International Journal of Electrical Power & Energy Systems最新文献

{"title":"Explainable modeling for wind power forecasting: A Glass-Box model with high accuracy","authors":"Wenlong Liao ,&nbsp;Jiannong Fang ,&nbsp;Birgitte Bak-Jensen ,&nbsp;Guangchun Ruan ,&nbsp;Zhe Yang ,&nbsp;Fernando Porté-Agel","doi":"10.1016/j.ijepes.2025.110643","DOIUrl":"10.1016/j.ijepes.2025.110643","url":null,"abstract":"<div><div>Machine learning models (e.g., neural networks) achieve high accuracy in wind power forecasting, but they are usually regarded as black boxes that lack interpretability. To address this issue, the paper proposes a glass-box model that combines high accuracy with transparency for wind power forecasting. Specifically, the core is to sum up the feature effects by constructing shape functions, which effectively map the intricate non-linear relationships between wind power output and input features. Furthermore, the forecasting model is enriched by incorporating interaction terms that adeptly capture interdependencies and synergies among the input features. The additive nature of the proposed glass-box model ensures its interpretability. Simulation results show that the proposed glass-box model effectively interprets the results of wind power forecasting from both global and instance perspectives. Besides, it outperforms most benchmark models and exhibits comparable performance to the best-performing neural networks. This dual strength of transparency and high accuracy positions the proposed glass-box model as a compelling choice for reliable wind power forecasting.</div></div>","PeriodicalId":50326,"journal":{"name":"International Journal of Electrical Power & Energy Systems","volume":"167 ","pages":"Article 110643"},"PeriodicalIF":5.0,"publicationDate":"2025-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143735138","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}

{"title":"A source-load collaborative stochastic optimization method considering the electricity price uncertainty and industrial load peak regulation compensation benefit","authors":"Xiaoyu Yue ,&nbsp;Lijun Fu ,&nbsp;Siyang Liao ,&nbsp;Jian Xu ,&nbsp;Deping Ke ,&nbsp;Huiji Wang ,&nbsp;Shuaishuai Feng ,&nbsp;Jiaquan Yang ,&nbsp;Xuehao He","doi":"10.1016/j.ijepes.2025.110630","DOIUrl":"10.1016/j.ijepes.2025.110630","url":null,"abstract":"<div><div>Energy-intensive industrial load offers substantial capacity and rapid adjustment capabilities, which can be effectively coordinated with deep peak regulation (DPR) methods of thermal power to optimize the peak regulation state of the system. The uncertainty of electricity prices and the current peak regulation compensation mechanism significantly affect the economic viability of industrial load regulation. In this study, electrolytic aluminum load (EAL) is used as a representative industrial load. This paper combines the complete ensemble empirical mode decomposition adaptive noise (CEEMDAN), whale optimization algorithm (WOA), and long short-term memory network (LSTM) to propose a CEEMDAN-WOA-LSTM prediction model for electricity price scenarios. Subsequently, comprehensive cost and fine adjustment models for electrolytic aluminum load (EAL) are developed, incorporating the current peak regulation compensation mechanism. Finally, a source-load collaborative stochastic optimization method is proposed, integrating the scenario method and chance constraints. The effectiveness of the proposed scheme is verified using a real regional system, demonstrating significant reductions in total social peak regulation costs, a substantial decrease in renewable energy (RE) abandonment rates, reduced frequency of thermal power DPR, and improved economic efficiency of thermal power. Additionally, the current peak regulation compensation mechanism effectively guarantees the benefits of EAL and encourages its adjustment willingness.</div></div>","PeriodicalId":50326,"journal":{"name":"International Journal of Electrical Power & Energy Systems","volume":"167 ","pages":"Article 110630"},"PeriodicalIF":5.0,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143724973","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}

{"title":"Terminal sliding mode control with sensor reduction of a permanent magnet synchronous generator supplying a pumping system with battery storage","authors":"Clotaire Thierry Sanjong Dagang ,&nbsp;Mathieu Jean Pierre Pesdjock ,&nbsp;Godpromesse Kenné","doi":"10.1016/j.ijepes.2025.110609","DOIUrl":"10.1016/j.ijepes.2025.110609","url":null,"abstract":"<div><div>This work is concerned with the study and development of a terminal sliding mode control process that employs an estimator of the wind speed and the mechanical rotation speed of the permanent magnet synchronous generator (PMSG). This results in a reduction in the overall cost of the wind power system, which comprises a PMSG, a Pulse Width Modulation (PWM) rectifier, a battery, a DC–DC converter, a PWM inverter and a centrifugal pump driven by an asynchronous squirrel-cage machine. The wind power system is validated in the MATLAB Simulink numerical simulation environment. Subsequently, the results obtained are compared with those of a conventional sliding-mode control (with a tachometric sensor and an anemometric sensor) in order to ascertain the efficacy of the proposed control method in terms of trajectory tracking, energy consumption and the reliability of the proposed estimation algorithm. The simulation results demonstrate that the proposed approach is both robust and reliable. However, it should be noted that the settling time of the estimated quantities is greater than that of the same quantities when measured with the compared approach (conventional sliding mode control).</div></div>","PeriodicalId":50326,"journal":{"name":"International Journal of Electrical Power & Energy Systems","volume":"167 ","pages":"Article 110609"},"PeriodicalIF":5.0,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143714628","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}

{"title":"Efficient optimal power flow learning: A deep reinforcement learning with physics-driven critic model","authors":"Ahmed Sayed ,&nbsp;Khaled Al Jaafari ,&nbsp;Xian Zhang ,&nbsp;Hatem Zeineldin ,&nbsp;Ahmed Al-Durra ,&nbsp;Guibin Wang ,&nbsp;Ehab Elsaadany","doi":"10.1016/j.ijepes.2025.110621","DOIUrl":"10.1016/j.ijepes.2025.110621","url":null,"abstract":"<div><div>The transition to decarbonized energy systems presents significant operational challenges due to increased uncertainties and complex dynamics. Deep reinforcement learning (DRL) has emerged as a powerful tool for optimizing power system operations. However, most existing DRL approaches rely on approximated data-driven critic networks, requiring numerous risky interactions to explore the environment and often facing estimation errors. To address these limitations, this paper proposes an efficient DRL algorithm with a physics-driven critic model, namely a differentiable holomorphic embedding load flow model (D-HELM). This approach enables accurate policy gradient computation through a differentiable loss function based on system states of realized uncertainties, simplifying both the replay buffer and the learning process. By leveraging continuation power flow principles, D-HELM ensures operable, feasible solutions while accelerating gradient steps through simple matrix operations. Simulation results across various test systems demonstrate the computational superiority of the proposed approach, outperforming state-of-the-art DRL algorithms during training and model-based solvers in online operations. This work represents a potential breakthrough in real-time energy system operations, with extensions to security-constrained decision-making, voltage control, unit commitment, and multi-energy systems.</div></div>","PeriodicalId":50326,"journal":{"name":"International Journal of Electrical Power & Energy Systems","volume":"167 ","pages":"Article 110621"},"PeriodicalIF":5.0,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143706241","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}

{"title":"Distributed transmission-distribution coordinated voltage control: A bidirectional Anderson acceleration based master slave splitting approach","authors":"Zhenming Lu ,&nbsp;Zhongkai Yi ,&nbsp;Ying Xu ,&nbsp;Zhenghong Tu ,&nbsp;Zhimin Li ,&nbsp;Junfei Wu","doi":"10.1016/j.ijepes.2025.110625","DOIUrl":"10.1016/j.ijepes.2025.110625","url":null,"abstract":"<div><div>As the penetration of renewable energy increases, the voltages in power systems frequently change and fluctuate significantly. A tractable coordinated voltage control model for transmission and distribution systems is formulated to make efficient control decisions and realize distributed transmission-distribution coordinated voltage control, which avoids nonlinear and non-convex terms. Subsequently, using the data-driven bidirectional Anderson acceleration method, this study proposes an improved generalized master–slave-splitting method (G-MSSM), which is employed to solve the proposed coordinated voltage control model. Finally, the convergence index is introduced and derived with a rigid mathematical proof that can quantitatively evaluate the convergence efficiency of the proposed G-MSSM. Numerical simulations illustrate the effectiveness and scalability of the proposed approach in multiple scenarios with high-penetration renewable energy. The proposed approach achieves higher computational efficiency and better convergence performance than several representative approaches in the state-of-the-art literature.</div></div>","PeriodicalId":50326,"journal":{"name":"International Journal of Electrical Power & Energy Systems","volume":"167 ","pages":"Article 110625"},"PeriodicalIF":5.0,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143706240","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}

{"title":"Research on modeling and simulation of traction power supply system of guideway rubber-tires train","authors":"Haida Xu ,&nbsp;Liwei Zhang ,&nbsp;Jiapeng Wang ,&nbsp;Xu Wang","doi":"10.1016/j.ijepes.2025.110555","DOIUrl":"10.1016/j.ijepes.2025.110555","url":null,"abstract":"<div><div>Guideway rubber-tires system, also known as Rapid rubber-tires trail (RRT), is a new type of urban rail transit. The train uses rubber tires as running wheels and uses guide rails to achieve steering. The guideway rubber-tires train generally adopts the power supply mode of on-board energy storage and can operate in an unmanned way. Through the simulation research of traction power supply system of guideway rubber-tires train, it can provide important support data for system planning and design, economic benefit evaluation and safety performance monitoring. In this paper, the component model of traction power supply system of guideway rubber-tires train is established. According to the dynamic multi-train condition, the execution flow of AC-DC power flow calculation is proposed, the load simulation of traction power supply system is realized, and the calculation results are analyzed. On the basis of normal condition simulation, fault condition simulation is carried out. The simulation results mainly include the performance of key components in the traction power supply system, the simulation of the fault charging curve of the vehicle overcapacity, and the verification of the redundancy performance of the line. The results show that the simulation system can simulate the normal and fault conditions of the traction power supply system well, and the simulation results show that the traction power supply system of the line meets the design requirements.</div></div>","PeriodicalId":50326,"journal":{"name":"International Journal of Electrical Power & Energy Systems","volume":"167 ","pages":"Article 110555"},"PeriodicalIF":5.0,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143687049","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}

{"title":"Enhancing resilience of distribution system under extreme weather: Two-stage energy storage system configuration strategy based on robust optimization","authors":"Ye He ,&nbsp;Hongyun Fu ,&nbsp;Andrew Y. Wu ,&nbsp;Hongbin Wu ,&nbsp;Ming Ding","doi":"10.1016/j.ijepes.2025.110624","DOIUrl":"10.1016/j.ijepes.2025.110624","url":null,"abstract":"<div><div>Extreme natural disasters can easily cause large-scale power outages in distribution networks (DN), and energy storage system (ESS) contributes to an essential part of integrated solutions to this problem owing to its flexible regulation and rapid response characteristics. A two-stage robust optimization model for ESS that considers the resilience enhancement of a DN under extreme weather conditions is proposed. First, the impacts of secondary hazards on the component failure rates were quantified, and a time-varying matrix of distribution line failures was constructed. Second, an overall recovery index of the DN and an important load recovery index were proposed. Finally, a two-stage robust optimization model for the ESS is established to improve DN resilience with the objective of minimizing the comprehensive economic cost of the ESS and the annual comprehensive weighted load loss, which is solved using the column-and-constraint generation algorithm (C&amp;CG). Furthermore, numerous simulations were performed on the IEEE 33-node system, and it showed that the proposed method can not only ensure the optimal comprehensive economics of the ESS and fully tap the support potential of the ESS, but also maximize the resilience of the DN. Compared to the DN without energy storage system, the proposed method improves the overall resilience and important load recovery of the DN by about 15.9% and 4.3%, respectively.</div></div>","PeriodicalId":50326,"journal":{"name":"International Journal of Electrical Power & Energy Systems","volume":"167 ","pages":""},"PeriodicalIF":5.0,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143687051","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}

{"title":"Optimized multi-unit coordinated scheduling based on improved IGDT: Low-carbon scheduling research for the electric-heat-oxygen integrated energy system","authors":"Zhe Yin ,&nbsp;Zhifan Zhang ,&nbsp;Ruijin Zhu ,&nbsp;Yifan Zhang ,&nbsp;Jiyuan Wang ,&nbsp;Wenxing Tang","doi":"10.1016/j.ijepes.2025.110629","DOIUrl":"10.1016/j.ijepes.2025.110629","url":null,"abstract":"<div><div>To address the oxygen supply demands and the challenges posed by high penetration of renewable energy in high-altitude regions, this paper proposes a low-carbon scheduling model for an electric-heat-oxygen integrated energy system (EHO-IES), designed for energy dispatch and management in these areas. The model integrates carbon capture and storage with power-to-gas (CCS-P2G), concentrated solar power plant (CSPP), combined heat and power (CHP) unit, and ground-source heat pump (GSHP). By optimizing the coordinated operation of multiple energy sources, the model enhances their complementarity and interaction. To effectively manage the multiple uncertainties in renewable energy and load, this study introduces an improved information-gap decision theory (IGDT) model, referred to as EWNS-IGDT. This model combines the entropy weight method (EWM) and non-dominated sorting genetic algorithm II (NSGA-II), improving the objectivity and rationality of uncertainty weight settings in risk-averse strategy (RAS) and risk-seeking strategy (RSS). The paper further analyzes the impact of these strategies on low-carbon scheduling. Case study results show that the coordinated operation of multiple units significantly reduces total cost (by 89.93 %) and carbon trading cost (by 97.95 %), while achieving near-complete integration of photovoltaic (PV) and wind turbine (WT) output. Under the RAS, total cost increased by 20 %, and carbon trading cost rose by 90.06 %. In contrast, under the RSS, total cost decreased by 19.98 %, while carbon trading cost significantly dropped by 321.90 %.</div></div>","PeriodicalId":50326,"journal":{"name":"International Journal of Electrical Power & Energy Systems","volume":"167 ","pages":"Article 110629"},"PeriodicalIF":5.0,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143687050","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}

{"title":"Optimal control strategy on hybrid energy storage systems to improve system inertia for a bipolar DC microgrid","authors":"Yuechao Ma ,&nbsp;Guangchen Liu ,&nbsp;Hongbin Hu ,&nbsp;Jun Tao ,&nbsp;Yu Xu","doi":"10.1016/j.ijepes.2025.110628","DOIUrl":"10.1016/j.ijepes.2025.110628","url":null,"abstract":"<div><div>For an islanded bipolar DC microgrid with positive and negative hybrid energy storage systems (HESSs), researchers need to take into account a special problem related to improving the system inertia by the HESSs. To solve this issue, an optimization control strategy for multiple HESSs is proposed. The strategy includes a battery and a supercapacitor (SC) for each HESS, with inertia improvement for the SCs. Specifically, to effectively improve the system inertia, a dynamic power distribution strategy is proposed for solving the unreasonable power distribution problem on positive and negative SCs caused by the asymmetric load power on the positive and negative systems. Subsequently, to improve the system inertia at the right time, 2 operating-state discriminators, one working as an output discriminator and the other as a recovery discriminator, are introduced for each SC. These discriminators are employed for avoiding the influence of SCs on the state-of-charge balancing on the positive and negative batteries and to control the output and recovery actions of the SCs. Based on the 2 operating-state discriminators, 2 virtual DC generators (VDCGs) are introduced into the output paths of the SCs for improving the positive and negative system inertia when the output signals of the operating-state discriminators are activated. Furthermore, to improve the entire system inertia in a bipolar DC microgrid and solve the paradox between the inertia improvement and the lag in the dynamic response speed, a particle swarm algorithm is adopted to joint optimize the parameters of the 2 VDCGs. Finally, to make the SCs output power and improve system inertia repeatedly, 2 time-varying virtual inductors are introduced into the recovery paths of the SCs for accelerating the recovery speed of terminal voltages for SCs when the recovery signals of the operating-state discriminators are activated. The simulation results in different working conditions reveal that the proposed control strategy helps in obtaining reasonable output powers of the positive and negative HESSs, improving the system inertia, ensuring the reliable operation of the SCs, and achieving the optimal operation of the system. Therefore, the accuracy and effectiveness of the proposed control strategy were verified.</div></div>","PeriodicalId":50326,"journal":{"name":"International Journal of Electrical Power & Energy Systems","volume":"167 ","pages":"Article 110628"},"PeriodicalIF":5.0,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143688028","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}

{"title":"Online Neural Dynamics Forecasting for power system security","authors":"Mert Karacelebi,&nbsp;Jochen L. Cremer","doi":"10.1016/j.ijepes.2025.110566","DOIUrl":"10.1016/j.ijepes.2025.110566","url":null,"abstract":"<div><div>The increase in variable renewable energy sources has brought about significant changes in power system dynamics, mainly due to the widespread adoption of power electronics and nonlinear controllers. The resulting complex system dynamics and the unpredictable nature of disturbances pose substantial challenges for real-time dynamic security assessment (DSA). Machine learning (ML) methods offer advantages in terms of computational speed compared to numerical methods and simulators. Offline-trained ML models, however, are limited by their training domain; e.g., they cannot easily consider various grid topologies and data changes. Neural Ordinary Differential Equations (NODEs) leverage the integration of neural networks and ODE solvers to enable continuous-time dynamic trajectory predictions from time series data, resolving the limitation on topological and data changes. This paper introduces the Online Neural Dynamics Forecaster (ONDF) workflow, designed to monitor and assess system security in real-time using multiple NODEs trained solely with local post-fault measurements. Through several case studies, we compare the regression and DSA classification capabilities of ONDF with various ML models. Our findings demonstrate that ONDF provides a novel and scalable approach for system operators to make informed decisions and apply corrective control actions based on predicted dynamics.</div></div>","PeriodicalId":50326,"journal":{"name":"International Journal of Electrical Power & Energy Systems","volume":"167 ","pages":"Article 110566"},"PeriodicalIF":5.0,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143687045","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}