theoretical analysis for SCF under grid faults, which also poses challenges to the suppression of SCF. To address the above issues, the phase portraits analysis method is developed to depict the dynamics of SCF during grid faults. In the proposed analysis method, the large-signal model of the inverter is derived, hereafter, the dominant inducements of SCF, including control parameters, grid sag depth, and grid impedance are elaborated quantitatively. Moreover, an adaptive PI controller is designed for DC voltage control in both steady state and grid fault conditions, which can ensure the safe operation of the inverter under various degrees of grid fault. Then parametric boundaries for maintaining the highest DC voltage during transients are also obtained. Experimental results verify the effectiveness of the analysis and the proposed strategy.</div></div>","PeriodicalId":50326,"journal":{"name":"International Journal of Electrical Power & Energy Systems","volume":"169 ","pages":"Article 110765"},"PeriodicalIF":5.0,"publicationDate":"2025-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144089191","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Online high-dimensional security boundary rapid generation framework considering over-limit risk for different operating states","authors":"Yuan Zeng, Wenya Xue, Junzhi Ren, Chao Qin","doi":"10.1016/j.ijepes.2025.110743","DOIUrl":"10.1016/j.ijepes.2025.110743","url":null,"abstract":"<div><div>The Thermal Security Region is a key tool for assessing the security margin of random operating modes in power systems. However, with the large-scale integration of renewable energy and the ongoing expansion of the power grid, operating modes have become increasingly complex and diverse. As a result, low-dimensional security boundaries constructed from historical data struggle to meet the current demands in terms of adaptability and timeliness. This study proposes an online generation method for high-dimensional security boundaries based on power flow over-limit risk, while considering the impact of different operating states on the accuracy of reduced-dimensional security boundaries. Firstly, the impact of different operating states on boundary fitting in the power system is identified using unsupervised clustering. Next, a security boundary set is constructed, and a risk prediction model based on AdaBoost.M2 is employed to identify potential boundary sets that may exceed limits, using confidence scoring. Finally, these selected security boundary features are utilized for generative adversarial network training, enabling the high-dimensional security boundaries to comprehensively account for multiple scenarios. This method enhances the credibility of the decision-making process through mechanism analysis while improving the speed and accuracy of high-dimensional security boundary generation. In tests using operational data from different states within the IEEE 39-bus and HZPG systems, it achieved an accuracy of over 95%. In terms of timeliness, the risk prediction component satisfies real-time application requirements, and the boundary generation process can be performed online.</div></div>","PeriodicalId":50326,"journal":{"name":"International Journal of Electrical Power & Energy Systems","volume":"169 ","pages":"Article 110743"},"PeriodicalIF":5.0,"publicationDate":"2025-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144099495","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ye Cao , Song Xiao , Jingdong Yan , Chenyang Liu , Tiangeng Li , Xiao Liu , Guangning Wu , Yujun Guo , Jiefu Hou , Yongdong He , Xueqin Zhang , Nibishaka Erneste , Jan K. Sykulski
{"title":"Contribution analysis of neutral current for the substations invaded by stray current from multiple metro lines","authors":"Ye Cao , Song Xiao , Jingdong Yan , Chenyang Liu , Tiangeng Li , Xiao Liu , Guangning Wu , Yujun Guo , Jiefu Hou , Yongdong He , Xueqin Zhang , Nibishaka Erneste , Jan K. Sykulski","doi":"10.1016/j.ijepes.2025.110773","DOIUrl":"10.1016/j.ijepes.2025.110773","url":null,"abstract":"<div><div>As a type of convenient and environmentally friendly transportation tool, urban rail transit has been constructed as vital infrastructure in numerous cities over the world. Currently, direct current (DC) traction power supply mode has been applied as mainstream for most of metro lines. However, along with long-term service, the insulation performance between steel track and concrete sleeper deteriorates gradually, possibly causing traction current leaking from rail to ground, forming as ‘stray current’. It possibly invades into transformers through their grounding poles, causing local thermal surge, abnormal vibration or even power quality degradation. At present, only relying on the passively protecting method via installing fixed impedance at the grounding pole can hardly cope with the transiently-varying stray current. Tracing the origin of stray current especially under the scenario of multiple metro lines becomes essential, as the periodicity of traction current from each metro line can be extracted as ‘fingerprint’. A boundary element model of a region with multiple metro lines is launched based on practical geological data, for evaluating the route and distribution of stray current. Based on the Wavelet Transform (WT) method, the correlation is found precisely via comparing periodic feature between the traction current of different metro lines and the neutral current measured synchronously at substations. Moreover, an origin tracing method for clarifying the contributions made by different metro lines on the substation’s neutral current is proposed via analyzing the local periodicity of traction current and neutral current, for laying the solid foundation of precise suppression from origin.</div></div>","PeriodicalId":50326,"journal":{"name":"International Journal of Electrical Power & Energy Systems","volume":"169 ","pages":"Article 110773"},"PeriodicalIF":5.0,"publicationDate":"2025-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144089190","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Dong Liu , Juan S. Giraldo , Peter Palensky , Pedro P. Vergara
{"title":"A siamese neural network model for phase identification in distribution networks","authors":"Dong Liu , Juan S. Giraldo , Peter Palensky , Pedro P. Vergara","doi":"10.1016/j.ijepes.2025.110718","DOIUrl":"10.1016/j.ijepes.2025.110718","url":null,"abstract":"<div><div>Distribution system operators (DSOs) often lack high-quality data on low-voltage distribution networks (LVDNs), including the topology and the phase connection of residential customers. The phase connection is essential for phase balancing assessment and distributed energy resources (DERs) integration. The existing load profiles-based approaches rely on stepwise subtraction of the identified customers in a step-by-step identification procedure, while the accuracy of each step is not guaranteed. This paper introduces a siamese neural network model to identify single-phase connections without requiring stepwise subtraction. It comprises self-taught learning (STT) and a phase-label identification strategy. The introduced self-taught learning enables DSOs to train a recurrent neural network-based Siamese network (RSN) only relying on an unlabelled dataset. Besides, the siamese network (SN) is robust to noise and fluctuations in the data to a certain extent, making the proposed method robust to measurement errors. A Kendall correlation-based phase modification strategy is introduced to modified phase labels with lower confidence, aiming to mitigate the accuracy loss induced by the limited generalization of SN. The proposed approach is tested on the IEEE European low voltage test feeder and a residential network in the Netherlands Simulation results illustrate the feasibility and robustness of the proposed approach on incomplete datasets. The accuracy exceeded 83% and 90%, respectively, when using datasets of less than 20 days with and without measurement errors.</div></div>","PeriodicalId":50326,"journal":{"name":"International Journal of Electrical Power & Energy Systems","volume":"169 ","pages":"Article 110718"},"PeriodicalIF":5.0,"publicationDate":"2025-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144089184","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Wencong Xiao, Tao Yu, Zhiwei Chen, Zhenning Pan, Yufeng Wu, Qianjin Liu
{"title":"Data augmented offline deep reinforcement learning for stochastic dynamic power dispatch","authors":"Wencong Xiao, Tao Yu, Zhiwei Chen, Zhenning Pan, Yufeng Wu, Qianjin Liu","doi":"10.1016/j.ijepes.2025.110747","DOIUrl":"10.1016/j.ijepes.2025.110747","url":null,"abstract":"<div><div>Operating a power system under uncertainty while ensuring both economic efficiency and system security can be formulated as a stochastic dynamic economic dispatch (DED) problem. Deep reinforcement learning (DRL) offers a promising solution by learning dispatch policies through extensive system interaction and trial-and-error. However, the effectiveness of DRL is constrained by two key limitations: the high cost of real-time system interactions and the limited diversity of historical scenarios. To address these challenges, this paper proposes an offline deep reinforcement learning (ODRL) framework tailored for power system dispatch. First, a conditional generative adversarial network (CGAN) is employed to augment historical scenarios, thereby improving data diversity. The resulting training dataset combines both real and synthetically generated scenarios. Second, a conservative offline soft actor-critic (COSAC) algorithm is developed to learn dispatch policies directly from this hybrid offline dataset, eliminating the need for online interaction. Experimental results demonstrate that the proposed approach significantly outperforms both conventional DRL and existing offline learning methods in terms of reliability and economic performance.</div></div>","PeriodicalId":50326,"journal":{"name":"International Journal of Electrical Power & Energy Systems","volume":"169 ","pages":"Article 110747"},"PeriodicalIF":5.0,"publicationDate":"2025-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144089189","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}