International Journal of Electrical Power & Energy Systems最新文献

{"title":"SafetyGPT: An autonomous agent of electrical safety risks for monitoring workers’ unsafe behaviors","authors":"Wei Li ,&nbsp;Fuqi Ma ,&nbsp;Zhiyuan Zuo ,&nbsp;Rong Jia ,&nbsp;Bo Wang ,&nbsp;Abdullah M Alharbi","doi":"10.1016/j.ijepes.2025.110672","DOIUrl":"10.1016/j.ijepes.2025.110672","url":null,"abstract":"<div><div>Workers’ unsafe behavior is one of the major causes of accidents in electric power production. Intelligent monitoring of workers’ unsafe behaviors can effectively prevent the expansion of safety risks, thereby blocking the development process of risks to accidents. Electric power production processes are diverse in nature and require the frequent switching of operating scenarios. This makes it difficult to identify what is “unsafe” since worker behaviors within the given electrical context also exhibit variability and diversity. Existing methods have insufficient generalization and adaptability, which makes them inadequate for the case of electric power production. Therefore, this paper proposes Safety Generative Pre-trained Transformers (SafetyGPT), an autonomous agent of safety risk based on a multi-modal large language model, which incorporates a human–machine collaborative monitoring mode for unsafe behaviors of workers. SafetyGPT loads the electric power production video, and the backend supervisors set instructions for SafetyGPT based on task requirements. The model encodes visual and textual features into corresponding tokens, realizes multi-modal feature alignment and fusion through the cross-attention mechanism, and then generates targeted responses through the large language model. Next, the proposed method is applied to real production site data to confirm the effectiveness and superiority through comparison with other methods designed to identify unsafe behaviors. Experimental results show that the accuracy of the proposed method for the identification of unsafe behaviors in complex environments is 96.5%, and that it can generate reasonable recommended plan based on the identification results, assist backend supervisors in making decisions, and effectively improve the safety level of power production.</div></div>","PeriodicalId":50326,"journal":{"name":"International Journal of Electrical Power & Energy Systems","volume":"168 ","pages":"Article 110672"},"PeriodicalIF":5.0,"publicationDate":"2025-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143834141","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":"A fast SOC balancing control strategy for distributed energy storage system based on sinusoidal signal injection","authors":"Ling Yang ,&nbsp;Jiahao Luo ,&nbsp;Junhao Liao ,&nbsp;Xutao Wen ,&nbsp;Chongyao Yuan ,&nbsp;Yu Wang ,&nbsp;Dongtao Luo ,&nbsp;Marta Molinas ,&nbsp;Olav Bjarte Fosso","doi":"10.1016/j.ijepes.2025.110678","DOIUrl":"10.1016/j.ijepes.2025.110678","url":null,"abstract":"<div><div>In this paper, a fast state-of-charge balancing strategy for distributed energy storage system based on injected sinusoidal signals is proposed, which solves the problems of unbalanced state-of-charge, unreasonable load current sharing, and unstable direct current bus voltage. Firstly, the state-of-charge of distributed energy storage unit is directly combined with the reference current of the current closed-loop by using the arc-sin function, and two acceleration factors are set to realize rapid state-of-charge balance. Secondly, the frequency of the injected sinusoidal signals is constructed to be inversely proportional to the direct current output current of the distributed energy storage unit, which frees from the constraints of the framework of droop control and overcomes the limitations of conventional droop control. Then, the phase difference between the injected sinusoidal signals forms a reactive power circulation, which enables the output current of the distributed energy storage unit to be proportionally shared by its capacity without communication, reducing the cost of system communication. In addition, the bus voltage can be effectively compensated by designing the limiter link and virtual negative impedance. Finally, the feasibility and effectiveness of the proposed strategy are verified by experiments.</div></div>","PeriodicalId":50326,"journal":{"name":"International Journal of Electrical Power & Energy Systems","volume":"168 ","pages":"Article 110678"},"PeriodicalIF":5.0,"publicationDate":"2025-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143834139","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":"GNN assisted frequency constrained unit commitment of multi-region power systems with high penetration of renewable energy sources","authors":"Mingjian Tuo ,&nbsp;Cunzhi Zhao ,&nbsp;Mulan Zhang ,&nbsp;Tao Gao ,&nbsp;Xuequan Shang","doi":"10.1016/j.ijepes.2025.110670","DOIUrl":"10.1016/j.ijepes.2025.110670","url":null,"abstract":"<div><div>The increasing integration of renewable energy resources (RES) into the power grid poses significant challenges in system frequency dynamics. Traditional frequency-constrained unit commitment models simplify the average system frequency and neglect the spatial characteristics of frequency dynamics, potentially underestimating the risk of contingencies. In this paper, we consider a nodal frequency response model to capture the frequency dynamics in the unit commitment problem. Nodal frequency dynamics and rate of change of frequency (RoCoF) expressions are converted into security constraints against worst contingency, which are then incorporated into the proposed muti-region frequency-constrained unit commitment (MR-FCUC) formulations. To improve the efficiency and performance of the MR-FCUC model, a decomposition algorithm is implemented to solve the proposed MR-FCUC efficiently. The subproblem of the original model confirms the frequency dynamics, and sensitivity cuts are refined based on the validation errors. Additionally, a GNN-based voltage phase angle predictor is incorporated to boost the computational efficiency of the FCUC model. Case study involving modified IEEE 24-bus and IEEE 118-bus systems illustrates the effectiveness of the proposed GNN-MR-FCUC model. Simulation results of test systems affirm that the frequency stability is guaranteed: the maximal RoCoF is mitigated within 0.5 Hz/s, and the lowest frequency nadir is maintained above 59.71 Hz.</div></div>","PeriodicalId":50326,"journal":{"name":"International Journal of Electrical Power & Energy Systems","volume":"168 ","pages":"Article 110670"},"PeriodicalIF":5.0,"publicationDate":"2025-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143834140","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":"Experimental evaluation of an advanced predictive control technique for variable-speed wind turbine systems","authors":"Farah Echiheb ,&nbsp;Btissam Majout ,&nbsp;Ismail EL Kafazi ,&nbsp;Badre Bossoufi ,&nbsp;Abdelhamid Rabhi ,&nbsp;Nicu Bizon ,&nbsp;Anton Zhilenkov ,&nbsp;Saleh Mobayen","doi":"10.1016/j.ijepes.2025.110668","DOIUrl":"10.1016/j.ijepes.2025.110668","url":null,"abstract":"<div><div>Wind energy control plays a crucial role in optimizing the performance of Doubly Fed Induction Generators (DFIGs) by maximizing power extraction while ensuring stable grid integration. To achieve this, a Maximum Power Point Tracking (MPPT) strategy is employed to determine the optimal mechanical speed and reference power, enabling efficient wind energy conversion. However, maintaining precise control over the active and reactive power exchange remains a challenge, especially under varying operating conditions. This paper presents an experimental study on the application of deadbeat predictive control to a DFIG-based wind energy system, integrating MPPT for optimal power tracking. The study, conducted using a DSPACE DS1104 test bench, includes the development of a comprehensive mathematical model, an analysis of the deadbeat control strategy, and its implementation in MATLAB/Simulink. Experimental validation demonstrates that the proposed control method achieves faster response time (0.0504 s), reduced Total Harmonic Distortion (THD) to 0.5 %, and enhanced robustness against parameter variations, ensuring both maximum power extraction and high-quality power injection into the grid. These results confirm the superiority of the MPPT-integrated deadbeat predictive control over conventional methods in terms of efficiency, power quality, and system stability. However, while this method shows promising results, its implementation in real-world, large-scale systems requires further investigation to address challenges such as grid stability under fluctuating conditions and the scalability of the control strategy. In terms of practical implications, the proposed control method offers potential for improving the performance and efficiency of DFIG-based wind energy systems, contributing to more sustainable and reliable energy production. The research also holds social implications by advancing renewable energy technologies, which are essential for reducing dependency on fossil fuels and mitigating the effects of climate change.</div></div>","PeriodicalId":50326,"journal":{"name":"International Journal of Electrical Power & Energy Systems","volume":"168 ","pages":""},"PeriodicalIF":5.0,"publicationDate":"2025-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143833423","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":"Optimal charging station placement of electric vehicles in the smart distribution network based on the mixed integer linear programming","authors":"Mehdi Veisi ,&nbsp;Hossein Naderian ,&nbsp;Mazaher Karimi","doi":"10.1016/j.ijepes.2025.110675","DOIUrl":"10.1016/j.ijepes.2025.110675","url":null,"abstract":"<div><div>This article discusses the optimal placement of electric vehicle charging stations in the distribution network. The proposed approach is an optimization problem with the objective function equal to minimizing the cost of building charging stations and energy costs. Inevitably, minimizing the voltage deviation from the desired (reference) value is also considered in the objective function. The constraints of this problem include the equations of power flow, the restrictions governing electric vehicles and charging stations, and the limitations of network indicators. The mentioned problem can be described as mixed integer nonlinear programming (MINLP). Nevertheless, the MINLP optimization problem tends to run very slowly when the dimension of the grid increases significantly, and that’s why it is unlikely that we obtain an absolute optimal solution. Consequently, a mixed integer linear programming (MILP) formulation that resembles the main problem is developed. Ultimately, a distribution network consisting of 69 buses is modeled in GAMS to evaluate the proposed formulation. In the proposed plan with the appropriate placement of electric vehicle charging stations, initially a favorable economic cost is obtained for the aforementioned stations. In the following, charging management at the aforementioned stations has caused the network operation status to improve. When EVs are absent, the maximum voltage drop is approximately 0.092p.u. and energy losses reach 2.08  MW. In contrast, with EVs present the voltage drop falls to about 0.037p.u. and energy losses drop to roughly 1.23  MW.</div></div>","PeriodicalId":50326,"journal":{"name":"International Journal of Electrical Power & Energy Systems","volume":"168 ","pages":"Article 110675"},"PeriodicalIF":5.0,"publicationDate":"2025-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143829107","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":"Type recognition and parameter identification of power quality disturbances using improved 1D-YOLO and multi-task learning","authors":"Luo Bin ,&nbsp;Wang Huifang ,&nbsp;Ma Yongji ,&nbsp;Chen Wentong ,&nbsp;Li Yiming ,&nbsp;Ni Xuming","doi":"10.1016/j.ijepes.2025.110681","DOIUrl":"10.1016/j.ijepes.2025.110681","url":null,"abstract":"<div><div>Accurate recognition and parameter identification of Power Quality Disturbances (PQDs) are crucial for effective disturbance management. This research presents a model built on an improved One-Dimensional You Only Look Once (1D-YOLO) framework, incorporating multi-task learning to unify three tasks: type recognition, time localization, and characteristic parameter identification. The proposed model utilizes a Path Aggregation Network (PANet) for advanced multi-scale feature fusion, while decoupled heads enable concurrent analysis of 10 PQD elements. The case study results indicate that the model achieves over 99.5% mean average precision and classification accuracy for both element-level and signal-level recognition tasks. Additionally, it precisely identifies starting-ending times, as well as key parameters, with multi-task learning further enhancing the performance of individual tasks.</div></div>","PeriodicalId":50326,"journal":{"name":"International Journal of Electrical Power & Energy Systems","volume":"168 ","pages":"Article 110681"},"PeriodicalIF":5.0,"publicationDate":"2025-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143829108","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":"An enhanced multi-objective reactive power dispatch for hybrid Wind-Solar power system using Archimedes optimization algorithm","authors":"Prisma Megantoro ,&nbsp;Syahirah Abd Halim ,&nbsp;Nor Azwan Mohamed Kamari ,&nbsp;Lilik Jamilatul Awalin ,&nbsp;Ramizi Mohamed ,&nbsp;Hazwani Mohd Rosli","doi":"10.1016/j.ijepes.2025.110676","DOIUrl":"10.1016/j.ijepes.2025.110676","url":null,"abstract":"<div><div>Optimal reactive power dispatch (ORPD) is essential for addressing power system challenges related to distributed generation (DG), particularly from renewable energy (RE) sources such as wind and solar. The intermittent nature and uncertainty of these energy sources, influenced by varying wind speeds and solar irradiation, complicate their integration into power systems. This paper proposes a solution to the ORPD problem in systems with RE-DG integration using the Archimedes Optimization Algorithm (AOA). The uncertainties of wind and solar power generation were modelled using Weibull and lognormal probability density functions (PDFs), respectively, and the optimization model was tested using a scenario-based method. The AOA was applied to the IEEE 57 bus system to minimize power loss, voltage deviation, and voltage stability index (VSI). The results demonstrated that AOA contributed to a 15.7% reduction in power loss, and an 83.9% enhancement in VSI compared to the base case. In the multi-objective optimization scenario, AOA achieved a 7.1% reduction in power loss, with an additional 11.6% improvement upon the integration of DGs. The performance of AOA was also compared with other metaheuristic algorithms, demonstrating superior results in terms of tracking accuracy and convergence speed. AOA outperformed the multi-objective ant lion optimization (MOALO) and the Levy-based Interior Search Algorithm (LISA) in terms of power loss reduction and voltage stability. AOA achieved a 1.83% lower power loss and a 29.67% lower VSI compared to MOALO. When compared to LISA, AOA achieved a 1.68% lower power loss, demonstrating its superior optimization capabilities. These findings confirm that AOA is a highly effective method for solving the ORPD problem, accounting for renewable energy uncertainties and improving overall system performance.</div></div>","PeriodicalId":50326,"journal":{"name":"International Journal of Electrical Power & Energy Systems","volume":"168 ","pages":"Article 110676"},"PeriodicalIF":5.0,"publicationDate":"2025-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143828159","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":"A generalisable agent-based model of residential electricity demand for load forecasting and demand response management","authors":"Baxter Lorenzo McIntosh Williams ,&nbsp;Daniel Gnoth ,&nbsp;R.J. Hooper ,&nbsp;J. Geoffrey Chase","doi":"10.1016/j.ijepes.2025.110671","DOIUrl":"10.1016/j.ijepes.2025.110671","url":null,"abstract":"<div><div>Electrification and increased uptake of intermittent renewable generation challenge power systems worldwide. These challenges increase with increasing renewable generation, such as in Aotearoa New Zealand. To address these challenges, Demand Response (DR) can reduce peak loads and balance demand with intermittent supply, extending network lifetimes and reducing greenhouse gas emissions. In Aotearoa New Zealand, residential demand is the largest contributor to peak loads and a key target for DR. However, residential demand is highly influenced by human behaviour. Current electricity demand models are typically deterministic or stochastic and do not capture behavioural dynamics, the understanding of which is crucial for successful DR. This research presents an agent-based model of residential electricity demand in low-voltage networks, which is built using high-level census data and thus generalisable to regions with similar available data. The model is constructed in MATLAB R2022b with sub-models for appliance use, space heating, and water heating, and validated with real electricity demand profiles from low-voltage distribution transformers in Aotearoa New Zealand and data from appliance use in homes around the country. By incorporating realistic behaviours and their variability, this model offers a platform for testing how human behaviour influences DR strategies and impacts human outcomes. Thus, it can inform and improve the design of DR programs based on program uptake and desired outcomes, leading to decreased network costs through increased resilience and energy security, and reduced greenhouse gas emissions through better utilisation of intermittent renewable generation.</div></div>","PeriodicalId":50326,"journal":{"name":"International Journal of Electrical Power & Energy Systems","volume":"168 ","pages":"Article 110671"},"PeriodicalIF":5.0,"publicationDate":"2025-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143823978","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":"Consensus control of multiple electric springs considering non-critical load electricity fairness in islanded microgrid","authors":"Fagen Yin ,&nbsp;Chun Wang","doi":"10.1016/j.ijepes.2025.110663","DOIUrl":"10.1016/j.ijepes.2025.110663","url":null,"abstract":"<div><div>Due to the uncertainty of renewable energy source (RES) generation, the islanded microgrid with RESs is prone to voltage and frequency fluctuations. The electric spring (ES) is an effective means to mitigate these fluctuations. However, a single ES may not be sufficient to ensure voltage stability for each node or support system frequency regulation. To address this issue, a consensus control strategy is proposed to coordinate multiple ESs participating in voltage control and frequency regulation. This strategy consists of three layers. The upper layer generates reference voltage and reference angular frequency for each node based on a consensus algorithm. The middle layer calculates d-axis and q-axis components of ES reference output voltage, subsequently synthesizing the reference output voltage of ES. The bottom layer utilizes adaptive sliding mode control to ensure actual output voltage of ES tracks the reference output voltage in real time. This strategy ensures the reactive power output ratio of each ES is equal and that there is consistency in the voltage deviation ratio of each NCL while achieving nodes voltage and system frequency stability.</div></div>","PeriodicalId":50326,"journal":{"name":"International Journal of Electrical Power & Energy Systems","volume":"168 ","pages":"Article 110663"},"PeriodicalIF":5.0,"publicationDate":"2025-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143821046","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":"A high-impedance fault location method for resonant grounded distribution networks based on transformer and few-shot learning","authors":"Bo Li ,&nbsp;Yunyao Tan ,&nbsp;Kai Liao ,&nbsp;Jianwei Yang ,&nbsp;Zhengyou He","doi":"10.1016/j.ijepes.2025.110649","DOIUrl":"10.1016/j.ijepes.2025.110649","url":null,"abstract":"<div><div>High-impedance faults (HIFs) in resonant grounded distribution networks have illegible fault features, which are difficult to accurately be located. Existing HIF location methods rely heavily on the HIF nonlinearity features rather than the deep laws, the performance and adaptability are invalid. This paper proposes a novel HIF location method based on Transformer and Few-Shot Learning (FSL) for the resonant grounded distribution network. A HIF location method is designed to identify the fault feeder accurately and adaptively, in which the improved Transformer-based HIF location model is constructed to explore deep properties of HIFs with high anti-interference ability. Specifically, the FSL is introduced to construct a HIF location migration structure, which can realize the new topology migration with high accuracy and fast training speed only needing a few fault data. This approach ensures strong accuracy and adaptability in various operational conditions and topologies, making it highly effective for practical applications. Finally, numerical simulations based on PSCAD/EMTDC were carried out, which reveals the accuracy and adaptability of the proposed HIF location method.</div></div>","PeriodicalId":50326,"journal":{"name":"International Journal of Electrical Power & Energy Systems","volume":"168 ","pages":"Article 110649"},"PeriodicalIF":5.0,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143817393","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}