Sustainable Energy Grids & Networks最新文献_第4页

Integrated optimization of smart building energy consumption in microgrids using linearized real-time control strategies 基于线性化实时控制策略的微电网智能建筑能耗集成优化

IF 4.8 2区工程技术

Sustainable Energy Grids & Networks Pub Date : 2025-05-20 DOI: 10.1016/j.segan.2025.101745

Xiaochun Cheng , Yunfu Zhang , Xiaolin Su

{"title":"Integrated optimization of smart building energy consumption in microgrids using linearized real-time control strategies","authors":"Xiaochun Cheng , Yunfu Zhang , Xiaolin Su","doi":"10.1016/j.segan.2025.101745","DOIUrl":"10.1016/j.segan.2025.101745","url":null,"abstract":"<div><div>This research develops a model to reduce main grid electricity costs and boost local demand and generation within a microgrid, adhering to operational constraints. It uses a mixed-integer nonlinear programming (MINLP) framework to manage heating, ventilation, air conditioning, lighting, photovoltaic generation, and energy storage while ensuring indoor comfort. A rolling horizon strategy was employed to simplify the original model, accompanied by pre-processing in EnergyPlus software utilizing linearization techniques, culminating in a Mixed-Integer Linear Programming approximation. Linearization yields an optimally solvable model that is appropriate for real-time energy management applications. We performed simulations under decentralized and centralized schemes for a 13-bus microgrid with uncontrollable loads and smart buildings. This study conducted a scalability analysis for the 34-bus microgrid case. The rolling horizon method successfully handled uncertainties in demand and reduced the amount of data needed for forecasting across five different consumption models, which included various combinations of photovoltaic units and energy storage systems. The findings indicated a 16 % decrease in peak power demand and an error margin when comparing linearized results with actual data, showcasing notable enhancements in cost efficiency and stability. The testing provided insights into optimal configurations for each region, validating the model's effectiveness in enhancing microgrid reliability, sustainability, cost-effectiveness, and occupant comfort.</div></div>","PeriodicalId":56142,"journal":{"name":"Sustainable Energy Grids & Networks","volume":"43 ","pages":"Article 101745"},"PeriodicalIF":4.8,"publicationDate":"2025-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144170217","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 distributed voltage inference framework for cyber-physical attacks detection and localization in active distribution grids 一种分布式电压推理框架，用于主动配电网网络物理攻击检测与定位

IF 4.8 2区工程技术

Sustainable Energy Grids & Networks Pub Date : 2025-05-19 DOI: 10.1016/j.segan.2025.101750

Mazhar Ali, Wei Sun

{"title":"A distributed voltage inference framework for cyber-physical attacks detection and localization in active distribution grids","authors":"Mazhar Ali, Wei Sun","doi":"10.1016/j.segan.2025.101750","DOIUrl":"10.1016/j.segan.2025.101750","url":null,"abstract":"<div><div>The transition to active distribution grids with real-time monitoring and control depends on the proliferation of advanced communication networks and devices. This paradigm shift towards a cyber-physical architecture also introduces new vulnerabilities for adversaries to exploit and launch sophisticated cyber-physical attacks targeting grid observability. Current research highlights the challenges in distinguishing attacks on voltage phasor or nodal injection measurements and isolating multi-source attack locations in a multiphase distribution grid. The attack detection and localization methods in literature face accuracy issues, applications across diverse attack scenarios, or scalability limits. To bridge these gaps, this paper proposes a distributed Voltage Inference framework for real-time detection and localization of cyber-physical attacks, addressing scalability, adaptability, and accuracy challenges in state-of-the-art methods. The proposed methodology leverages the distributed nature of the Voltage Inference framework through a two-step process of prediction and correction, together with a tractable graph partitioning approach, providing a reliable solution to identify compromised measurement sources and facilitate isolation. Extensive testing on IEEE 13 and 123-node distribution feeders underscores the algorithm’s efficacy, enhancing the security and resilience of active distribution grids against evolving cyber threats. Additionally, Hardware-in-the-Loop (HIL) implementation validates the proposed strategy’s practical applicability in real-world scenarios.</div></div>","PeriodicalId":56142,"journal":{"name":"Sustainable Energy Grids & Networks","volume":"43 ","pages":"Article 101750"},"PeriodicalIF":4.8,"publicationDate":"2025-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144137950","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

Operational risk quantification of power grids using graph neural network surrogates of the DC optimal power flow 用图神经网络替代直流最优潮流进行电网运行风险量化

IF 4.8 2区工程技术

Sustainable Energy Grids & Networks Pub Date : 2025-05-19 DOI: 10.1016/j.segan.2025.101748

Yadong Zhang, Pranav M. Karve, Sankaran Mahadevan

{"title":"Operational risk quantification of power grids using graph neural network surrogates of the DC optimal power flow","authors":"Yadong Zhang, Pranav M. Karve, Sankaran Mahadevan","doi":"10.1016/j.segan.2025.101748","DOIUrl":"10.1016/j.segan.2025.101748","url":null,"abstract":"<div><div>Surrogates or proxies of a decision-making algorithm (DC optimal power flow or DC OPF) are developed to expedite Monte Carlo (MC) sampling-based grid risk quantification. Sampling-based risk quantification allows explicit computation of the risk associated with a given probabilistic forecast of power demand and supply. However, it requires solving a large number of optimization (DC OPF) problems within a short time, which is computationally demanding. The computational burden is alleviated by developing graph neural network (GNN) surrogates, because GNNs are especially suitable for modeling graph-structured data. In contrast to previous works that developed GNN surrogates to predict bus-level (generator dispatch) decisions or line flow, the proposed GNN models directly predict zonal/system level quantities needed for grid risk assessment. That is, in addition to generator dispatch and line flow, we develop GNN models that directly predict zonal or system level reserve shortage and load shedding. The benefits of these GNN surrogates are demonstrated using four synthetic grids (Case118, Case300, Case1354pegase, and Case2848rte). It is shown that the proposed GNN surrogates are 250–800 times faster than numerical solvers at predicting the grid state, and they enable fast as well as accurate risk quantification for power grids. It is also shown that directly predicting aggregated zonal/system level quantities leads to more accurate predictions than aggregating bus level predictions.</div></div>","PeriodicalId":56142,"journal":{"name":"Sustainable Energy Grids & Networks","volume":"43 ","pages":"Article 101748"},"PeriodicalIF":4.8,"publicationDate":"2025-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144123689","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

Enhancing resilience of power-transportation coupled networks to typhoons: A tri-stage integration strategy of multi-resources 增强电力-交通耦合网络对台风的抵御能力：多资源三阶段整合策略

IF 4.8 2区工程技术

Sustainable Energy Grids & Networks Pub Date : 2025-05-19 DOI: 10.1016/j.segan.2025.101747

Xianglong Lian, Lei Qiu, Chenkai Song, Lijun Liu, Zhezhuang Xu

{"title":"Enhancing resilience of power-transportation coupled networks to typhoons: A tri-stage integration strategy of multi-resources","authors":"Xianglong Lian, Lei Qiu, Chenkai Song, Lijun Liu, Zhezhuang Xu","doi":"10.1016/j.segan.2025.101747","DOIUrl":"10.1016/j.segan.2025.101747","url":null,"abstract":"<div><div>With the increasing frequency and severity of extreme disaster events, enhancing the resilience of urban power grids has become critical. Most studies focus on distribution networks (DNs) without considering the important coupling relationship between transportation networks (TNs) and DNs. This paper addresses this gap by proposing a tri-stage resilience improvement method for power–transportation coupled networks (PTNs), incorporating flexible resources. The approach includes three models: (1) a pre-allocation model with a line hardening strategy based on vulnerability index for defense, (2) a failure response model that analyzes the impact of typhoons on PTN and minimizes load reduction in the DN, and (3) a restoration model that integrates emergency repair crews and mobile energy storage, optimized via linear programming. The performance of the proposed method is evaluated using a PTN with the IEEE 33-bus distribution test system and its corresponding TN. Results demonstrate that the resilience of PTN can be enhanced effectively by applying the proposed tri-stage method.</div></div>","PeriodicalId":56142,"journal":{"name":"Sustainable Energy Grids & Networks","volume":"43 ","pages":"Article 101747"},"PeriodicalIF":4.8,"publicationDate":"2025-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144135101","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

Energy management in smart homes with adversary detection and noise mitigation using a moving prediction window scheme 智能家居中的能源管理，使用移动预测窗口方案进行对手检测和噪声缓解

IF 4.8 2区工程技术

Sustainable Energy Grids & Networks Pub Date : 2025-05-19 DOI: 10.1016/j.segan.2025.101723

Hamid Reza Babaei Ghazvini, Saeed Adelipour, Mohammad Haeri

{"title":"Energy management in smart homes with adversary detection and noise mitigation using a moving prediction window scheme","authors":"Hamid Reza Babaei Ghazvini, Saeed Adelipour, Mohammad Haeri","doi":"10.1016/j.segan.2025.101723","DOIUrl":"10.1016/j.segan.2025.101723","url":null,"abstract":"<div><div>This paper presents an energy management algorithm for scheduling a large number of residential households, utilizing the moving prediction window to make it resilient against false data injection attacks and communication noise. We model multiple communities of smart homes, each managed by a local controller, where self-interested residential households engage in a global non-cooperative game. The cost functions of the households are influenced by a constrained aggregated power consumption term across all households from all communities. The interactions among households are modeled through a multi-community aggregative game. To reach a Nash equilibrium, we propose an iterative algorithm wherein local controllers estimate the coupling aggregate term and corresponding Lagrange multiplier for their respective households and collaborate with other controllers via an unreliable communication network to refine the aggregate estimations. Given the vulnerability of the communication network to external intrusions and the potential for internal controllers to behave maliciously, we explore a moving horizon window technique to detect false data injection attacks and mitigate communication noise. In this regard, first, a moving horizon estimator predicts the community’s current behavior based on historical data; second, a residual-based detection mechanism flags an attack when predicted residuals exceed a dynamic threshold; and third, corrupted measurements are discarded, and the average of the predictions is used in the Krasnoselskii-Mann update to reduce the noise impact. Numerical simulations show the effectiveness of the proposed algorithm in increasing the speed of reaching consensus by about 30 percent while managing the energy consumption of households.</div></div>","PeriodicalId":56142,"journal":{"name":"Sustainable Energy Grids & Networks","volume":"43 ","pages":"Article 101723"},"PeriodicalIF":4.8,"publicationDate":"2025-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144098981","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 multivariate prediction framework for flood-induced substation damage based on generative adversarial network and MPformer-based two-stage model 基于生成对抗网络和基于mpform的两阶段模型的变电站洪水损伤多元预测框架

IF 4.8 2区工程技术

Sustainable Energy Grids & Networks Pub Date : 2025-05-16 DOI: 10.1016/j.segan.2025.101740

Yu Shi , Ying Shi , Degui Yao , Ming Lu , Yun Liang , Wei Huang

{"title":"A multivariate prediction framework for flood-induced substation damage based on generative adversarial network and MPformer-based two-stage model","authors":"Yu Shi , Ying Shi , Degui Yao , Ming Lu , Yun Liang , Wei Huang","doi":"10.1016/j.segan.2025.101740","DOIUrl":"10.1016/j.segan.2025.101740","url":null,"abstract":"<div><div>Frequent extreme rainstorms have significantly increased the flooding risk, threatening the security and stability of electrical substations. The process of flood-induced substation damage is complex and nonlinear, challenging traditional predictive methods. Therefore, a novel predictive framework is proposed for flood-induced substation damage. This framework uses a generative adversarial network (GAN)-based model to capture complex data relationships and generate realistic samples, which mitigates training data imbalance. A multivariate predictive Transformer network (MPformer), integrating three improved modules: time embedding, multi-factor fusion encoding, and attention-based encoder, is proposed to capture temporal dependencies and complex interactions between influencing factors and flood-induced damage. Based on MPformer and sensitive cost learning, a two-stage integrated model is designed to reduce the problem of sample imbalance further and realize the simultaneous prediction of the substation damage probability, severity, and time. The experimental results show that the GAN-based method is superior to the traditional method in terms of sample balancing, and the MPformer-based two-stage model outperforms the mainstream model, with a 12.30 % average increase in F1 score for probability prediction and reductions of 38.56 % and 45.31 % in RMSE for severity and time predictions, respectively. A case study shows that the proposed method can offer reliable pre-disaster prediction.</div></div>","PeriodicalId":56142,"journal":{"name":"Sustainable Energy Grids & Networks","volume":"43 ","pages":"Article 101740"},"PeriodicalIF":4.8,"publicationDate":"2025-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144105619","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

Multi-objective smart charging scheduling scheme for EV integration and energy loss minimization in active distribution networks using mixed integer programming 基于混合整数规划的有源配电网电动汽车集成和能量损失最小化的多目标智能充电调度方案

IF 4.8 2区工程技术

Sustainable Energy Grids & Networks Pub Date : 2025-05-14 DOI: 10.1016/j.segan.2025.101743

Subhadarshini Panda, Sanjib Ganguly

{"title":"Multi-objective smart charging scheduling scheme for EV integration and energy loss minimization in active distribution networks using mixed integer programming","authors":"Subhadarshini Panda, Sanjib Ganguly","doi":"10.1016/j.segan.2025.101743","DOIUrl":"10.1016/j.segan.2025.101743","url":null,"abstract":"<div><div>Efficient scheduling of electric vehicles (EVs) within power distribution networks (PDNs) is crucial due to the conflicting interests of various stakeholders, such as EV owners, who seek cost savings, and distribution network operators (DNOs), who focus on minimizing peak demand and reducing losses. This issue becomes even more pronounced with vehicle-to-grid (V2G) operations. This paper proposes a multi-objective EV scheduling model to determine the optimal trade-off between the economic interests of EV owners and the technical needs of the grid, thereby offering benefits to both stakeholders. The proposed model minimizes the total charging cost of EV owners and flattens the load curve in the EV-integrated PDN simultaneously. This is achieved by optimally utilizing both the grid-to-vehicle (G2V) and V2G capabilities of EVs while also considering battery health. A weighted sum method is used to find a set of non-dominated solutions to the multi-objective EV scheduling problem. Additionally, to further enhance the network efficiency and complement the multi-objective EV scheduling, the model incorporates distribution network reconfiguration (DNR) that is carried out at each hour of the day. The efficacy of the proposed model is validated by implementing it on a modified 33-node and IEEE 123-node test networks.</div></div>","PeriodicalId":56142,"journal":{"name":"Sustainable Energy Grids & Networks","volume":"43 ","pages":"Article 101743"},"PeriodicalIF":4.8,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144070584","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

Power coordinated strategy of vehicle-to-microgrid integrated hybrid AC/DC microgrids considering electric vehicles as flexible energy storage 考虑电动汽车柔性储能的车-微网一体化交/直流混合微网功率协调策略

IF 4.8 2区工程技术

Sustainable Energy Grids & Networks Pub Date : 2025-05-14 DOI: 10.1016/j.segan.2025.101737

Hao Wang , Jiawei Yan , Boyang Kang

{"title":"Power coordinated strategy of vehicle-to-microgrid integrated hybrid AC/DC microgrids considering electric vehicles as flexible energy storage","authors":"Hao Wang , Jiawei Yan , Boyang Kang","doi":"10.1016/j.segan.2025.101737","DOIUrl":"10.1016/j.segan.2025.101737","url":null,"abstract":"<div><div>Increasing adoption of electric vehicles (EVs) entrance to hybrid ac/dc microgrids (HMGs) would provide flexible energy storage sources (FESSs) to perform vehicle-to-microgrid (V2MG) operation. However, especially in islanded mode, the state of charge (SOC) of traditional energy storage unit (ESU) approaching the critical value of charge/discharge would inevitably lead to unreliable power supply. To solve this problem, a power coordinated strategy of V2MG integrated HMGs considering EVs as FESSs is proposed in this paper. First, a joint energy storage sources (JESSs) dynamic grouping method is presented for traditional ESU and scaled electric vehicle groups (EVGs) within HMGs containing multiple subgrids, which divides ESU and EVGs into panels and sets at the same time scale. Then, the operation modes and conditions of HMGs are classified according to the power surplus/deficient state of each subgrid. Further, this paper designs response priority based on real-time grouping of JESSs to balance the SOC of ESU and formulates power coordination control strategies for abnormal SOC of ESU and subgrid power overlimit, among which the FESSs provide auxiliary service for system power regulation. Finally, the results of the simulation analysis show that the proposed strategy can achieve coordinated regulation of traditional ESU and EV as FESSs in islanded microgrids, reducing the system's dependence on traditional ESU and improving the power supply reliability of microgrid systems.</div></div>","PeriodicalId":56142,"journal":{"name":"Sustainable Energy Grids & Networks","volume":"43 ","pages":"Article 101737"},"PeriodicalIF":4.8,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144084534","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

Load peak-valley shape clustering and drift analysis for improving temporal pattern representation 负载峰谷形状聚类和漂移分析改进时间模式表示

IF 4.8 2区工程技术

Sustainable Energy Grids & Networks Pub Date : 2025-05-14 DOI: 10.1016/j.segan.2025.101734

Yiwei Ma , Yimeng Shen , Xianlun Tang , Dong Yan

{"title":"Load peak-valley shape clustering and drift analysis for improving temporal pattern representation","authors":"Yiwei Ma , Yimeng Shen , Xianlun Tang , Dong Yan","doi":"10.1016/j.segan.2025.101734","DOIUrl":"10.1016/j.segan.2025.101734","url":null,"abstract":"<div><div>Load shape pattern clustering is an important foundation for developing appropriate tariff design and load management to achieve more economical and reliable benefits. However, the existing load shape pattern clustering methods mainly focus on the whole load shape and various clustering algorithms, which do not consider the peak-valley shape features and distribution drift issue of the load shapes. Therefore, peak-valley shape pattern clustering and drift measurement of daily load shapes are proposed to solve this problem. To accurately reveal the peak-valley electricity consumption behaviors, load peak-valley shape models and a hybrid distance measurement are proposed to obtain more representative temporal patterns that have more compact peak-valley shape distributions. Moreover, two measurement models for power drift and time drift are proposed to analyze the significant drift problem between daily load peak-valley shape patterns. The results showed that the proposed method outperformed other methods, as it not only achieved the best clustering effectiveness scores, such as DBI, WAS, CHI, SC, and DI scores of 0.5537, 0.2633, 502.3634, 0.8872, and 1.4730, respectively, but also accurately obtained the time drift values between different modes, such as the maximum backward shift of the two peak times by 90 and 150 minutes, and the maximum backward shift of the valley time by 45 and 60 minutes, respectively.</div></div>","PeriodicalId":56142,"journal":{"name":"Sustainable Energy Grids & Networks","volume":"43 ","pages":"Article 101734"},"PeriodicalIF":4.8,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144070581","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

Predicting faults in power distribution grids during heatwaves: A comparative study of machine learning models applied to Milan distribution network 热浪期间配电网故障预测：应用于米兰配电网的机器学习模型的比较研究

IF 4.8 2区工程技术

Sustainable Energy Grids & Networks Pub Date : 2025-05-13 DOI: 10.1016/j.segan.2025.101741

Morteza Aghahadi , Alessandro Bosisio , Andrea Pegoiani , Samuele Forciniti , Marco Merlo , Alberto Berizzi

{"title":"Predicting faults in power distribution grids during heatwaves: A comparative study of machine learning models applied to Milan distribution network","authors":"Morteza Aghahadi , Alessandro Bosisio , Andrea Pegoiani , Samuele Forciniti , Marco Merlo , Alberto Berizzi","doi":"10.1016/j.segan.2025.101741","DOIUrl":"10.1016/j.segan.2025.101741","url":null,"abstract":"<div><div>The increasing frequency and severity of extreme weather events, such as heatwaves in Milan, intensified by climate change, pose significant challenges to the reliability and resilience of electrical power distribution systems. Traditional deterministic planning methods are becoming inadequate as these events grow more unpredictable. This study introduces a novel machine learning methodology to enhance grid resilience during heatwaves, focusing on fault prediction and heatwave forecasting. Three complementary approaches were systematically evaluated: Ridge Regression with Recursive Feature Elimination and Cross-Validation, Random Forest Regression, and Second-order Polynomial Poisson Regression with Recursive Feature Elimination and Cross-Validation. Through innovative feature engineering incorporating soil temperature, humidity gradients, and dynamic load demand patterns, predictive accuracy was significantly improved over conventional methods. Rigorous cross-validation with statistical validation demonstrated model stability across varying conditions, with the Second-order Polynomial Poisson model achieving a mean absolute error of 0.15 in predicting fault occurrences. To address the observed heteroscedasticity during high-fault periods, adaptive prediction intervals were developed, providing operators with crucial uncertainty quantification when it matters most. When translated to operational reality, these models enable Distribution System Operators to implement proactive fault management strategies, potentially reducing outage response times by an estimated 15–20 % during extreme weather events. This research bridges the critical gap between climate science and power system engineering, offering data-driven decision support for the increasingly volatile operational environment facing urban distribution networks.</div></div>","PeriodicalId":56142,"journal":{"name":"Sustainable Energy Grids & Networks","volume":"43 ","pages":"Article 101741"},"PeriodicalIF":4.8,"publicationDate":"2025-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144070583","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