Pub Date : 2025-09-23DOI: 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.
{"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}
Pub Date : 2025-09-23DOI: 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.
{"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}
Pub Date : 2025-09-22DOI: 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 (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 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.
{"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}
Pub Date : 2025-09-22DOI: 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.
{"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}
Pub Date : 2025-09-19DOI: 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.
{"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}
Pub Date : 2025-09-16DOI: 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 (), band gap (), and cathode voltage (). 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.
{"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}
Pub Date : 2025-09-13DOI: 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.
{"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}
Pub Date : 2025-09-13DOI: 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.
{"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}
Most distribution system operators may not accurately record or completely maintain the phase connections for the numerous LV customers. Different consumer phase identification (CPI) approaches based on voltages, powers or other measurements are proposed in the literature. Due to the technical challenges in collecting voltage measurements, power measurement based approaches are preferable. Hence, this paper proposes a novel power based CPI methodology applying Graph Neural Networks (GNNs). The CPI methodology generates synthetic transformer power profiles assuming random combinations of phases for the measured load profiles, which are used altogether to train the GNN model. The GNN model is then tested using measured transformer and load power profiles. The performance of the methodology is evaluated in a test low voltage grid of 55 loads under various conditions of Photovoltaic penetration, Photovoltaics under maintenance, measurement errors, unmetered consumption, uncertain grid asset parameters and inaccurate phase connections. Further tests on a real low voltage grid with 111 loads prove the scalability of the methodology. The attained results show that the GNN model can achieve accuracy above 90% in most cases, outperforming various state-of-the-art methods.
{"title":"Consumer phase identification in distribution grids using Graph Neural Networks based on synthetic and measured power profiles","authors":"Chandra Sekhar Charan Dande , Nikolaos A. Efkarpidis , Matthias Christen , Mirko Ginocchi , Antonello Monti","doi":"10.1016/j.egyai.2025.100607","DOIUrl":"10.1016/j.egyai.2025.100607","url":null,"abstract":"<div><div>Most distribution system operators may not accurately record or completely maintain the phase connections for the numerous LV customers. Different consumer phase identification (CPI) approaches based on voltages, powers or other measurements are proposed in the literature. Due to the technical challenges in collecting voltage measurements, power measurement based approaches are preferable. Hence, this paper proposes a novel power based CPI methodology applying Graph Neural Networks (GNNs). The CPI methodology generates synthetic transformer power profiles assuming random combinations of phases for the measured load profiles, which are used altogether to train the GNN model. The GNN model is then tested using measured transformer and load power profiles. The performance of the methodology is evaluated in a test low voltage grid of 55 loads under various conditions of Photovoltaic penetration, Photovoltaics under maintenance, measurement errors, unmetered consumption, uncertain grid asset parameters and inaccurate phase connections. Further tests on a real low voltage grid with 111 loads prove the scalability of the methodology. The attained results show that the GNN model can achieve accuracy above 90% in most cases, outperforming various state-of-the-art methods.</div></div>","PeriodicalId":34138,"journal":{"name":"Energy and AI","volume":"22 ","pages":"Article 100607"},"PeriodicalIF":9.6,"publicationDate":"2025-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145045867","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}
Pub Date : 2025-09-10DOI: 10.1016/j.egyai.2025.100614
Javad Enayati , Pedram Asef , Alexandre Benoit
This paper introduces a novel hybrid method combining H- filtering and an adaptive linear neuron (ADALINE) network for flicker component estimation in power distribution systems. The proposed method leverages the robustness of the H- filter to extract the voltage envelope under uncertain and noisy conditions, followed by the use of ADALINE to accurately identify the relative amplitudes of flicker components () at standard IEC-defined frequencies embedded in the envelope. This synergy enables efficient time-domain estimation with rapid convergence and noise resilience, addressing key limitations of existing frequency-domain approaches. Unlike conventional techniques, this hybrid model handles complex power disturbances without prior knowledge of noise characteristics or extensive training. To validate the method’s performance, we conduct simulation studies based on IEC Standard 61000-4-15, supported by statistical analysis, Monte Carlo simulations, and real-world data. Results demonstrate superior accuracy, robustness, and reduced computational load compared to Fast Fourier Transform (FFT) and Discrete Wavelet Transform (DWT)-based estimators.
{"title":"A hybrid Artificial Intelligence method for estimating flicker in power systems","authors":"Javad Enayati , Pedram Asef , Alexandre Benoit","doi":"10.1016/j.egyai.2025.100614","DOIUrl":"10.1016/j.egyai.2025.100614","url":null,"abstract":"<div><div>This paper introduces a novel hybrid method combining H-<span><math><mi>∞</mi></math></span> filtering and an adaptive linear neuron (ADALINE) network for flicker component estimation in power distribution systems. The proposed method leverages the robustness of the H-<span><math><mi>∞</mi></math></span> filter to extract the voltage envelope under uncertain and noisy conditions, followed by the use of ADALINE to accurately identify the relative amplitudes of flicker components (<span><math><mrow><mi>Δ</mi><msub><mrow><mi>V</mi></mrow><mrow><mi>i</mi></mrow></msub><mo>/</mo><msub><mrow><mi>V</mi></mrow><mrow><mi>t</mi></mrow></msub></mrow></math></span>) at standard IEC-defined frequencies embedded in the envelope. This synergy enables efficient time-domain estimation with rapid convergence and noise resilience, addressing key limitations of existing frequency-domain approaches. Unlike conventional techniques, this hybrid model handles complex power disturbances without prior knowledge of noise characteristics or extensive training. To validate the method’s performance, we conduct simulation studies based on IEC Standard 61000-4-15, supported by statistical analysis, Monte Carlo simulations, and real-world data. Results demonstrate superior accuracy, robustness, and reduced computational load compared to Fast Fourier Transform (FFT) and Discrete Wavelet Transform (DWT)-based estimators.</div></div>","PeriodicalId":34138,"journal":{"name":"Energy and AI","volume":"22 ","pages":"Article 100614"},"PeriodicalIF":9.6,"publicationDate":"2025-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145045869","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}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号