Energy and AI最新文献_第6页

EGBAD: Ensemble graph-boosted anomaly detection for user-level multi-energy load data EGBAD：用户级多能量负载数据的集成图增强异常检测

IF 9.6 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Energy and AI

Pub Date : 2025-10-01 DOI: 10.1016/j.egyai.2025.100627

Yuxuan Chen, Shuo Dai, Ruoyi Xu, Haipeng Xie, Yao Zhang

Anomaly detection is crucial for data-driven applications in integrated energy systems. Traditional anomaly detection methods primarily focus on one single energy load, often neglecting potential spatial correlations between multivariate energy time series. Meanwhile, addressing the imbalanced nature of user-level multi-energy load data remains a significant challenge. In this paper, we propose EGBAD, an Ensemble Graph-Boosted Anomaly Detection framework for user-level multi-energy load that leverages the advantages of graph relational analysis and ensemble learning. First, a dynamic graph construction method based on multidimensional scaling (MDS) is proposed to transform multi-energy load data into graph representations. These graphs are subsequently processed using graph convolutional network (GCN) to capture the spatiotemporal correlations between multi-energy load time series. In addition, to improve detection robustness under class imbalance, the entire training process is embedded within a Boosting ensemble learning framework, where the weight assigned to the minority class is progressively increased at each boosting stage. Experimental results on publicly real-world datasets demonstrate that the proposed model achieves superior anomaly detection accuracy compared to most baseline methods. Notably, it performs especially well in scenarios characterized by extreme data imbalance, achieving the highest recall and F1-score for anomaly detection.

异常检测对于综合能源系统中数据驱动的应用至关重要。传统的异常检测方法主要关注单个能量负荷，往往忽略了多元能量时间序列之间潜在的空间相关性。同时，解决用户级多能负荷数据的不平衡性仍然是一个重大挑战。在本文中，我们提出了EGBAD，一个针对用户级多能量负载的集成图增强异常检测框架，它利用了图关系分析和集成学习的优势。首先，提出了一种基于多维尺度（MDS）的动态图构建方法，将多能负荷数据转换为图表示。随后使用图卷积网络（GCN）对这些图进行处理，以捕获多能负荷时间序列之间的时空相关性。此外，为了提高类不平衡下的检测鲁棒性，将整个训练过程嵌入到Boosting集成学习框架中，在每个Boosting阶段逐步增加分配给少数类的权重。在公开的真实数据集上的实验结果表明，与大多数基线方法相比，该模型具有更高的异常检测精度。值得注意的是，它在数据极度不平衡的情况下表现得特别好，在异常检测方面达到了最高的召回率和f1分。

{"title":"EGBAD: Ensemble graph-boosted anomaly detection for user-level multi-energy load data","authors":"Yuxuan Chen, Shuo Dai, Ruoyi Xu, Haipeng Xie, Yao Zhang","doi":"10.1016/j.egyai.2025.100627","DOIUrl":"10.1016/j.egyai.2025.100627","url":null,"abstract":"<div><div>Anomaly detection is crucial for data-driven applications in integrated energy systems. Traditional anomaly detection methods primarily focus on one single energy load, often neglecting potential spatial correlations between multivariate energy time series. Meanwhile, addressing the imbalanced nature of user-level multi-energy load data remains a significant challenge. In this paper, we propose EGBAD, an <strong>E</strong>nsemble <strong>G</strong>raph-<strong>B</strong>oosted <strong>A</strong>nomaly <strong>D</strong>etection framework for user-level multi-energy load that leverages the advantages of graph relational analysis and ensemble learning. First, a dynamic graph construction method based on multidimensional scaling (MDS) is proposed to transform multi-energy load data into graph representations. These graphs are subsequently processed using graph convolutional network (GCN) to capture the spatiotemporal correlations between multi-energy load time series. In addition, to improve detection robustness under class imbalance, the entire training process is embedded within a Boosting ensemble learning framework, where the weight assigned to the minority class is progressively increased at each boosting stage. Experimental results on publicly real-world datasets demonstrate that the proposed model achieves superior anomaly detection accuracy compared to most baseline methods. Notably, it performs especially well in scenarios characterized by extreme data imbalance, achieving the highest recall and F1-score for anomaly detection.</div></div>","PeriodicalId":34138,"journal":{"name":"Energy and AI","volume":"22 ","pages":"Article 100627"},"PeriodicalIF":9.6,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145219587","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Investigation of fuel cell stack performance degradation based on 1000 h durability experiments and long short-term memory prediction frameworks under dynamic load conditions 动态载荷条件下基于1000 h耐久性实验和长短期记忆预测框架的燃料电池堆性能退化研究

IF 9.6 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Energy and AI

Pub Date : 2025-09-30 DOI: 10.1016/j.egyai.2025.100628

Zirong Yang , Yang Ge , Xuefeng Ji , Xiaolu Li , Daokuan Jiao , Yongping Hou , Yanyi Zhang , Dong Hao

Investigating the proton exchange membrane fuel cell (PEMFC) stack performance degradation phenomena is of vital importance for product development. In the study, the 1000 h durability experiment of a 5-kW fuel cell stack was performed under dynamic cyclic test conditions, and the test data containing 16 key parameters was utilized to develop the performance prediction framework based on long short-term memory (LSTM) model and LSTM model incorporating attention mechanism (Attention-LSTM). Data preprocessing and postprocessing for eight current modes as well as incremental learning approach were also presented. Experimental results show that the voltage degradation ratio is about 2.0 % at the total dynamic cyclic duration of 500 h and approximately 4.8 % at 1000 h. The degradation ratio at higher stack operating currents is found larger than that of lower operating currents. The calculated voltage degradation speeds among all current modes fall within the range of 25∼60 μV h^-1. When it comes to model prediction performances, both LSTM and Attention-LSTM models could effectively capture the voltage variations under current rising and dropping conditions. The LSTM model exhibits superior transient prediction capabilities near current change moments while the Attention-LSTM model demonstrates smaller prediction deviations at relatively stable conditions. When the advanced forecast time reaches or exceeds 200 h, the Attention-LSTM model predictions agree better with the bench test data, and it maintains consistent prediction accuracy across different current modes. The study contributes to fuel cell stack durability performance analysis and degradation prediction.

研究质子交换膜燃料电池（PEMFC）堆性能退化现象对产品开发具有重要意义。在动态循环试验条件下进行5kw燃料电池堆1000 h耐久性试验，利用包含16个关键参数的试验数据，构建了基于长短期记忆（LSTM）模型和考虑注意机制的LSTM模型（attention -LSTM）的性能预测框架。介绍了八种当前模式的数据预处理和后处理以及增量学习方法。实验结果表明，在总动态循环时间为500 h时，电压退化率约为2.0%，在1000 h时，电压退化率约为4.8%，且高工作电流时的电压退化率大于低工作电流时的电压退化率。计算得到的电压衰减速度在25 ~ 60 μV h-1范围内。在模型预测性能方面，LSTM和Attention-LSTM模型都能有效捕捉电流上升和下降条件下的电压变化。LSTM模型在电流变化时刻表现出优越的瞬态预测能力，而Attention-LSTM模型在相对稳定的条件下表现出较小的预测偏差。当超前预报时间达到或超过200 h时，Attention-LSTM模型预报结果与台架试验数据吻合较好，且在不同电流模式下预报精度保持一致。该研究有助于燃料电池堆耐久性分析和退化预测。

{"title":"Investigation of fuel cell stack performance degradation based on 1000 h durability experiments and long short-term memory prediction frameworks under dynamic load conditions","authors":"Zirong Yang , Yang Ge , Xuefeng Ji , Xiaolu Li , Daokuan Jiao , Yongping Hou , Yanyi Zhang , Dong Hao","doi":"10.1016/j.egyai.2025.100628","DOIUrl":"10.1016/j.egyai.2025.100628","url":null,"abstract":"<div><div>Investigating the proton exchange membrane fuel cell (PEMFC) stack performance degradation phenomena is of vital importance for product development. In the study, the 1000 h durability experiment of a 5-kW fuel cell stack was performed under dynamic cyclic test conditions, and the test data containing 16 key parameters was utilized to develop the performance prediction framework based on long short-term memory (LSTM) model and LSTM model incorporating attention mechanism (Attention-LSTM). Data preprocessing and postprocessing for eight current modes as well as incremental learning approach were also presented. Experimental results show that the voltage degradation ratio is about 2.0 % at the total dynamic cyclic duration of 500 h and approximately 4.8 % at 1000 h. The degradation ratio at higher stack operating currents is found larger than that of lower operating currents. The calculated voltage degradation speeds among all current modes fall within the range of 25∼60 μV h<sup>-1</sup>. When it comes to model prediction performances, both LSTM and Attention-LSTM models could effectively capture the voltage variations under current rising and dropping conditions. The LSTM model exhibits superior transient prediction capabilities near current change moments while the Attention-LSTM model demonstrates smaller prediction deviations at relatively stable conditions. When the advanced forecast time reaches or exceeds 200 h, the Attention-LSTM model predictions agree better with the bench test data, and it maintains consistent prediction accuracy across different current modes. The study contributes to fuel cell stack durability performance analysis and degradation prediction.</div></div>","PeriodicalId":34138,"journal":{"name":"Energy and AI","volume":"22 ","pages":"Article 100628"},"PeriodicalIF":9.6,"publicationDate":"2025-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145320593","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Joint reinforcement learning to optimize multiple UAV charger deployments for individual energy requirement in IoT 联合强化学习优化多个无人机充电器部署，以满足物联网中单个能源需求

IF 9.6 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Energy and AI

Pub Date : 2025-09-23 DOI: 10.1016/j.egyai.2025.100622

He Li , Chuang Dong , Shixian Sun , Cong Zhao , Peng Yu , Qinglei Qi , Xiaopu Ma , Wentao Li

The technology of wireless power transfer (WPT) utilizing unmanned aerial vehicles (UAVs) presents novel avenues for enhancing the longevity of wireless sensor networks (WSNs), which constitute a critical component of the Internet of Things (IoT). However, existing research on charging deployment generally overlooks the heterogeneous energy requirements within the network, resulting in low charging efficiency for high-energy-consuming nodes. This paper addresses the multiple UAVs optimal cooperative charging deployment problem (MUAVs-OCCDP) and proposes a phased optimization strategy. Firstly, it constructs the network topology and records the energy requirements of the nodes. Based on the strength advantage relationship (SDR), an improved NSGA-II algorithm is designed to generate the initial deployment plan. Then, a two-phase reinforcement learning framework is established: the phase 1 aims to reduce the number of UAVs by optimizing the number of covered nodes and the average charging efficiency; the phase 2 promotes collaboration through the sharing of multi-agent experience and a hybrid reward mechanism to achieve balanced charging energy distribution.

利用无人机（uav）的无线电力传输（WPT）技术为提高无线传感器网络（wsn）的使用寿命提供了新的途径，无线传感器网络是物联网（IoT）的关键组成部分。然而，现有的充电部署研究往往忽略了网络内部的异构能量需求，导致高能耗节点的充电效率较低。针对多无人机最优协同充电部署问题（muav - occdp），提出了一种阶段性优化策略。首先，构建网络拓扑，记录节点能量需求；基于力量优势关系（SDR），设计了一种改进的NSGA-II算法生成初始部署方案。然后，建立了两阶段强化学习框架：第一阶段通过优化覆盖节点数和平均充电效率来减少无人机数量；第二阶段通过多智能体经验共享和混合奖励机制促进协作，实现充电能量均衡分配。

{"title":"Joint reinforcement learning to optimize multiple UAV charger deployments for individual energy requirement in IoT","authors":"He Li , Chuang Dong , Shixian Sun , Cong Zhao , Peng Yu , Qinglei Qi , Xiaopu Ma , Wentao Li","doi":"10.1016/j.egyai.2025.100622","DOIUrl":"10.1016/j.egyai.2025.100622","url":null,"abstract":"<div><div>The technology of wireless power transfer (WPT) utilizing unmanned aerial vehicles (UAVs) presents novel avenues for enhancing the longevity of wireless sensor networks (WSNs), which constitute a critical component of the Internet of Things (IoT). However, existing research on charging deployment generally overlooks the heterogeneous energy requirements within the network, resulting in low charging efficiency for high-energy-consuming nodes. This paper addresses the multiple UAVs optimal cooperative charging deployment problem (MUAVs-OCCDP) and proposes a phased optimization strategy. Firstly, it constructs the network topology and records the energy requirements of the nodes. Based on the strength advantage relationship (SDR), an improved NSGA-II algorithm is designed to generate the initial deployment plan. Then, a two-phase reinforcement learning framework is established: the phase 1 aims to reduce the number of UAVs by optimizing the number of covered nodes and the average charging efficiency; the phase 2 promotes collaboration through the sharing of multi-agent experience and a hybrid reward mechanism to achieve balanced charging energy distribution.</div></div>","PeriodicalId":34138,"journal":{"name":"Energy and AI","volume":"22 ","pages":"Article 100622"},"PeriodicalIF":9.6,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145158649","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A robust hybrid machine learning framework for short-term load forecasting: integrating multi-linear regression, long short-term memory, and feed-forward neural networks for enhanced accuracy and efficiency 一个用于短期负荷预测的鲁棒混合机器学习框架：集成多元线性回归、长短期记忆和前馈神经网络，以提高准确性和效率

IF 9.6 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Energy and AI

Pub Date : 2025-09-23 DOI: 10.1016/j.egyai.2025.100625

Fareeduddin Mohammed, Ameni Boumaiza, Antonio Sanfilippo, Daniel Perez-Astudillo, Dunia Bachour

Efficient energy management and grid stability strongly rely on accurate Short-Term Load Forecasting (STLF). Existing forecasting models, unfortunately, are often inaccurate and computationally demanding. To overcome these challenges, a novel hybrid model, combining both linear regression and machine learning techniques, is proposed in this study. The hybrid model, MLR-LSTM-FFNN, captures both temporal and non-linear dependencies in load data by integrating multi-linear regression (MLR) with long short-term memory (LSTM) networks and feed-forward neural networks (FFNN). Using datasets from Qatar, with 5 min, 15 min, 30 min, and 1 h time intervals and from Panama City with a 1 h interval, experiments were conducted to thoroughly test the robustness of the model. The results showed that the MLR-LSTM-FFNN hybrid model outperformed the baseline and state-of-the-art hybrid models for each of the datasets, in terms of lower RMSE, MAE, and MAPE values along with a faster training time. This superior performance across different datasets underscores the model’s scalability and reliability as an STLF approach, providing a practical solution to energy demand prediction tasks. The improvement in short-term forecasting accuracy provides utilities with a practical tool to optimize demand-side management, reduce operational costs, and enhance grid reliability.

有效的能源管理和电网稳定在很大程度上依赖于准确的短期负荷预测。不幸的是，现有的预测模型往往是不准确的，而且计算要求很高。为了克服这些挑战，本研究提出了一种结合线性回归和机器学习技术的新型混合模型。混合模型MLR-LSTM-FFNN通过将多元线性回归（MLR）与长短期记忆（LSTM）网络和前馈神经网络（FFNN）相结合，捕获负载数据的时间和非线性依赖关系。使用来自卡塔尔的数据集，间隔时间为5分钟、15分钟、30分钟和1小时，以及来自巴拿马城的数据集，间隔时间为1小时，进行实验以彻底测试模型的稳健性。结果表明，MLR-LSTM-FFNN混合模型在每个数据集的RMSE， MAE和MAPE值较低以及训练时间更快方面优于基线和最先进的混合模型。这种跨不同数据集的卓越性能强调了该模型作为STLF方法的可扩展性和可靠性，为能源需求预测任务提供了实用的解决方案。短期预测准确性的提高为电力公司优化需求侧管理、降低运营成本和提高电网可靠性提供了实用工具。

{"title":"A robust hybrid machine learning framework for short-term load forecasting: integrating multi-linear regression, long short-term memory, and feed-forward neural networks for enhanced accuracy and efficiency","authors":"Fareeduddin Mohammed, Ameni Boumaiza, Antonio Sanfilippo, Daniel Perez-Astudillo, Dunia Bachour","doi":"10.1016/j.egyai.2025.100625","DOIUrl":"10.1016/j.egyai.2025.100625","url":null,"abstract":"<div><div>Efficient energy management and grid stability strongly rely on accurate Short-Term Load Forecasting (STLF). Existing forecasting models, unfortunately, are often inaccurate and computationally demanding. To overcome these challenges, a novel hybrid model, combining both linear regression and machine learning techniques, is proposed in this study. The hybrid model, MLR-LSTM-FFNN, captures both temporal and non-linear dependencies in load data by integrating multi-linear regression (MLR) with long short-term memory (LSTM) networks and feed-forward neural networks (FFNN). Using datasets from Qatar, with 5 min, 15 min, 30 min, and 1 h time intervals and from Panama City with a 1 h interval, experiments were conducted to thoroughly test the robustness of the model. The results showed that the MLR-LSTM-FFNN hybrid model outperformed the baseline and state-of-the-art hybrid models for each of the datasets, in terms of lower RMSE, MAE, and MAPE values along with a faster training time. This superior performance across different datasets underscores the model’s scalability and reliability as an STLF approach, providing a practical solution to energy demand prediction tasks. The improvement in short-term forecasting accuracy provides utilities with a practical tool to optimize demand-side management, reduce operational costs, and enhance grid reliability.</div></div>","PeriodicalId":34138,"journal":{"name":"Energy and AI","volume":"22 ","pages":"Article 100625"},"PeriodicalIF":9.6,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145219589","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Presolving convexified optimal power flow with mixtures of gradient experts 梯度专家混合求解凸型最优潮流

IF 9.6 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Energy and AI

Pub Date : 2025-09-22 DOI: 10.1016/j.egyai.2025.100609

Shourya Bose, Kejun Chen, Yu Zhang

Convex relaxations and approximations of the optimal power flow (OPF) problem have gained significant research and industrial interest for planning and operations in electric power networks. One approach for reducing their solve times is presolving which eliminates constraints from the problem definition, thereby reducing the burden of the underlying optimization algorithm. To this end, we propose a presolving framework for convexified optimal power flow (C-OPF) problems, which uses a novel deep learning-based architecture called

M o G E

(Mixture of Gradient Experts). In this framework, problem size is reduced by learning the mapping between C-OPF parameters and optimal dual variables (the latter being representable as gradients), which is then used to screen constraints that are non-binding at optimum. The validity of using this presolve framework across arbitrary families of C-OPF problems is theoretically demonstrated. We characterize generalization in

M o G E

and develop a post-solve recovery procedure to mitigate possible constraint classification errors. Using two different C-OPF models, we show via simulations that our framework reduces solve times by upto 34% across multiple PGLIB and MATPOWER test cases, while providing an identical solution as the full problem.

最优潮流（OPF）问题的凸松弛和逼近在电网规划和运行中获得了重要的研究和工业兴趣。减少求解时间的一种方法是求解，它消除了问题定义中的约束，从而减少了底层优化算法的负担。为此，我们提出了一个求解凸最优潮流（C-OPF）问题的框架，该框架使用了一种新的基于深度学习的架构，称为MoGE（混合梯度专家）。在这个框架中，通过学习C-OPF参数和最优对偶变量（后者可以表示为梯度）之间的映射来减少问题的规模，然后使用该对偶变量来筛选最优时非绑定的约束。从理论上证明了该求解框架在任意C-OPF问题族中的有效性。我们描述了MoGE的泛化特征，并开发了一个解后恢复程序来减轻可能的约束分类错误。使用两种不同的C-OPF模型，我们通过模拟表明，我们的框架在多个PGLIB和MATPOWER测试用例中减少了高达34%的解决时间，同时提供了与完整问题相同的解决方案。

{"title":"Presolving convexified optimal power flow with mixtures of gradient experts","authors":"Shourya Bose, Kejun Chen, Yu Zhang","doi":"10.1016/j.egyai.2025.100609","DOIUrl":"10.1016/j.egyai.2025.100609","url":null,"abstract":"<div><div>Convex relaxations and approximations of the optimal power flow (OPF) problem have gained significant research and industrial interest for planning and operations in electric power networks. One approach for reducing their solve times is <em>presolving</em> which eliminates constraints from the problem definition, thereby reducing the burden of the underlying optimization algorithm. To this end, we propose a presolving framework for convexified optimal power flow (C-OPF) problems, which uses a novel deep learning-based architecture called <span><math><mstyle><mi>M</mi><mi>o</mi><mi>G</mi><mi>E</mi></mstyle></math></span> (Mixture of Gradient Experts). In this framework, problem size is reduced by learning the mapping between C-OPF parameters and optimal dual variables (the latter being representable as gradients), which is then used to screen constraints that are non-binding at optimum. The validity of using this presolve framework across arbitrary families of C-OPF problems is theoretically demonstrated. We characterize generalization in <span><math><mstyle><mi>M</mi><mi>o</mi><mi>G</mi><mi>E</mi></mstyle></math></span> and develop a post-solve recovery procedure to mitigate possible constraint classification errors. Using two different C-OPF models, we show via simulations that our framework reduces solve times by upto 34% across multiple PGLIB and MATPOWER test cases, while providing an identical solution as the full problem.</div></div>","PeriodicalId":34138,"journal":{"name":"Energy and AI","volume":"22 ","pages":"Article 100609"},"PeriodicalIF":9.6,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145219588","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An integrated agent-based modelling and artificial intelligence framework for enhancing the experience of minority ethnic communities in digital energy services 一个集成的基于主体的建模和人工智能框架，用于增强少数民族社区在数字能源服务中的体验

IF 9.6 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Energy and AI

Pub Date : 2025-09-22 DOI: 10.1016/j.egyai.2025.100624

Mennan Guder, Nazmiye Balta-Ozkan

Digitalisation plays a pivotal role in enhancing energy efficiency; however, it also highlights significant governance challenges and exacerbates various forms of energy injustice. This study explores how technological injustice exacerbates energy poverty, particularly via disparities in digital service access. The focus is on understanding and addressing challenges faced by minority ethnic (ME) communities, who often encounter heightened barriers to essential online energy services. While previous research has noted barriers ME communities face in energy markets, this study broadens this literature to analyse these issues for access to digital energy services.

The study integrates modelling, simulation, and AI to address these inequalities. The framework comprises three core modules: AI, Environment Configuration, and Agent-Based Modelling (ABM) and Simulation. Its primary aim is to identify effective strategies, policy changes, and adjustments that enhance online service experiences while addressing the unique challenges faced by these communities.

The AI Module uses ensemble-based ML pipelines to develop region-specific models. It addresses issues such as high dimensionality and overfitting by incorporating methods like Principal Component Analysis, Recursive Feature Elimination, and hyperparameter optimization.

The Environment Configuration Module supports tailored simulations by adapting datasets and regional characteristics, ensuring the accuracy and relevance of the simulations to the target communities.

The ABM and Simulation Module facilitates in-depth analysis of policy impacts and service provider attributes.

This framework offers valuable insights into improving online service delivery, promoting fairness, and addressing disparities in digital experiences. This work advances energy justice research by quantifying how socio-technical barriers disproportionately affect ME communities.

数字化在提高能源效率方面发挥着关键作用；然而，它也凸显了重大的治理挑战，并加剧了各种形式的能源不公平。本研究探讨了技术不公正如何加剧能源贫困，特别是通过数字服务获取方面的差异。重点是了解和解决少数民族（ME）社区面临的挑战，他们在获得基本的在线能源服务方面经常遇到更高的障碍。虽然以前的研究已经注意到中小企业社区在能源市场上面临的障碍，但本研究扩大了这一文献，分析了这些问题，以获得数字能源服务。该研究整合了建模、仿真和人工智能来解决这些不平等问题。该框架包括三个核心模块：人工智能、环境配置和基于代理的建模（ABM）和仿真。其主要目的是确定有效的战略、政策变化和调整，以增强在线服务体验，同时解决这些社区面临的独特挑战。AI模块使用基于集成的ML管道来开发特定区域的模型。它通过结合主成分分析、递归特征消除和超参数优化等方法来解决诸如高维数和过拟合等问题。环境配置模块通过调整数据集和区域特征来支持量身定制的模拟，确保模拟与目标社区的准确性和相关性。ABM和仿真模块有助于对策略影响和服务提供者属性进行深入分析。该框架为改善在线服务交付、促进公平和解决数字体验中的差异提供了宝贵的见解。这项工作通过量化社会技术障碍如何不成比例地影响ME社区来推进能源正义研究。

{"title":"An integrated agent-based modelling and artificial intelligence framework for enhancing the experience of minority ethnic communities in digital energy services","authors":"Mennan Guder, Nazmiye Balta-Ozkan","doi":"10.1016/j.egyai.2025.100624","DOIUrl":"10.1016/j.egyai.2025.100624","url":null,"abstract":"<div><div>Digitalisation plays a pivotal role in enhancing energy efficiency; however, it also highlights significant governance challenges and exacerbates various forms of energy injustice. This study explores how technological injustice exacerbates energy poverty, particularly via disparities in digital service access. The focus is on understanding and addressing challenges faced by minority ethnic (ME) communities, who often encounter heightened barriers to essential online energy services. While previous research has noted barriers ME communities face in energy markets, this study broadens this literature to analyse these issues for access to digital energy services.</div><div>The study integrates modelling, simulation, and AI to address these inequalities. The framework comprises three core modules: AI, Environment Configuration, and Agent-Based Modelling (ABM) and Simulation. Its primary aim is to identify effective strategies, policy changes, and adjustments that enhance online service experiences while addressing the unique challenges faced by these communities.</div><div>The AI Module uses ensemble-based ML pipelines to develop region-specific models. It addresses issues such as high dimensionality and overfitting by incorporating methods like Principal Component Analysis, Recursive Feature Elimination, and hyperparameter optimization.</div><div>The Environment Configuration Module supports tailored simulations by adapting datasets and regional characteristics, ensuring the accuracy and relevance of the simulations to the target communities.</div><div>The ABM and Simulation Module facilitates in-depth analysis of policy impacts and service provider attributes.</div><div>This framework offers valuable insights into improving online service delivery, promoting fairness, and addressing disparities in digital experiences. This work advances energy justice research by quantifying how socio-technical barriers disproportionately affect ME communities.</div></div>","PeriodicalId":34138,"journal":{"name":"Energy and AI","volume":"22 ","pages":"Article 100624"},"PeriodicalIF":9.6,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145220301","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Explainable and generalizable AI for AGC dispatch with heterogeneous generation units: A case study using graph convolutional networks 具有异构发电单元的AGC调度的可解释和可推广的人工智能：使用图卷积网络的案例研究

IF 9.6 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Energy and AI

Pub Date : 2025-09-19 DOI: 10.1016/j.egyai.2025.100621

Xiaoshun Zhang , Kun Zhang , Zhengxun Guo , Penggen Wang , Penghui Xiong , Mingyu Wang

Automatic generation control (AGC) dispatch is essential for maintaining frequency stability and power balance in modern grids with high renewable penetration. Conventional optimization and machine learning methods either incur heavy computational costs or act as black-box models, which limits interpretability and generalization in safety–critical operations. To overcome these gaps, we propose an explainable and generalizable framework that integrates graph convolutional networks (GCNs) with Shapley additive explanations (SHAP). SHAP provides quantitative feature attributions, revealing spatiotemporal variability and redundancy, while the derived insights are used to iteratively optimize the GCN adjacency matrix and capture inter-generator dependencies more effectively. This closed-loop design enhances both model transparency and robustness. Case studies on a two-area load frequency control (LFC) system and a provincial power grid in China show consistent improvements: in the LFC model, frequency deviation, power deviation, and ACE are reduced by 14.30%, 58.95%, and 29.22%, respectively; in the provincial grid, ACE overshoot decreases by 99.52%, frequency deviation by 80.67%, and power overshoot is eliminated, with correction distance reduced by up to 55.24%. These results demonstrate that explainability-driven graph learning can significantly improve the reliability and adaptability of AI-based AGC dispatch in complex, heterogeneous power systems.

在可再生能源普及率高的现代电网中，自动发电控制（AGC）调度对于保持频率稳定和功率平衡至关重要。传统的优化和机器学习方法要么产生大量的计算成本，要么充当黑盒模型，这限制了安全关键操作的可解释性和通用性。为了克服这些差距，我们提出了一个可解释和可推广的框架，该框架将图卷积网络（GCNs）与Shapley加性解释（SHAP）集成在一起。SHAP提供定量特征归因，揭示时空变异性和冗余，而派生的见解用于迭代优化GCN邻接矩阵并更有效地捕获生成器之间的依赖关系。这种闭环设计提高了模型透明性和鲁棒性。两区负荷频率控制（LFC）系统和中国省级电网的案例研究表明，在LFC模型下，频率偏差、功率偏差和ACE分别降低了14.30%、58.95%和29.22%；省网ACE超调减小99.52%，频率偏差减小80.67%，消除功率超调，校正距离减小55.24%。这些结果表明，可解释性驱动的图学习可以显著提高复杂异构电力系统中基于ai的AGC调度的可靠性和适应性。

{"title":"Explainable and generalizable AI for AGC dispatch with heterogeneous generation units: A case study using graph convolutional networks","authors":"Xiaoshun Zhang , Kun Zhang , Zhengxun Guo , Penggen Wang , Penghui Xiong , Mingyu Wang","doi":"10.1016/j.egyai.2025.100621","DOIUrl":"10.1016/j.egyai.2025.100621","url":null,"abstract":"<div><div>Automatic generation control (AGC) dispatch is essential for maintaining frequency stability and power balance in modern grids with high renewable penetration. Conventional optimization and machine learning methods either incur heavy computational costs or act as black-box models, which limits interpretability and generalization in safety–critical operations. To overcome these gaps, we propose an explainable and generalizable framework that integrates graph convolutional networks (GCNs) with Shapley additive explanations (SHAP). SHAP provides quantitative feature attributions, revealing spatiotemporal variability and redundancy, while the derived insights are used to iteratively optimize the GCN adjacency matrix and capture inter-generator dependencies more effectively. This closed-loop design enhances both model transparency and robustness. Case studies on a two-area load frequency control (LFC) system and a provincial power grid in China show consistent improvements: in the LFC model, frequency deviation, power deviation, and ACE are reduced by 14.30%, 58.95%, and 29.22%, respectively; in the provincial grid, ACE overshoot decreases by 99.52%, frequency deviation by 80.67%, and power overshoot is eliminated, with correction distance reduced by up to 55.24%. These results demonstrate that explainability-driven graph learning can significantly improve the reliability and adaptability of AI-based AGC dispatch in complex, heterogeneous power systems.</div></div>","PeriodicalId":34138,"journal":{"name":"Energy and AI","volume":"22 ","pages":"Article 100621"},"PeriodicalIF":9.6,"publicationDate":"2025-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145118543","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Energy-GNoME: A living database of selected materials for energy applications energy - gnome：能源应用中选定材料的活数据库

IF 9.6 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Energy and AI

Pub Date : 2025-09-16 DOI: 10.1016/j.egyai.2025.100605

Paolo De Angelis , Giulio Barletta , Giovanni Trezza , Pietro Asinari , Eliodoro Chiavazzo

Artificial Intelligence (AI) in materials science is driving significant advancements in the discovery of advanced materials for energy applications. The recent GNoME protocol identifies over 380,000 novel stable crystals. From this, we identify over 38,500 materials with potential as energy materials forming the core of the Energy-GNoME database. Our unique combination of Machine Learning (ML) and Deep Learning (DL) tools mitigates cross-domain data bias using feature spaces, thus identifying potential candidates for thermoelectric materials, novel battery cathodes, and novel perovskites. First, classifiers with both structural and compositional features detect domains of applicability, where we expect enhanced reliability of regressors. Here, regressors are trained to predict key materials properties, like thermoelectric figure of merit (

z T

), band gap (

E_{g}

), and cathode voltage (

Δ V_{c}

). This method significantly narrows the pool of potential candidates, serving as an efficient guide for experimental and computational chemistry investigations and accelerating the discovery of materials suited for electricity generation, energy storage and conversion.

材料科学中的人工智能（AI）正在推动能源应用先进材料的发现取得重大进展。最近的GNoME协议确定了超过38万个新的稳定晶体。由此，我们确定了超过38,500种有潜力成为能源材料的材料，形成了energy - gnome数据库的核心。我们独特的机器学习（ML）和深度学习（DL）工具组合使用特征空间减轻了跨域数据偏差，从而确定了热电材料、新型电池阴极和新型钙钛矿的潜在候选材料。首先，具有结构和组成特征的分类器检测适用性领域，我们期望在这些领域增强回归器的可靠性。在这里，回归量被训练来预测关键的材料性能，如热电性能图（zT）、带隙（Eg）和阴极电压（ΔVc）。这种方法大大缩小了潜在候选材料的范围，为实验和计算化学研究提供了有效的指导，并加速了适合发电、储能和转换的材料的发现。

{"title":"Energy-GNoME: A living database of selected materials for energy applications","authors":"Paolo De Angelis , Giulio Barletta , Giovanni Trezza , Pietro Asinari , Eliodoro Chiavazzo","doi":"10.1016/j.egyai.2025.100605","DOIUrl":"10.1016/j.egyai.2025.100605","url":null,"abstract":"<div><div>Artificial Intelligence (AI) in materials science is driving significant advancements in the discovery of advanced materials for energy applications. The recent GNoME protocol identifies over 380,000 novel stable crystals. From this, we identify over 38,500 materials with potential as energy materials forming the core of the Energy-GNoME database. Our unique combination of Machine Learning (ML) and Deep Learning (DL) tools mitigates cross-domain data bias using feature spaces, thus identifying potential candidates for thermoelectric materials, novel battery cathodes, and novel perovskites. First, classifiers with both structural and compositional features detect domains of applicability, where we expect enhanced reliability of regressors. Here, regressors are trained to predict key materials properties, like thermoelectric figure of merit (<span><math><mrow><mi>z</mi><mi>T</mi></mrow></math></span>), band gap (<span><math><msub><mrow><mi>E</mi></mrow><mrow><mi>g</mi></mrow></msub></math></span>), and cathode voltage (<span><math><mrow><mi>Δ</mi><msub><mrow><mi>V</mi></mrow><mrow><mi>c</mi></mrow></msub></mrow></math></span>). This method significantly narrows the pool of potential candidates, serving as an efficient guide for experimental and computational chemistry investigations and accelerating the discovery of materials suited for electricity generation, energy storage and conversion.</div></div>","PeriodicalId":34138,"journal":{"name":"Energy and AI","volume":"22 ","pages":"Article 100605"},"PeriodicalIF":9.6,"publicationDate":"2025-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145096080","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Sequential constrained optimization for multi-entity operation of integrated electricity-gas distribution systems 电-气一体化系统多实体运行的序贯约束优化

IF 9.6 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Energy and AI

Pub Date : 2025-09-13 DOI: 10.1016/j.egyai.2025.100619

Yeong Geon Son, Sung-Yul Kim

The reliable and coordinated operation of energy systems is becoming increasingly important as renewable energy penetration grows and electricity and gas infrastructures become more interconnected. This study addresses the challenge of aligning multiple stakeholders’ objectives in integrated electricity and gas distribution systems by proposing a sequential constrained optimization method. The method solves the multi-objective optimization problem by sequentially prioritizing each entity’s objective while incorporating others as adaptive-weighted sub-objectives and constraints. This process ensures that all entities participate in a fair and balanced decision-making procedure, ultimately converging to a consensus-based solution. The algorithm is validated using IEEE 33-bus and 118-bus test systems coupled with gas networks. Results show that the proposed method improves optimal resource allocation effectiveness by up to 3.66 compared to individual-objective or aggregated-objective benchmarks. Specifically, the method achieves performance improvements ranging from 0.02 pu to 1.7 pu across four distinct entities, highlighting its superiority in balancing conflicting operational goals. Moreover, the method demonstrates low computational delay and converges in fewer than 15 iterations for all tested cases. The algorithm adapts flexibly to different system configurations and maintains solution stability even under asymmetric stakeholder preferences. These findings indicate that the proposed sequential constrained optimization framework is a scalable and effective approach for equitable, multi-agent coordination in integrated multi-energy systems.

随着可再生能源普及率的提高以及电力和天然气基础设施的相互联系日益紧密，能源系统的可靠和协调运行变得越来越重要。本研究通过提出一种顺序约束优化方法，解决了在综合电力和天然气分配系统中协调多个利益相关者目标的挑战。该方法通过对每个实体的目标进行排序，同时将其他实体的目标作为自适应加权子目标和约束，解决了多目标优化问题。这一进程确保所有实体参与公平和平衡的决策程序，最终达成基于协商一致的解决办法。采用IEEE 33总线和118总线测试系统，结合燃气网络对算法进行了验证。结果表明，与个体目标基准和聚合目标基准相比，所提方法的最优资源分配效率提高了3.66。具体来说，该方法在四个不同的实体上实现了从0.02到1.7 pu的性能改进，突出了其在平衡冲突的操作目标方面的优势。此外，该方法具有较低的计算延迟，并且在所有测试用例的15次迭代以内收敛。该算法能够灵活适应不同的系统配置，即使在利益相关者偏好不对称的情况下也能保持解的稳定性。这些结果表明，所提出的顺序约束优化框架是一种可扩展且有效的方法，可用于集成多能系统中公平的多智能体协调。

{"title":"Sequential constrained optimization for multi-entity operation of integrated electricity-gas distribution systems","authors":"Yeong Geon Son, Sung-Yul Kim","doi":"10.1016/j.egyai.2025.100619","DOIUrl":"10.1016/j.egyai.2025.100619","url":null,"abstract":"<div><div>The reliable and coordinated operation of energy systems is becoming increasingly important as renewable energy penetration grows and electricity and gas infrastructures become more interconnected. This study addresses the challenge of aligning multiple stakeholders’ objectives in integrated electricity and gas distribution systems by proposing a sequential constrained optimization method. The method solves the multi-objective optimization problem by sequentially prioritizing each entity’s objective while incorporating others as adaptive-weighted sub-objectives and constraints. This process ensures that all entities participate in a fair and balanced decision-making procedure, ultimately converging to a consensus-based solution. The algorithm is validated using IEEE 33-bus and 118-bus test systems coupled with gas networks. Results show that the proposed method improves optimal resource allocation effectiveness by up to 3.66 compared to individual-objective or aggregated-objective benchmarks. Specifically, the method achieves performance improvements ranging from 0.02 pu to 1.7 pu across four distinct entities, highlighting its superiority in balancing conflicting operational goals. Moreover, the method demonstrates low computational delay and converges in fewer than 15 iterations for all tested cases. The algorithm adapts flexibly to different system configurations and maintains solution stability even under asymmetric stakeholder preferences. These findings indicate that the proposed sequential constrained optimization framework is a scalable and effective approach for equitable, multi-agent coordination in integrated multi-energy systems.</div></div>","PeriodicalId":34138,"journal":{"name":"Energy and AI","volume":"22 ","pages":"Article 100619"},"PeriodicalIF":9.6,"publicationDate":"2025-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145118544","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Predictive maintenance for wind turbines: A physics-driven reinforcement learning strategy with economic-reliability collaborative optimization 风力涡轮机的预测性维护：具有经济可靠性协同优化的物理驱动强化学习策略

IF 9.6 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Energy and AI

Pub Date : 2025-09-13 DOI: 10.1016/j.egyai.2025.100620

Jianghao Zhu , Wei Chen , Le Su , Bin Lan , Tingting Pei , Long Jin

Wind turbine maintenance optimization faces challenges in balancing economic efficiency with operational reliability under environmental uncertainty. Traditional maintenance approaches exhibit limitations in adaptive decision-making, leading to increased operational costs and reliability risks. This study develops a physics-informed reinforcement learning framework that integrates established domain knowledge with adaptive decision algorithms. The approach embeds physical principles—including Weibull wind dynamics and multi-stage degradation models—into a reinforcement learning architecture, while introducing bidirectional temperature-degradation coupling for enhanced failure prediction. A high-fidelity simulation environment enables policy training through Proximal Policy Optimization, capturing complex interactions between environmental variability and equipment deterioration. The framework was validated through case study implementation using northern China wind farm operational data. Results demonstrate zero-failure operation over simulated 19-year lifecycles, with economic performance improvements of 109.3 % and 54.5 % compared to conventional periodic and threshold-based maintenance strategies. By integrating physical constraints with intelligent algorithms, the method achieves adaptive maintenance decisions based on multi-dimensional state information.

在环境不确定性条件下，风电机组维护优化面临着平衡经济效益与运行可靠性的挑战。传统的维护方法在自适应决策方面存在局限性，导致运营成本和可靠性风险增加。本研究开发了一个基于物理的强化学习框架，该框架将已建立的领域知识与自适应决策算法集成在一起。该方法将物理原理（包括威布尔风动力学和多阶段退化模型）嵌入到强化学习架构中，同时引入双向温度-退化耦合以增强故障预测。高保真仿真环境通过近端策略优化实现策略训练，捕获环境可变性和设备退化之间的复杂相互作用。通过对中国北方风电场运行数据的案例研究，对该框架进行了验证。结果表明，在模拟的19年生命周期内，零故障运行，与传统的定期和基于阈值的维护策略相比，经济性能提高了109.3%和54.5%。该方法将物理约束与智能算法相结合，实现了基于多维状态信息的自适应维修决策。

{"title":"Predictive maintenance for wind turbines: A physics-driven reinforcement learning strategy with economic-reliability collaborative optimization","authors":"Jianghao Zhu , Wei Chen , Le Su , Bin Lan , Tingting Pei , Long Jin","doi":"10.1016/j.egyai.2025.100620","DOIUrl":"10.1016/j.egyai.2025.100620","url":null,"abstract":"<div><div>Wind turbine maintenance optimization faces challenges in balancing economic efficiency with operational reliability under environmental uncertainty. Traditional maintenance approaches exhibit limitations in adaptive decision-making, leading to increased operational costs and reliability risks. This study develops a physics-informed reinforcement learning framework that integrates established domain knowledge with adaptive decision algorithms. The approach embeds physical principles—including Weibull wind dynamics and multi-stage degradation models—into a reinforcement learning architecture, while introducing bidirectional temperature-degradation coupling for enhanced failure prediction. A high-fidelity simulation environment enables policy training through Proximal Policy Optimization, capturing complex interactions between environmental variability and equipment deterioration. The framework was validated through case study implementation using northern China wind farm operational data. Results demonstrate zero-failure operation over simulated 19-year lifecycles, with economic performance improvements of 109.3 % and 54.5 % compared to conventional periodic and threshold-based maintenance strategies. By integrating physical constraints with intelligent algorithms, the method achieves adaptive maintenance decisions based on multi-dimensional state information.</div></div>","PeriodicalId":34138,"journal":{"name":"Energy and AI","volume":"22 ","pages":"Article 100620"},"PeriodicalIF":9.6,"publicationDate":"2025-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145096069","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0