Electric Power Systems Research最新文献_第9页

Dynamic state estimation for distribution networks with photovoltaic power forecasting based on long short-term memory 基于长短期记忆的光伏发电预测配电网动态估计

IF 3.3 3区工程技术

Electric Power Systems Research Pub Date : 2025-04-21 DOI: 10.1016/j.epsr.2025.111712

Guisheng Xiao , Liang Ji , Xiao Chang , Huiqiang Zhi , Qiteng Hong , Chizhou Jin , Zhenkun Li , Botong Li

{"title":"Dynamic state estimation for distribution networks with photovoltaic power forecasting based on long short-term memory","authors":"Guisheng Xiao , Liang Ji , Xiao Chang , Huiqiang Zhi , Qiteng Hong , Chizhou Jin , Zhenkun Li , Botong Li","doi":"10.1016/j.epsr.2025.111712","DOIUrl":"10.1016/j.epsr.2025.111712","url":null,"abstract":"<div><div>With the large-scale integration of renewable energy, the accuracy and dependability of the dynamic state estimation for modern distribution networks might be compromised by the uncertainty and fluctuation of renewable sources. To address these challenges, the paper proposed a new dynamic state estimation method based on Long Short-Term Memory instead of traditional Kalman Filter method. The proposed method exhibits promising accuracy with less time-cost by mitigating the negative influences of uncertainty and fluctuation brought by PV, all the while requiring limited measurements. In the paper, an improved photovoltaic power forecasting method was firstly introduced. The distribution network model considering PV forecasting effect was established by through the application of LSTM. Then, a dynamic state estimation method was developed based on established distribution network model. To prove the effectiveness of the method, the real time simulations based on RTDS platform and comparisons with traditional method were conducted.</div></div>","PeriodicalId":50547,"journal":{"name":"Electric Power Systems Research","volume":"246 ","pages":"Article 111712"},"PeriodicalIF":3.3,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143854758","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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

Integrated maintenance scheduling for generators and transmission lines considering renewable energy sources and energy storages 考虑可再生能源和储能的发电机和输电线路的综合维护调度

IF 3.3 3区工程技术

Electric Power Systems Research Pub Date : 2025-04-21 DOI: 10.1016/j.epsr.2025.111696

Vincent F. Yu, Quyen Vo Nguyen Truc, Nguyen Ngoc Minh

{"title":"Integrated maintenance scheduling for generators and transmission lines considering renewable energy sources and energy storages","authors":"Vincent F. Yu, Quyen Vo Nguyen Truc, Nguyen Ngoc Minh","doi":"10.1016/j.epsr.2025.111696","DOIUrl":"10.1016/j.epsr.2025.111696","url":null,"abstract":"<div><div>An efficient and reliable energy system is imperative to meet the escalating energy demand, address environmental issues, and accommodate technological advancements. This study aims to develop optimal strategies for integrated maintenance scheduling (IMS) in energy systems, considering factors such as generating units, transmission networks, and power flow constraints. The proposed maintenance strategy incorporates a scenario-based model to account for the uncertainty in power generation from renewable sources, validated using a realistic dataset from Taiwan. This dataset includes wind speed records from offshore wind farms and solar radiation records with photovoltaic module specifications. Additionally, energy storage (ES) is integrated to mitigate potential energy deficits during peak load periods or maintenance outages. The primary objective is to minimize total operational and maintenance costs, and energy not supplied (ENS), while adhering to safety and reliability regulations. A mixed nonlinear integer programming model is formulated for the IMS problem. The BARON solver is used to solve small-scale problems, while a genetic algorithm-based matheuristic is developed to solve large-scale problems. The results demonstrate that the proposed algorithm improves solving efficiency while reducing computational time. Additionally, integrating the ES system reduces ENS and positively impacts system costs.</div></div>","PeriodicalId":50547,"journal":{"name":"Electric Power Systems Research","volume":"246 ","pages":"Article 111696"},"PeriodicalIF":3.3,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143851617","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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

Co-planning of network-load-storage to enhance the power-balancing capability of active distribution networks 协同规划电网负荷存储，增强有源配电网的功率均衡能力

IF 3.3 3区工程技术

Electric Power Systems Research Pub Date : 2025-04-21 DOI: 10.1016/j.epsr.2025.111723

Bo Tang , Qinlin Shi , Yitong Chen , Xiaoli Zhao , Peng Yang , Xin Lai , S.M. Muyeen

{"title":"Co-planning of network-load-storage to enhance the power-balancing capability of active distribution networks","authors":"Bo Tang , Qinlin Shi , Yitong Chen , Xiaoli Zhao , Peng Yang , Xin Lai , S.M. Muyeen","doi":"10.1016/j.epsr.2025.111723","DOIUrl":"10.1016/j.epsr.2025.111723","url":null,"abstract":"<div><div>With the large-scale DGs and FLs plug-in, the power supply and demand in different areas are becoming increasingly divergent. This phenomenon highlights the need to enhance consideration of power balance in the planning and operation of distribution networks. This paper presents a co-planning approach called the NLS method based on the grid pattern of China's distribution network. It extends the control of individual resources to a co-planning of three resources, aiming to achieve optimal power balance and economic objectives. Firstly, to address the uncertainty of source-load, a WGAN algorithm based on SDPA is proposed, which improves the quality of generated scenarios by setting weights to the input-output power matching degree. Secondly, a BZ partitioning index is constructed based on source-load and electrical characteristics, and the SPTV-improved GA is used to achieve optimal partitioning of the distribution network, reducing the configuration cost of active resources by 81 %. Finally, a dual-layer model of DR-ESS is established, with DR prioritized and ESS as auxiliary, to achieve the collaborative optimization of both, improving the DG absorption rate by over 10 %. A GDN in Zhejiang, China, is taken as an example for case analysis. The results show that the proposed NLS co-planning method reduces the daily operating cost of the distribution network, improves DG absorption by 38 %, and decreases the supply-demand imbalance by 63 %. It demonstrates the scientific validity and effectiveness of the method in improving the source-load balance of the distribution network.</div></div>","PeriodicalId":50547,"journal":{"name":"Electric Power Systems Research","volume":"246 ","pages":"Article 111723"},"PeriodicalIF":3.3,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143854757","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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

Enhancing peak electricity demand forecasting for commercial buildings using novel LSTM loss functions 利用新型 LSTM 损失函数加强商业建筑高峰电力需求预测

IF 3.3 3区工程技术

Electric Power Systems Research Pub Date : 2025-04-19 DOI: 10.1016/j.epsr.2025.111722

Heidi S. Nygård , Sigurd Grøtan , Kjersti Rustad Kvisberg , Leonardo Rydin Gorjão , Thomas Martinsen

{"title":"Enhancing peak electricity demand forecasting for commercial buildings using novel LSTM loss functions","authors":"Heidi S. Nygård , Sigurd Grøtan , Kjersti Rustad Kvisberg , Leonardo Rydin Gorjão , Thomas Martinsen","doi":"10.1016/j.epsr.2025.111722","DOIUrl":"10.1016/j.epsr.2025.111722","url":null,"abstract":"<div><div>The increasing integration of variable renewable energy necessitates new measures for grid balancing and cost optimization. Consumers can contribute through demand response, provided accurate predictions, particularly during peak periods. This study aims to enhance electricity demand forecasting using a Long Short-Term Memory (LSTM) neural network with two novel loss functions: Weighted Mean Squared Error (WMSE) and Negative Log Likelihood (NLL). WMSE emphasizes high-demand periods, while NLL captures prediction uncertainty. The model, trained on two years of hourly data for Oslo Airport Gardermoen (Norway), incorporates temporal features, historical demand, passenger numbers, and outdoor air temperature. Optimal model architecture is determined through grid search and cross-validation. Results reveal that top-performing model configurations have minimal architecture, suggesting that a simple model is sufficient for capturing temporal and seasonal demand variations. Models trained with WMSE and NLL demonstrate reliable peak predictions and valuable uncertainty estimations, with the top performing model achieving a Mean Absolute Percentage Error (MAPE) of 5.54 ± 1.00 %. Visual inspections confirm reproducible daily demand patterns, including characteristic dual peaks and weekday-weekend distinctions. This research demonstrates that LSTM models are effective and easy to use for electricity demand forecasts, empowering consumers in making informed decisions about flexibility management and demand response strategies.</div></div>","PeriodicalId":50547,"journal":{"name":"Electric Power Systems Research","volume":"246 ","pages":"Article 111722"},"PeriodicalIF":3.3,"publicationDate":"2025-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143848007","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 risk-based scheduling optimization strategy with explainability enhanced multi-scenario photovoltaic forecasting 基于风险的可解释性增强多场景光伏预测调度优化策略

IF 3.3 3区工程技术

Electric Power Systems Research Pub Date : 2025-04-19 DOI: 10.1016/j.epsr.2025.111729

Haiteng Han, Xiangchen Jiang, Simin Zhang, Chen Wu, Shuyu Cao, Haixiang Zang, Guoqiang Sun, Zhinong Wei

{"title":"A risk-based scheduling optimization strategy with explainability enhanced multi-scenario photovoltaic forecasting","authors":"Haiteng Han, Xiangchen Jiang, Simin Zhang, Chen Wu, Shuyu Cao, Haixiang Zang, Guoqiang Sun, Zhinong Wei","doi":"10.1016/j.epsr.2025.111729","DOIUrl":"10.1016/j.epsr.2025.111729","url":null,"abstract":"<div><div>Photovoltaic (PV) power generation, as a crucial technology for addressing energy transition and climate change, is increasingly becoming essential for power systems. However, its inherent randomness and uncertainty challenge stable operation and economic efficiency. To address these, this paper proposes a risk-based scheduling optimization strategy with explainable multi-scenario photovoltaic forecasting to mitigate these uncertainties. First, by employing an enhanced Copula function and ISODATA clustering, multiple joint output scenarios are generated to capture PV uncertainty. Building on this, a Stacking regression model is utilized to improve forecasting accuracy, while Shapley Additive Explanations (SHAP) explainability analysis is incorporated to enhance the transparency and decision-making of the model. Furthermore, to optimize the dispatch strategy for PV generation, this paper introduces the GlueVaR risk measurement method, which combines the benefits of Value at Risk (VaR) and Conditional Value at Risk (CVaR), thereby refining risk management and increasing the reliability of decision-making. Case studies demonstrate that the proposed strategy enhances PV forecasting reliability, with the R² reaching 0.86, and improves model explainability through SHAP-based analysis. In addition, the GlueVaR-based risk scheduling reduces potential risk by approximately 6 %, while maintaining a balance between power system economy and stability.</div></div>","PeriodicalId":50547,"journal":{"name":"Electric Power Systems Research","volume":"246 ","pages":"Article 111729"},"PeriodicalIF":3.3,"publicationDate":"2025-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143848008","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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

Analysis of high-ampacity and low-sag conductors of 275 kV overhead transmission lines using reconductoring technique 275 kV架空输电线路高容低凹陷导线重导技术分析

IF 3.3 3区工程技术

Electric Power Systems Research Pub Date : 2025-04-19 DOI: 10.1016/j.epsr.2025.111719

Matiullah Ahsan , Md Nor Ramdon Baharom , Ihsan Ullah Khalil , Zainab Zainal

引用次数: 0

An improved dynamic model for overcurrent relays in protection of electrical networks: Addressing two-level fault currents 电网保护中过流继电器的改进动态模型：处理两级故障电流

IF 3.3 3区工程技术

Electric Power Systems Research Pub Date : 2025-04-18 DOI: 10.1016/j.epsr.2025.111713

Salar Rashaei, Amin Yazdaninejadi

{"title":"An improved dynamic model for overcurrent relays in protection of electrical networks: Addressing two-level fault currents","authors":"Salar Rashaei, Amin Yazdaninejadi","doi":"10.1016/j.epsr.2025.111713","DOIUrl":"10.1016/j.epsr.2025.111713","url":null,"abstract":"<div><div>The paper aims to enhance the dynamic model of directional overcurrent relays (DOCRs), ensuring that it satisfies selectivity constraints not only for two-level faults but also for faults with resistance. To this end, a new scaling factor is introduced and integrated with the coefficient of fault current in the relay model which virtually increases the fault currents seen by the corresponding DOCR. In the proposed approach, this scaling factor is considered as an optimization variable and individual setting for the DOCR to create a proper distinction between fault currents and load currents. By doing so, this new variable facilitates the optimal relay coordination within a new framework that results in meeting selectivity constraints and reducing the relays operation times. However, the integration of this scaling factor alongside the coefficient of fault current in the model of relays may leads to unintentional tripping during normal conditions. Therefore, through an innovative modification in the logic of the DOCR, this challenge is addressed. Since the developed logic necessitates the use of numerical relays, the associated costs of replacing traditional relays with numerical ones should be taken into account. Therefore, the proposed coordination scheme is subsequently extended through a techno-economic model and the gray relational analysis (GRA) algorithm is employed to navigate the complex decision-making process from the Pareto front. The results demonstrate that replacing 25 % of the relays with numeric ones can satisfy selectivity requirements even in the presence of fault resistance, while the overall operation times of primary and backup relays can be reduced dramatically by up to 65 %. The proposed is tested not only on the IEEE 14-bus distribution network but also on the 30-bus network, validating its applicability across larger systems.</div></div>","PeriodicalId":50547,"journal":{"name":"Electric Power Systems Research","volume":"246 ","pages":"Article 111713"},"PeriodicalIF":3.3,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143843736","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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

Adaptive fault identification for multi-level relays using fault tree and user-defined inverse-time characteristics equation 基于故障树和自定义逆时特征方程的多级继电器自适应故障识别

IF 3.3 3区工程技术

Electric Power Systems Research Pub Date : 2025-04-18 DOI: 10.1016/j.epsr.2025.111672

Nana Chang , Guobing Song , Jiaheng Jiang

{"title":"Adaptive fault identification for multi-level relays using fault tree and user-defined inverse-time characteristics equation","authors":"Nana Chang , Guobing Song , Jiaheng Jiang","doi":"10.1016/j.epsr.2025.111672","DOIUrl":"10.1016/j.epsr.2025.111672","url":null,"abstract":"<div><div>The traditional inverse-time overcurrent (ITOC) protection setting method relies on a fixed topology, and the setting workload in large-scale networks is very large and difficult to adapt to topology changes. An adaptive fault identification (AFI) scheme is proposed, which is applicable to ring or large networks, and does not require prior knowledge of the primary/backup coordination relationships between relays or the stepwise setting of inverse-time characteristic parameters. First, the positive sequence fault component voltages (PSFCVs) with natural distribution characteristics is analyzed. By utilizing the communication channels in existing wide-area protection systems (WAPS), only the protection action signal (PAS) of primary protection is transmitted, generating a fault tree that automatically reflects the relationship between each relay and the fault point. Secondly, a user-defined inverse-time characteristic equation (ITCE) and an online adaptive method for setting parameters are provided. The calculated tripping time depends solely on the parameters of the individual lines. Finally, an IEEE 30-bus test system is built in PSCAD/EMTDC to verify the effectiveness of the proposed scheme under different network topologies and when distributed generation (DG) is connected.</div></div>","PeriodicalId":50547,"journal":{"name":"Electric Power Systems Research","volume":"246 ","pages":"Article 111672"},"PeriodicalIF":3.3,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143843735","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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

Withdrawal notice to: “Iterative Matrix Fitting Approach of Frequency Dependent Matrices based on Vector Fitting” [Electric Power Systems Research 243 (2025) 111499] 撤销公告：“基于矢量拟合的频率相关矩阵迭代矩阵拟合方法”[电力系统研究243 (2025)111499]

IF 3.3 3区工程技术

Electric Power Systems Research Pub Date : 2025-04-18 DOI: 10.1016/j.epsr.2025.111718

E.S. Bañuelos-Cabral , J.A. Gutiérrez-Robles , J.J. Nuño-Ayón , M.G. Vega-Grijalva , J.L. Naredo , J. Sotelo-Castañón

引用次数: 0

A load forecasting method based on heterogeneous network for integrated electricity and heat systems 基于异构网络的电热一体化系统负荷预测方法

IF 3.3 3区工程技术

Electric Power Systems Research Pub Date : 2025-04-18 DOI: 10.1016/j.epsr.2025.111725

Bohan Li, Xueping Li, Yao Cai, Qi Han

{"title":"A load forecasting method based on heterogeneous network for integrated electricity and heat systems","authors":"Bohan Li, Xueping Li, Yao Cai, Qi Han","doi":"10.1016/j.epsr.2025.111725","DOIUrl":"10.1016/j.epsr.2025.111725","url":null,"abstract":"<div><div>Accurate load forecasting in Integrated Electricity and Heat Systems (IEHS) is crucial for optimizing energy utilization and ensuring system stability. However, existing models struggle to capture the complex interdependencies between electricity and heat networks, leading to suboptimal predictions, particularly at coupling nodes. This study proposes a Heterogeneous Graph Attention Network-Gated Recurrent Unit (HAN-GRU) model within a Heterogeneous Network (HetNet) framework to enhance forecasting accuracy. By leveraging node-level and semantic-level attention mechanisms, HAN-GRU effectively integrates heterogeneous spatial dependencies and temporal correlations, prioritizing critical coupling nodes and optimizing information aggregation. The proposed model is validated on the Bali integrated energy system, as well as a 23-node radial heating network coupled with IEEE 33-bus and IEEE 118-bus power distribution networks. Simulation results demonstrate that HAN-GRU significantly outperforms baseline models in both accuracy and efficiency, highlighting its potential as a scalable and interpretable solution for multi-energy system forecasting.</div></div>","PeriodicalId":50547,"journal":{"name":"Electric Power Systems Research","volume":"246 ","pages":"Article 111725"},"PeriodicalIF":3.3,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143843737","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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