Sustainable Energy Grids & Networks最新文献_第5页

Machine learning approaches for the prediction of public EV charge point flexibility

IF 4.8 2区工程技术

Sustainable Energy Grids & Networks Pub Date : 2025-02-24 DOI: 10.1016/j.segan.2025.101657

Federica Bellizio , Bart Dijkstra , Angelika Fertig , Jules Van Dijk , Philipp Heer

{"title":"Machine learning approaches for the prediction of public EV charge point flexibility","authors":"Federica Bellizio , Bart Dijkstra , Angelika Fertig , Jules Van Dijk , Philipp Heer","doi":"10.1016/j.segan.2025.101657","DOIUrl":"10.1016/j.segan.2025.101657","url":null,"abstract":"<div><div>The increasing number of electric vehicles on the road can play a key role as a source of flexibility for a reliable power system operation. Charge point operators, in particular, can adjust individual electric vehicle charging loads to provide system operators with aggregated energy flexibility, e.g. for congestion management, ancillary services or greenhouse gas emission reduction. However, managing individual charging sessions requires information about the expected session duration and energy demand, which are not available at the beginning of a session. In this work, a novel predictive workflow based on two causality-informed machine learning approaches with different levels of generalization is proposed to predict individual session duration and energy demand. Our key contributions include the development of a cluster-based predictive model for charge points and a user-based predictive model to capture individual charging behaviours, and the comparison of these models using a large-scale, real-world dataset. The proposed approaches were tested on real charging data provided by TotalEnergies, showing that considering user-specific charging behaviours enhances the accuracy performance by 16.1% and 37.9% for predictions of session duration and energy demand, respectively. By leveraging clustering and feature selection techniques, accounting for charge point- and user-specific charging patterns, and utilizing a large-scale real-world charging dataset, the proposed predictive workflow enables a comprehensive comparison of machine learning techniques in terms of accuracy performance when predicting public electric vehicle charge point flexibility.</div></div>","PeriodicalId":56142,"journal":{"name":"Sustainable Energy Grids & Networks","volume":"42 ","pages":"Article 101657"},"PeriodicalIF":4.8,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143577721","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}

引用次数: 0

Congestion-aware multi-objective scheduling and control for a user-centered EV charging hub

IF 4.8 2区工程技术

Sustainable Energy Grids & Networks Pub Date : 2025-02-24 DOI: 10.1016/j.segan.2025.101656

Bart Nijenhuis, Gerwin Hoogsteen, Johann L. Hurink

{"title":"Congestion-aware multi-objective scheduling and control for a user-centered EV charging hub","authors":"Bart Nijenhuis, Gerwin Hoogsteen, Johann L. Hurink","doi":"10.1016/j.segan.2025.101656","DOIUrl":"10.1016/j.segan.2025.101656","url":null,"abstract":"<div><div>This paper presents a congestion-aware Energy Management System (EMS) for Electric Vehicle (EV) charging hubs with on-site PV generation and energy storage in the built environment. The concept of the system is based on a time-discretized scheduling approach that incorporates all relevant assets at the hub to charge the EVs without creating grid congestion problems. Since EV charging schedules in general have to be determined based on incomplete and often inaccurate forecasts and information, the scheduler is combined with an online control policy that operates to compensate for forecast errors or that can be used to react on external market price signals or congestion information. A simulation study of the scheduling concept and its underlying model shows that incorporating the current peak-tariff structure used in the Netherlands into the EMS can contribute to reducing the peak demand on the grid throughout the year for the proposed charging hub by 8.4%. The simulations furthermore show that the application of a peak shaving approach can lead to a peak load reduction of up to 36%, at only a 2.6% increase in total operational costs. The research objective of this study is to investigate how the theoretical model of the EMS can be applied in a real-world implementation. For this, the EMS is implemented in a real-life operational demonstration of the concept with real devices, data and users. The demonstration of the EMS in a real-world implementation advances the state of knowledge on these topics by demonstrating conflicting interests the lack of information-exchange between different stakeholders and the effect of this on the EV charging ecosystem. Further research is necessary, specifically on the interaction between EVs, Charge Point Operators, Mobility Service Providers and other relevant market parties such as energy traders.</div></div>","PeriodicalId":56142,"journal":{"name":"Sustainable Energy Grids & Networks","volume":"42 ","pages":"Article 101656"},"PeriodicalIF":4.8,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143520401","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}

引用次数: 0

Modelling the influence of atmospheric conditions represented by wind, precipitation and air temperature on the intensity of failure and restoration time of medium-voltage power lines

IF 4.8 2区工程技术

Sustainable Energy Grids & Networks Pub Date : 2025-02-24 DOI: 10.1016/j.segan.2025.101652

Andrzej Ł. Chojnacki

引用次数: 0

A fully adaptive distributionally robust multistage framework based on mixed decision rules for wind-thermal system operation under uncertainty 基于混合决策规则的完全自适应分布式稳健多阶段框架，用于不确定条件下的风热系统运行

IF 4.8 2区工程技术

Sustainable Energy Grids & Networks Pub Date : 2025-02-21 DOI: 10.1016/j.segan.2025.101664

Ying Yang , Linfeng Yang , Xinwei Shen , Zhaoyang Dong

{"title":"A fully adaptive distributionally robust multistage framework based on mixed decision rules for wind-thermal system operation under uncertainty","authors":"Ying Yang , Linfeng Yang , Xinwei Shen , Zhaoyang Dong","doi":"10.1016/j.segan.2025.101664","DOIUrl":"10.1016/j.segan.2025.101664","url":null,"abstract":"<div><div>The growing integration of renewable energy into power systems offers opportunities for achieving low-cost and sustainable energy supplies. However, its intermittency poses technical challenges, necessitating flexible and reliable decision-making methods. This study aims to develop a framework to enhance the integration of wind power while ensuring system reliability and minimizing costs. A fully adaptive distributionally robust multistage framework is proposed, leveraging mixed decision rules to enable dynamic and efficient use of quick-start units and generation dispatch. The improved mixed decision rules expand the feasible region and handle higher dimensional variables, are first introduced in such problem. Advanced optimization techniques are employed to reformulate the framework into mixed integer linear programming, ensuring computational tractability. The introduction of improved mixed decision rules with distributionally robust optimization and the solvable reformulation of the framework highlight the novelty of this work. Case studies on IEEE test systems demonstrate the framework’s superiority over traditional models by increasing wind power penetration, reducing fossil fuel consumption, and providing feasible and optimal solutions in uncertain environments.</div></div>","PeriodicalId":56142,"journal":{"name":"Sustainable Energy Grids & Networks","volume":"42 ","pages":"Article 101664"},"PeriodicalIF":4.8,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143520402","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

Design of P2P coordinative transaction mechanism considering low-carbon preference of multiple prosumers in regional electricity market

IF 4.8 2区工程技术

Sustainable Energy Grids & Networks Pub Date : 2025-02-20 DOI: 10.1016/j.segan.2025.101661

Yue Guan, Qiang Hou, Shiquan Wang

{"title":"Design of P2P coordinative transaction mechanism considering low-carbon preference of multiple prosumers in regional electricity market","authors":"Yue Guan, Qiang Hou, Shiquan Wang","doi":"10.1016/j.segan.2025.101661","DOIUrl":"10.1016/j.segan.2025.101661","url":null,"abstract":"<div><div>The market-oriented trading of distributed energy with the participation of multiple prosumers has gradually become a solution to promote the consumption of distributed energy. The transaction preferences of prosumers have a significant impact on market transaction efficiency. How to design a market transaction mechanism that considers the transaction preferences of prosumers to promote efficiency improvement has become a current research hotspot. In this paper: firstly, a regional electricity market trading framework with the participation of multiple prosumers at the distribution network level was established; Secondly, the internal resources of prosumers were analyzed, and the mathematical models of their output units and loads were constructed; Thirdly, a peer-to-peer (P2P) transaction mechanism for regional electricity market was designed based on the combinatorial double auction theory, which takes into account different energy demands and low-carbon preferences of prosumers, among them, with the goal of minimizing operating costs during the scheduling cycle of prosumers, the internal resources were coordinated to achieve balance and their energy supply - demand plans were obtained (as their bidding electricity quantity), and on the basis of considering the low-carbon preferences, a Supply Function Equilibrium (SFE) model was adopted to construct their bidding price strategy (as their bidding electricity price). Third party auctioneer was used to coordinate P2P transactions between prosumers, and different bidding types were introduced to accurately express prosumers´ different energy demands during the trading process. Finally, the effectiveness and feasibility of the proposed P2P transaction mechanism were verified through numerical examples.</div></div>","PeriodicalId":56142,"journal":{"name":"Sustainable Energy Grids & Networks","volume":"42 ","pages":"Article 101661"},"PeriodicalIF":4.8,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143479049","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

Critical component analysis of cyber-physical power systems in cascading failures using graph convolutional networks: An energy-based approach

IF 4.8 2区工程技术

Sustainable Energy Grids & Networks Pub Date : 2025-02-19 DOI: 10.1016/j.segan.2025.101653

Sajedeh Soleimani, Ahmad Afshar, Hajar Atrianfar

{"title":"Critical component analysis of cyber-physical power systems in cascading failures using graph convolutional networks: An energy-based approach","authors":"Sajedeh Soleimani, Ahmad Afshar, Hajar Atrianfar","doi":"10.1016/j.segan.2025.101653","DOIUrl":"10.1016/j.segan.2025.101653","url":null,"abstract":"<div><div>Power systems, with increasing integration into communication networks, have evolved to become complex and interdependent cyber–physical power systems that are highly vulnerable to cascading failures. These failures, due to their propagation through the cyber and physical networks, often lead to severe disruptions. We employ improved percolation theory to model cascading failures triggered by malware cyber-attacks. Addressing the vulnerability of CPPS requires a comprehensive analysis that spans both the structural and functional dimensions of CPPS. This paper introduces a novel framework for vulnerability assessment in CPPS using Graph Convolutional Networks (GCN). Our approach captures the topological complexities and dynamic characteristics of CPPS, incorporating the entropy of potential energy of power system as a new feature to predict and analyze failure propagation. Through Layer-wise Relevance Propagation (LRP), we subsequently quantify the influence of potential energy on system vulnerabilities. Critical components are identified by using LRP scores and an entropy weighting method (EWM). Simulation results based on the cyber–physical IEEE 39-bus and IEEE RTS-96 power systems as test cases, demonstrate the model’s efficacy in identifying vulnerable nodes and branches and highlight the significant role of potential energy in cascading failures. This framework provides a comprehensive approach for real-time vulnerability assessments and resilience enhancement in CPPS.</div></div>","PeriodicalId":56142,"journal":{"name":"Sustainable Energy Grids & Networks","volume":"42 ","pages":"Article 101653"},"PeriodicalIF":4.8,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143464390","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

Optimizing electric vehicle battery health monitoring: A resilient ensemble learning approach for state-of-health prediction

IF 4.8 2区工程技术

Sustainable Energy Grids & Networks Pub Date : 2025-02-19 DOI: 10.1016/j.segan.2025.101655

Vankamamidi S. Naresh, P.N.S. Gayathri, P.Baby Tejaswi, P. Induja, Ch Rohith Reddy, Y.Sai Sudheer

{"title":"Optimizing electric vehicle battery health monitoring: A resilient ensemble learning approach for state-of-health prediction","authors":"Vankamamidi S. Naresh, P.N.S. Gayathri, P.Baby Tejaswi, P. Induja, Ch Rohith Reddy, Y.Sai Sudheer","doi":"10.1016/j.segan.2025.101655","DOIUrl":"10.1016/j.segan.2025.101655","url":null,"abstract":"<div><div>State of Health (SoH) prediction is critical for optimizing electric vehicle (EV) battery performance and longevity. This study proposes an Ensemble of Ensemble Models (EEMs) framework to enhance SoH prediction accuracy by combining ensemble learning methods—Random Forests, Gradient Boosting, and AdaBoost—using a stacking-based meta-learning approach. The method captures complex patterns in key input features such as voltage, temperature, and charge-discharge cycles. The approach was tested using a Li-ion battery dataset, with evaluation metrics including MSE, RMSE and R-squared. Results demonstrate that EEMs with 99.9 accuracy and nearly error-free predictions (RMSE of 0.00000025), validate the importance of advanced ensemble techniques in optimizing SoH prediction and outperform individual and conventional ensemble models, providing accurate and reliable SoH estimates. This framework offers practical implications for improving battery management, extending battery lifespan, and promoting energy sustainability in EV systems.</div></div>","PeriodicalId":56142,"journal":{"name":"Sustainable Energy Grids & Networks","volume":"42 ","pages":"Article 101655"},"PeriodicalIF":4.8,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143520333","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

Coordinated routing optimization and charging scheduling in a multiple-charging station system: A strategic bilevel multi-objective programming

IF 4.8 2区工程技术

Sustainable Energy Grids & Networks Pub Date : 2025-02-19 DOI: 10.1016/j.segan.2025.101659

Pegah Alaee , Junyan Shao , Július Bemš , Josep M. Guerrero

{"title":"Coordinated routing optimization and charging scheduling in a multiple-charging station system: A strategic bilevel multi-objective programming","authors":"Pegah Alaee , Junyan Shao , Július Bemš , Josep M. Guerrero","doi":"10.1016/j.segan.2025.101659","DOIUrl":"10.1016/j.segan.2025.101659","url":null,"abstract":"<div><div>Effectively managing EV charging queues not only alleviates traffic congestion in high-demand areas but also improves user satisfaction by minimizing waiting times. This framework enhances overall system efficiency by better distributing the concentration of EVs during peak periods. This research investigates collaborative mechanisms from the perspectives of various stakeholders, including charging stations (CSs) and EVs, to optimize the charging process. A route optimization model is employed to direct EVs toward the most suitable CSs, followed by the introduction of two scheduling models: (1) a social welfare maximization model and (2) a game-theoretic iterative framework. These models aim to optimize EV charging locations while increasing CS profitability. EVs scheduling is performed using a mixed-integer non-linear programming (MINLP) approach, offering critical insights into its applicability across different scenarios. The numerical results demonstrate that coordinated EV scheduling substantially enhances the operational efficiency of E-mobility systems in both centralized and decentralized configurations. Compared to uncoordinated scheduling, total profits for CSs are 42 % higher for Test System 1 and 39 % higher for Test System 2. EV owners’ costs decrease by 47 % in the social welfare model and 32 % in the game-based model for Test System 1. In Test System 2, cost reductions are 12 % and 7 % for the social welfare and game-based models, respectively. Although power transactions with the market are slightly higher in the social welfare model, the game-based model demonstrates a more efficient distribution of EVs across charging stations, especially in Test System 2, resulting in a more balanced system and optimized resource allocation.</div></div>","PeriodicalId":56142,"journal":{"name":"Sustainable Energy Grids & Networks","volume":"42 ","pages":"Article 101659"},"PeriodicalIF":4.8,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143454602","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

Integrated stochastic reserve estimation and MILP energy planning for high renewable penetration: Application to 2050 South African energy system

IF 4.8 2区工程技术

Sustainable Energy Grids & Networks Pub Date : 2025-02-18 DOI: 10.1016/j.segan.2025.101650

Enrico Giglio , Davide Fioriti , Munyaradzi Justice Chihota , Davide Poli , Bernard Bekker , Giuliana Mattiazzo

{"title":"Integrated stochastic reserve estimation and MILP energy planning for high renewable penetration: Application to 2050 South African energy system","authors":"Enrico Giglio , Davide Fioriti , Munyaradzi Justice Chihota , Davide Poli , Bernard Bekker , Giuliana Mattiazzo","doi":"10.1016/j.segan.2025.101650","DOIUrl":"10.1016/j.segan.2025.101650","url":null,"abstract":"<div><div>The energy transition imposes a shift towards renewable energy sources, and the integration of variable ones introduces significant risks to power system stability. Variable renewable energy sources are mostly unpredictable and can provide limited spare capacity to compensate for imbalance in demand and supply. To meet system adequacy and reliability requirements, the power system is operated with different types of reserve margins to ensure the availability of spare capacity at various time scales. However, despite existing guidelines to operate the current system, limited methodologies have been proposed to estimate reserve requirements for future power systems with high penetration of renewables, including their integration into planning tools. In this study, a comprehensive methodology is proposed to estimate the least-cost power system design which include an endogenous stochastic model for estimating reserve requirements interfaced to a Mixed-Integer Linear Programming model. The proposed stochastic reserve estimation model incorporates generator tripping events, renewable energy variability, and ramping characteristics of the residual demand, extending ENTSO-E guidelines to accommodate future scenarios with high penetration of renewable energy sources. Furthermore, a non-linear parametric function is trained to represent the results of the stochastic reserve estimation model and then integrated into an optimization model to plan future power systems, using an iterative approach. The methodology is validated on the current South African power system. The results indicate the model’s effectiveness in optimizing reserve requirements, showing substantial benefits in including storage and other renewable energy technologies to meet future energy demands, while reducing carbon emissions and enhancing grid reliability.</div></div>","PeriodicalId":56142,"journal":{"name":"Sustainable Energy Grids & Networks","volume":"42 ","pages":"Article 101650"},"PeriodicalIF":4.8,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143464392","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}

引用次数: 0

DSO-prosumers cooperative scheduling approach considering multi-timescale peer-to-peer transactions of electricity and flexibility resources

IF 4.8 2区工程技术

Sustainable Energy Grids & Networks Pub Date : 2025-02-17 DOI: 10.1016/j.segan.2025.101632

Kang Wang , Chengfu Wang , Jianwei Dai , Shuang Dong , Yongling Cui , Guoying Wang

{"title":"DSO-prosumers cooperative scheduling approach considering multi-timescale peer-to-peer transactions of electricity and flexibility resources","authors":"Kang Wang , Chengfu Wang , Jianwei Dai , Shuang Dong , Yongling Cui , Guoying Wang","doi":"10.1016/j.segan.2025.101632","DOIUrl":"10.1016/j.segan.2025.101632","url":null,"abstract":"<div><div>The rapid evolution of peer-to-peer (P2P) transaction mechanisms has facilitated end-use prosumers in energy sharing to enhance energy utilization and address uncertainties in renewable energy sources (RES). However, the lack of coordination across different timescales and heterogeneous distributed resources results in potential economic losses. To this end, a cooperative scheduling approach considering multi-timescale P2P transactions is proposed. Firstly, multi-timescale P2P transactions mechanism is proposed to coordinate the heterogeneous resources between prosumers. In day-ahead stage, prosumers engage in electricity transactions using expected output of RES. In intraday stage, flexible resources are traded among prosumers to mitigate prediction deviation of RES. Meanwhile, the Nash bargaining theory is introduced to allocate the interests. Then, to determine reasonable flexibility requirement in intraday stage, a two-side chance constrained economic dispatch (TS-CCED) model is proposed, in which DSO can set the reference requirement interval at given confidence level to balance the economy and safety of system operation. Finally, to reduce the computational complexity, the Gaussian mixture model is applied to convert the TS-CCED model into a convex optimization problem with guaranteed accuracy. Case study based on the IEEE 33-bus system and IEEE-123 bus system verifies the effectiveness of the proposed method.</div></div>","PeriodicalId":56142,"journal":{"name":"Sustainable Energy Grids & Networks","volume":"42 ","pages":"Article 101632"},"PeriodicalIF":4.8,"publicationDate":"2025-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143474642","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