International Journal of Electrical Power & Energy Systems最新文献_第2页

Enhanced insulator fault detection using optimized ensemble of deep learning models based on weighted boxes fusion 基于加权盒融合的深度学习模型优化集成增强绝缘子故障检测

IF 5 2区工程技术

International Journal of Electrical Power & Energy Systems Pub Date : 2025-04-26 DOI: 10.1016/j.ijepes.2025.110682

Stefano Frizzo Stefenon , Laio Oriel Seman , Gurmail Singh , Kin-Choong Yow

{"title":"Enhanced insulator fault detection using optimized ensemble of deep learning models based on weighted boxes fusion","authors":"Stefano Frizzo Stefenon , Laio Oriel Seman , Gurmail Singh , Kin-Choong Yow","doi":"10.1016/j.ijepes.2025.110682","DOIUrl":"10.1016/j.ijepes.2025.110682","url":null,"abstract":"<div><div>Fault identification in transmission line insulators is essential to keep the power system running. Using deep learning-based models combined with interpretative techniques can be an alternative to improve power grid inspections and increase their reliability. Based on that consideration, this paper proposes an optimized ensemble of deep learning models (OEDL) based on weighted boxes fusion (WBF), called OEDL-WBF, to enhance the fault detection of power grid insulators. The proposed model is hypertuned considering a tree-structured Parzen estimator (TPE), and interpretative results are provided using the eigenvector-based class activation map (Eigen-CAM) algorithm. The Eigen-CAM had better results than Grad-CAM, Activation-CAM, MaxActivation-CAM, and WeightedActivation-CAM. The multi-criteria optimization of the structure by TPE ensures that the appropriate hyperparameters of the you only look once (YOLO) model are used for object detection. With a mean average precision (mAP)@[0.5] of 0.9841 and mAP@[0.5:0.95] of 0.9722 the proposed OEDL-WBF outperforms other deep learning-based structures, such as YOLOv8, YOLOv9, YOLOv10, YOLOv11, and YOLOv12 in a benchmarking. The Eigen-CAM further helps to interpret the outcomes of the model.</div></div>","PeriodicalId":50326,"journal":{"name":"International Journal of Electrical Power & Energy Systems","volume":"168 ","pages":"Article 110682"},"PeriodicalIF":5.0,"publicationDate":"2025-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143874168","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}

引用次数: 0

Distribution network restoration with mobile resources dispatch: A simulation-based online dynamic programming approach 基于移动资源调度的配电网恢复：一种基于仿真的在线动态规划方法

IF 5 2区工程技术

International Journal of Electrical Power & Energy Systems Pub Date : 2025-04-26 DOI: 10.1016/j.ijepes.2025.110667

Mingxuan Li , Wei Wei , Yin Xu , Ying Wang , Shanshan Shi

{"title":"Distribution network restoration with mobile resources dispatch: A simulation-based online dynamic programming approach","authors":"Mingxuan Li , Wei Wei , Yin Xu , Ying Wang , Shanshan Shi","doi":"10.1016/j.ijepes.2025.110667","DOIUrl":"10.1016/j.ijepes.2025.110667","url":null,"abstract":"<div><div>Dispatching mobile resources such as repair crews and mobile emergency generators is essential for the rapid restoration of distribution systems after extreme events. However, the restoration process is affected by various uncertain factors including repair time, road condition, and newly observed failures, necessitating online decision-making in response to real-time information. This paper proposes a simulation-based online dynamic programming approach to provide real-time restoration actions considering the dispatch of mobile resources. Using an index-based priority rule as the base policy, the remaining cumulative loss at the current state and a given action is evaluated from online simulation. As the base policy is explicit, the simulation is efficient. Then, the action leading to the minimum cumulative loss is chosen. It is proven that such a strategy improves the performance of base policy. The proposed policy adapts to real-time information updates and does not rely on offline training, so incurs no data and convergence-related issues, which is important in restoration tasks where the historical data of extreme events is rare. The rolling optimization approach may not meet the requirement of online use, because routing mobile resources gives rise to large-scale discrete optimization problems. Case studies on 123-bus and 8500-bus systems demonstrate that the proposed method achieves higher efficiency and better performance compared with rolling horizon optimization.</div></div>","PeriodicalId":50326,"journal":{"name":"International Journal of Electrical Power & Energy Systems","volume":"168 ","pages":"Article 110667"},"PeriodicalIF":5.0,"publicationDate":"2025-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143874167","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}

引用次数: 0

Risk-averse operation of microgrids in distribution systems with price-responsive demands 具有价格响应需求的配电系统中微电网的风险规避操作

IF 5 2区工程技术

International Journal of Electrical Power & Energy Systems Pub Date : 2025-04-25 DOI: 10.1016/j.ijepes.2025.110581

Seyed Saeed Fazlhashemi , Mohammad E. Khodayar , Mostafa Sedighizadeh , Mahdi Khodayar

{"title":"Risk-averse operation of microgrids in distribution systems with price-responsive demands","authors":"Seyed Saeed Fazlhashemi , Mohammad E. Khodayar , Mostafa Sedighizadeh , Mahdi Khodayar","doi":"10.1016/j.ijepes.2025.110581","DOIUrl":"10.1016/j.ijepes.2025.110581","url":null,"abstract":"<div><div>This paper introduces a decentralized, risk-averse operational framework for interconnected, unbalanced microgrids and the distribution system. Distribution system operation is modeled as a risk-averse optimization problem using conditional value-at-risk measures to enhance robustness against uncertainties in price-responsive demand bids. Microgrid operations are structured as scenario-based robust optimization problems, capturing the worst-case scenarios for demand and solar PV generation. Non-convex energy management problems within the distribution system and microgrids are reformulated as convex optimization problems using the moment relaxation technique. A decentralized scheme addresses heterogeneous uncertainties in microgrids and the distribution system. The framework is applied to two case studies: a distribution system connected to two microgrids and a modified IEEE 123-bus distribution system connected to four microgrids. The risk-averse optimization solution is compared to that of a stochastic programming approach. For the IEEE 123-bus system, the results show that introducing risk aversion decreases social welfare by 44.63% compared to the risk-neutral solution but improves the conditional value-at-risk by 44.04%. Additionally, the impacts of dispatchable resources, including energy storage and distributed generation, on operation cost, phase balancing, and uncertainty control at the main feeder are examined. It is shown that incorporating a statistical distance metric to regulate power flow at the main feeder decreases social welfare by 6.48%.</div></div>","PeriodicalId":50326,"journal":{"name":"International Journal of Electrical Power & Energy Systems","volume":"168 ","pages":"Article 110581"},"PeriodicalIF":5.0,"publicationDate":"2025-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143869092","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}

引用次数: 0

Impact of phase shifting transformers on distance protection and fault ride-through scheme 移相变压器对距离保护和故障穿越方案的影响

IF 5 2区工程技术

International Journal of Electrical Power & Energy Systems Pub Date : 2025-04-24 DOI: 10.1016/j.ijepes.2025.110688

Tao Zheng , Jiaxu Yu , Xiaoxiao Liu , You Shen , Chengxi Sui

{"title":"Impact of phase shifting transformers on distance protection and fault ride-through scheme","authors":"Tao Zheng , Jiaxu Yu , Xiaoxiao Liu , You Shen , Chengxi Sui","doi":"10.1016/j.ijepes.2025.110688","DOIUrl":"10.1016/j.ijepes.2025.110688","url":null,"abstract":"<div><div>The phase shifting transformer (PST) serves as an important power flow control device that adjusts power flow by altering the phase of voltages at its terminals. This adjustment can affect the distance protection of lines equipped with PST, potentially leading to mal-operation of distance protection. To address this issue, this paper analyzes the impact of a PST on the calculated impedance of the distance relay and conducts a detailed analysis of the adaptability of distance protection in lines equipped with a PST, revealing that the phase shifting range is the primary factor affecting distance protection. The analysis indicates that the impact of small phase-shifting adjustments (within ± 10°) on distance protection is little, while large phase-shifting adjustments (beyond ± 10°) can lead to mal-operation. To deal with the challenges caused by large phase-shifting adjustments, a novel fault ride-through (FRT) scheme that employs an additional hardware loop is proposed in this paper. When a line fault is occurred, the additional hardware loop is triggered to ensure the quick isolation and safety of the PST. This FRT scheme guarantees that distance protection functions correctly, even during large phase-shifting adjustments. The effectiveness and feasibility of the proposed scheme are validated through simulations.</div></div>","PeriodicalId":50326,"journal":{"name":"International Journal of Electrical Power & Energy Systems","volume":"168 ","pages":"Article 110688"},"PeriodicalIF":5.0,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143863459","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}

引用次数: 0

Equivalent circuit model of grid-forming-converter based power grids: Visualizing control loop interactions on synchronization stability 基于并网变换器的电网等效电路模型：同步稳定性上控制回路相互作用的可视化

IF 5 2区工程技术

International Journal of Electrical Power & Energy Systems Pub Date : 2025-04-24 DOI: 10.1016/j.ijepes.2025.110692

Saizhao Yang , Rui Ma , Jinyu Wen , Shijie Cheng

{"title":"Equivalent circuit model of grid-forming-converter based power grids: Visualizing control loop interactions on synchronization stability","authors":"Saizhao Yang , Rui Ma , Jinyu Wen , Shijie Cheng","doi":"10.1016/j.ijepes.2025.110692","DOIUrl":"10.1016/j.ijepes.2025.110692","url":null,"abstract":"<div><div>For grid-forming (GFM) converter-based power grids, the impacts of AC voltage control (ACVC) loops on small-signal synchronization stability are rarely discussed in literature. To present the interactions between the synchronization control loop and the ACVC loop in an intuitive and clear approach, this paper establishes the equivalent circuit model of multi-GFM-converter based power systems, and analyzes the impacts of control loop interactions on small-signal synchronization stability. Firstly, the model of multi-GFM converter-based power grids has been established that incorporates the ACVC loop. Then, for the further visualization of control loop interactions, equivalent circuits of the whole systems are derived by the analogy-based method. This analysis allows us to assess the impacts of the ACVC on small-signal synchronization stability. This paper illustrates that ACVC can be equivalently represented as a negative impedance in parallel with the filter inductor. In this case, the ACVC brings about negative damping effects and deteriorates small-signal synchronization stability. Furthermore, the control parameters of the ACVC on small-signal synchronization stability are also quantitatively evaluated. Additionally, interactions between different GFM converters on small-signal synchronization stability are also investigated. Finally, the modified IEEE 10-GFM-converter 39-bus system is built in MATLAB/Simulink platform to validate analyzes and the proposed method.</div></div>","PeriodicalId":50326,"journal":{"name":"International Journal of Electrical Power & Energy Systems","volume":"168 ","pages":"Article 110692"},"PeriodicalIF":5.0,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143869048","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}

引用次数: 0

Debunking the speed-fidelity trade-off: Speeding-up large-scale energy models while keeping fidelity 推翻速度与保真度之间的权衡：在保持保真度的同时加快大规模能源模型的速度

IF 5 2区工程技术

International Journal of Electrical Power & Energy Systems Pub Date : 2025-04-24 DOI: 10.1016/j.ijepes.2025.110674

Diego A. Tejada-Arango , Juha Kiviluoma , Germán Morales-España

{"title":"Debunking the speed-fidelity trade-off: Speeding-up large-scale energy models while keeping fidelity","authors":"Diego A. Tejada-Arango , Juha Kiviluoma , Germán Morales-España","doi":"10.1016/j.ijepes.2025.110674","DOIUrl":"10.1016/j.ijepes.2025.110674","url":null,"abstract":"<div><div>Energy system models are essential for planning and supporting the energy transition. However, increasing temporal, spatial, and sectoral resolutions have led to large-scale linear programming (LP) models that are often (over)simplified to remain computationally tractable—frequently at the expense of model fidelity. This paper challenges the common belief that LP formulations cannot be improved without sacrificing their accuracy. Inspired by graph theory, we propose to model energy systems using <em>energy assets</em> (vertices), as a single building-block, and <em>flows</em> to connect between them. This reduces the need for additional components such as nodes and connections. The resulting formulation is more compact, without sacrificing accuracy, and leverages the inherent graph structure of energy systems. To evaluate performance, we implemented and compared four common modelling approaches varying in their use of building blocks and flow representations. We conducted experiments using TulipaEnergyModel.jl and applied them to a multi-sector case study with varying problem sizes. Results show that our single-building-block (1BB-1F) approach reduces variables and constraints by 26% and 35%, respectively, and achieves a 1.27x average speedup in solving time without any loss in model fidelity. The speedup increases with problem size, making this approach particularly advantageous for large-scale models. Our findings demonstrate that not all LPs are equal in quality and that better reformulations can lead to substantial computational benefits. This paper also aims to raise awareness of model quality considerations in energy system optimisation and promote more efficient formulations without compromising fidelity.</div></div>","PeriodicalId":50326,"journal":{"name":"International Journal of Electrical Power & Energy Systems","volume":"168 ","pages":"Article 110674"},"PeriodicalIF":5.0,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143869107","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}

引用次数: 0

Frequency control strategy of microgrid distributed virtual synchronous generator based on asynchronous event triggered communication protocol 基于异步事件触发通信协议的微电网分布式虚拟同步发电机频率控制策略

IF 5 2区工程技术

International Journal of Electrical Power & Energy Systems Pub Date : 2025-04-24 DOI: 10.1016/j.ijepes.2025.110666

HE Ping , ZHU Yongliang , TAO Yukun , LIU Xinyan , SHAO Jingjing

{"title":"Frequency control strategy of microgrid distributed virtual synchronous generator based on asynchronous event triggered communication protocol","authors":"HE Ping , ZHU Yongliang , TAO Yukun , LIU Xinyan , SHAO Jingjing","doi":"10.1016/j.ijepes.2025.110666","DOIUrl":"10.1016/j.ijepes.2025.110666","url":null,"abstract":"<div><div>Virtual Synchronous Generator (VSG) control technique is a potent solution to the issue of insufficient inertia in power systems. To address the challenges of low inertia and low output impedance in microgrids, this paper proposes a VSG frequency distributed collaborative secondary control strategy and develops a distributed active power sharing control strategy. Initially, considering the frequency parameter discrepancies among individual VSG, a tracking controller for the VSG frequency reference model is designed based on the heterogeneous multi-agent theory. Subsequently, to alleviate the communication overhead, an integral-type event triggering mechanism is constructed. This mechanism obviates the need for a time synchronization system in VSGs, allowing each unit to rely solely on its internal clock for periodic triggering condition assessments. In contrast to the existing VSG secondary control strategies, this approach ensures the efficacy of the distributed secondary control strategy amidst asynchronous communication networks. Furthermore, the stability of the proposed secondary control strategy is demonstrated using the Lyapunov function in conjunction with the event triggering mechanism. Ultimately, an island microgrid system is simulated on the MATLAB/simulink platform, and the simulation results verify the feasibility and effectiveness of the proposed control strategy.</div></div>","PeriodicalId":50326,"journal":{"name":"International Journal of Electrical Power & Energy Systems","volume":"168 ","pages":"Article 110666"},"PeriodicalIF":5.0,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143863460","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}

引用次数: 0

A non-intrusive load monitoring algorithm based on real-time feature extraction and deep learning model 一种基于实时特征提取和深度学习模型的非侵入式负荷监测算法

IF 5 2区工程技术

International Journal of Electrical Power & Energy Systems Pub Date : 2025-04-22 DOI: 10.1016/j.ijepes.2025.110637

Behrooz Taheri , Mostafa Sedighizadeh , Mohammad Reza Nasiri , Alireza Sheikhi Fini

{"title":"A non-intrusive load monitoring algorithm based on real-time feature extraction and deep learning model","authors":"Behrooz Taheri , Mostafa Sedighizadeh , Mohammad Reza Nasiri , Alireza Sheikhi Fini","doi":"10.1016/j.ijepes.2025.110637","DOIUrl":"10.1016/j.ijepes.2025.110637","url":null,"abstract":"<div><div>Researchers are increasingly interested in Non-intrusive Load Monitoring (NILM) as a cost-effective alternative to Intrusive Load Monitoring (ILM) for smart home energy monitoring. However, most NILM studies assume a fixed number of appliances and adjust classification models accordingly. This approach disregards the reality of varying appliance numbers in households, which can significantly impact model accuracy. To address this limitation, in this study, a comprehensive comparison between the proposed model and existing methods is conducted. The results show that the proposed model outperforms the existing methods on the UK-DALE and EMBED databases with an accuracy increase of 9.492% and 8.386%, respectively. Also, the accuracy of the proposed model has reached 99.74% compared to conventional methods, which shows its significant superiority over the lower accuracies of other models, including 95.11%, 92.09%, 88.70%, and 75.38%. This innovation combines a two-stage feature extraction method based on Soft Sifting Stopping Criterion Empirical Mode Decomposition (SSSC-EMD) and an adaptive deep learning model with architecture tuning capabilities, in order to improve the performance and accuracy of home appliance detection under different conditions.</div></div>","PeriodicalId":50326,"journal":{"name":"International Journal of Electrical Power & Energy Systems","volume":"168 ","pages":"Article 110637"},"PeriodicalIF":5.0,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143860329","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}

引用次数: 0

Robustness Enhanced control for Grid-Forming PMSG wind farm 并网PMSG风电场鲁棒增强控制

IF 5 2区工程技术

International Journal of Electrical Power & Energy Systems Pub Date : 2025-04-22 DOI: 10.1016/j.ijepes.2025.110679

Yun Wang , Chaoyang Long , Feilong Xie , Mingkun Liang , Qiuwei Wu , Senior Member, IEEE

{"title":"Robustness Enhanced control for Grid-Forming PMSG wind farm","authors":"Yun Wang , Chaoyang Long , Feilong Xie , Mingkun Liang , Qiuwei Wu , Senior Member, IEEE","doi":"10.1016/j.ijepes.2025.110679","DOIUrl":"10.1016/j.ijepes.2025.110679","url":null,"abstract":"<div><div>This paper studies the stability and control of the wind farm utilizing the permanent magnet synchronous generator (PMSG) with grid-forming control based on virtual synchronous generator (VSG) technology. It considers the uncertainties affecting the wind farm’s operation and proposes a robust grid-forming controller to improve stability. Firstly, a state-space model for the PMSG-VSG wind farm is established, incorporating uncertainties of wind speed, grid voltage variations, system control parameters, and short-circuit ratio (SCR) change. Secondly, eigenvalue and participation factor analyses reveal that excessive virtual inertia, insufficient virtual damping, high short-circuit ratios, and varying proportional-integral coefficients in the voltage control can degrade system stability and induce oscillations. Thirdly, a robust grid-forming controller is designed to enhance system stability and robustness in the presence of these uncertainties. The performance of the robust grid-forming controller is validated using an aggregation model of the PMSG-VSG wind farm. Compared with conventional grid-forming controller based on PI controller or additional damping controller, the proposed controller demonstrates superior capability to suppress system oscillations caused by grid voltage disturbances and control parameter uncertainties, thereby improving overall system robustness and stability.</div></div>","PeriodicalId":50326,"journal":{"name":"International Journal of Electrical Power & Energy Systems","volume":"168 ","pages":"Article 110679"},"PeriodicalIF":5.0,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143860328","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}

引用次数: 0

A data-physical fusion method for economic dispatch considering high renewable penetration and security constraints 考虑到高可再生能源渗透率和安全约束的经济调度数据物理融合方法

IF 5 2区工程技术

International Journal of Electrical Power & Energy Systems Pub Date : 2025-04-22 DOI: 10.1016/j.ijepes.2025.110691

Yuchen Dai , Wei Xu , Xiaokang Wu , Minghui Yan , Feng Xue , Jianfeng Zhao

{"title":"A data-physical fusion method for economic dispatch considering high renewable penetration and security constraints","authors":"Yuchen Dai , Wei Xu , Xiaokang Wu , Minghui Yan , Feng Xue , Jianfeng Zhao","doi":"10.1016/j.ijepes.2025.110691","DOIUrl":"10.1016/j.ijepes.2025.110691","url":null,"abstract":"<div><div>Economic dispatch plays a pivotal role in ensuring the safety and reliability of new power systems. Conventional model-based methods of economic dispatch encounter significant challenges due to the increasing uncertainties brought about by high renewable penetration. Reinforcement learning (RL) has shown great potential because it does not depend on probability distribution modelling of uncertainties. However, the disparity between training scenarios and real-world applications hinders the broader adoption of RL. To address these challenges, this paper presents a data-physical fusion method for economic dispatch considering high renewable penetration and security constraints. An invertible mapping is introduced in the action space of the Markov decision process model, comprising a balance layer and a reverse mapping. The invertible mapping can increase the exploration efficiency and guide the training quality of agents. Then, a physics-informed neural network based on the deep deterministic policy gradient algorithm is employed for fine-tuning and transfer learning. Physical models of unsatisfied constraints are integrated into the critic using Lagrange relaxation. The case studies demonstrate the superior performance of the proposed method in terms of both training speed and decision-making reliability compared to conventional data-driven methods. The fusion of physical models and neural networks enhances the interpretability of data-driven methods, thereby facilitating their broader application in new power systems.</div></div>","PeriodicalId":50326,"journal":{"name":"International Journal of Electrical Power & Energy Systems","volume":"168 ","pages":"Article 110691"},"PeriodicalIF":5.0,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143856046","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}

引用次数: 0