{"title":"Lithium-Ion Battery State-of-Charge and State-of-Energy Simultaneous Estimation via Sparse- Quasi Recurrent Neural Networks(S-QRNN)","authors":"Sakshi Sharma;Bijaya Ketan Panigrahi","doi":"10.1109/TIA.2024.3522506","DOIUrl":"https://doi.org/10.1109/TIA.2024.3522506","url":null,"abstract":"This paper presents an innovative methodology for the concurrent estimation of Lithium-Ion Battery (LiB) State-of-Charge (SoC) and State-of-Energy (SoE) employing Sparse Quasi-Recurrent Neural Networks (S-QRNN). The proposed framework is designed to leverage sparse connectivity patterns to efficiently capture intricate long-term dependencies within battery dynamics. Unlike traditional recurrent neural networks and Convolutional Networks, S-QRNN allows for more effective handling of sequential data, making them well-suited for predicting battery behavior, which exhibits complex temporal dynamics. Furthermore, the sparse connectivity structure reduces computational complexity and enhances the interpretability of the model. To validate the effectiveness and accuracy, adequate experimentation was conducted using laboratory-produced battery data. Moreover, the accuracy and computational efficacy of the proposed scheme have been verified in an OPAL-RT-based Real-Time Power Hardware-In-Loop (HIL) environment. The Opal RT platform provides a reliable and flexible environment integrated with MATLAB/Simulink for hardware-in-loop simulation. Experimental results demonstrate that the proposed method achieves robust and accurate estimation of both SoC and SoE, even in dynamic operational conditions of temperatures and battery load profiles.","PeriodicalId":13337,"journal":{"name":"IEEE Transactions on Industry Applications","volume":"61 1","pages":"774-783"},"PeriodicalIF":4.2,"publicationDate":"2024-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143396299","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}
{"title":"Hybrid Knowledge and Data-Driven Hydrogen Trading for Renewable-Dominated Hydrogen Refueling Stations","authors":"Kuan Zhang;Junyu Xie;Nian Liu","doi":"10.1109/TIA.2024.3522508","DOIUrl":"https://doi.org/10.1109/TIA.2024.3522508","url":null,"abstract":"This paper proposes a hybrid knowledge and data-driven predict-then-optimize paradigm for green hydrogen (H<sub>2</sub>) trading among renewable-dominated hydrogen refueling stations (HRSs). Firstly, a data-driven H<sub>2</sub> load forecasting method is formulated where the key influencing features are captured by XGBoost and the Informer algorithm with encoder and decoder processes is utilized to generate the predicted time series of hydrogen load. Then, a bi-level hybrid knowledge and data-driven H<sub>2</sub> trading model with rolling horizon optimization is proposed to determine the optimal trading quantity of H<sub>2</sub> and dynamically optimize the transportation routes for the traded H<sub>2</sub> based on the cell transmission model and traffic state. Moreover, a fully distributed solution algorithm is developed to decompose the complex multi-period H<sub>2</sub> trading problem into local electricity and hydrogen dispatch subproblems of HRSs for efficiently obtaining the optimal H<sub>2</sub> trading amount. Comparative studies have demonstrated the superior performance of the proposed methodology on the improvement of the distributed renewable energy accommodation and economic benefits for HRSs.","PeriodicalId":13337,"journal":{"name":"IEEE Transactions on Industry Applications","volume":"61 1","pages":"1658-1674"},"PeriodicalIF":4.2,"publicationDate":"2024-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143106879","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}
Shyamal S. Chand;Branislav Hredzak;Majid Farhangi;Ravneel Prasad;Dhirendran Munith Kumar;Adriano Fagiolini;Marco Di Benedetto;Hiye K. Mudaliar;Maurizio Cirrincione
{"title":"Adaptive Control of Grid-Following Inverter-Based Resources Under Low Network Short Circuit Ratio","authors":"Shyamal S. Chand;Branislav Hredzak;Majid Farhangi;Ravneel Prasad;Dhirendran Munith Kumar;Adriano Fagiolini;Marco Di Benedetto;Hiye K. Mudaliar;Maurizio Cirrincione","doi":"10.1109/TIA.2024.3522209","DOIUrl":"https://doi.org/10.1109/TIA.2024.3522209","url":null,"abstract":"The stability and dynamic response of inverter-based resources are greatly influenced by uncertain grid parameters. The grid short circuit ratio (SCR) serves as a standard metric for assessing the strength of the network at any location within the electrical power network. A high SCR suggests a strong grid, whereas a low SCR indicates a fragile grid, more prone to disturbances and likely to affect the stability of grid-feeding inverters. Weak grids may lead to extended oscillatory periods in the injected currents at the point of common coupling and compromise the DC link voltage integrity. This research introduces a feedforward adaptive control scheme that operates alongside the current loop proportional-integral controllers, producing a compensating voltage to guarantee the dependable functioning of the voltage-oriented controlled inverters in extremely weak grid scenarios. The adaptive compensator is formulated on the basis of the deadbeat control principle and utilizes the information of the grid impedance to determine the feedforward voltage in real time. Comparative results demonstrate the effectiveness of this method in damping oscillations and shortening the settling time for the DC link voltage, active and reactive power in low SCR grids under transients and faults while minimizing the current total harmonic distortion. The proposed adaptive feedforward control strategy is also experimentally verified on a low voltage test rig under several dynamic conditions including transients, varying operating setpoints, and low voltage ride-through.","PeriodicalId":13337,"journal":{"name":"IEEE Transactions on Industry Applications","volume":"61 2","pages":"1828-1838"},"PeriodicalIF":4.2,"publicationDate":"2024-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143769562","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}
{"title":"Bi-Level Planning of Microgrid Considering Seasonal Hydrogen Storage and Efficiency Degradation of Electrolyzer","authors":"Yanhui Xu;Zilin Deng","doi":"10.1109/TIA.2024.3522458","DOIUrl":"https://doi.org/10.1109/TIA.2024.3522458","url":null,"abstract":"Microgrids that contain a high percentage of renewable energy face the challenge of having insufficient resources for long-term regulation of the energy balance. Seasonal hydrogen storage emerges as a promising option. To analyze the feasibility and economic viability of seasonal hydrogen storage in microgrids, this paper proposes a bi-level planning approach. First, considering the dynamic characteristics of electrolyzer power-efficiency-degradation, a linearized method for calculating the dynamic efficiency is proposed. Taking into account the randomness of the data, a data-driven Markov Chain Monte Carlo method is used to generate typical daily time series. The upper level of the bi-level model focuses on investment decisions for electrolyzer capacity and seasonal hydrogen storage, while the lower level optimizes system operational revenue and electrolyzer usage costs. Then, addressing the nonlinear term issue in optimization calculations, a piecewise McCormick envelope method considering the power characteristics of the electrolyzer is proposed to convexify the optimization problem. The results of the case study show that the proposed planning method can increase the annual revenue by 11% and 595% compared to only considering constant efficiency and fixed electrolyzer lifespan. Additionally, the convex relaxation method enhances convergence speed while maintaining solution accuracy.","PeriodicalId":13337,"journal":{"name":"IEEE Transactions on Industry Applications","volume":"61 1","pages":"1385-1398"},"PeriodicalIF":4.2,"publicationDate":"2024-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143106953","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}
{"title":"Knowledge-Inspired Data-Aided Robust Power Flow in Distribution Networks With ZIP Loads and High DER Penetration","authors":"Sungjoo Chung;Ying Zhang;Yuanshuo Zhang","doi":"10.1109/TIA.2024.3522496","DOIUrl":"https://doi.org/10.1109/TIA.2024.3522496","url":null,"abstract":"Characterized by increasing penetration of distributed energy resources, active distribution networks necessitate developing uncertainty-adaptive power flow (PF) algorithms to cover broad operating conditions. Despite the success of data-driven methods in improving such adaptivity, the efficacy of these methods relies heavily on large, precise, and outlier-free datasets, which limits their materialization in practical grids. To address these dual issues, this paper proposes a knowledge-inspired data-aided robust PF algorithm in unbalanced distribution systems with ZIP load models and high penetration of distributed energy resources. The proposed method first uses Taylor expansion to derive an explicitly analytical linear solution for the PF calculation. A data-driven support vector regression-based method is further proposed to mitigate the approximation loss of the linearized PF model, which might surge in widening voltage variations. Inspired by physical knowledge of distribution system operation, the proposed method can adapt to a wide range of operating conditions without retraining and thus can be applied to passive/active distribution networks. Case studies in the IEEE 13- and 123-bus unbalanced feeders illustrate that the proposed algorithm exhibits superior computation efficiency and guaranteed accuracy, under variable penetration levels and lightweight datasets.","PeriodicalId":13337,"journal":{"name":"IEEE Transactions on Industry Applications","volume":"61 1","pages":"1523-1532"},"PeriodicalIF":4.2,"publicationDate":"2024-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143106831","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}
Shushu Zhu;Xun Li;Junqi Hu;Renhua Jiang;Chuang Liu;Kai Wang
{"title":"Multi-Objective Optimization of Permanent Magnet Assisted Synchronous Reluctance Motor for Industrial Drive Using Three-Step Optimization Method","authors":"Shushu Zhu;Xun Li;Junqi Hu;Renhua Jiang;Chuang Liu;Kai Wang","doi":"10.1109/TIA.2024.3520881","DOIUrl":"https://doi.org/10.1109/TIA.2024.3520881","url":null,"abstract":"Because of the advantages of high power factor and high power, and has been gradually applied in the field of industrial drive. The permanent magnet assisted synchronous reluctance motor has been widely applied in the field of industrial drive. The drive motor requires large output torque, high power factor and small torque ripple, thereby imposing more stringent demands on motor optimization. However, due to the complex rotor structure with the complex magnetic barrier, the optimization parameters of the permanent magnet assisted synchronous reluctance motor is large. Aiming at the above-mentioned problems, a three-step optimization method is studied. The relationship between the rotor structural dimensions is studied to reduce the number of parameters to be optimized. The parameter sensitivity is used to optimize the structure parameters. The response surface method and genetic algorithm are combined used to realize the comprehensive optimization of multi-objective. Then, the parameters with high sensitivity of single target are optimized by the single parameter scanning method. Finally, the structural detail of the magnetic barrier tip is precisely optimized to reduce the torque ripple. A 15 kW/1500 rpm permanent magnet assisted synchronous reluctance motor is optimized by the three-step optimization method. The simulation and experimental results are presented to verify the improvement of the motor performance.","PeriodicalId":13337,"journal":{"name":"IEEE Transactions on Industry Applications","volume":"61 1","pages":"218-230"},"PeriodicalIF":4.2,"publicationDate":"2024-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143107030","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}
{"title":"Newton-Raphson AC Power Flow Convergence Based on Deep Learning Initialization and Homotopy Continuation","authors":"Samuel N. Okhuegbe;Adedasola A. Ademola;Yilu Liu","doi":"10.1109/TIA.2024.3514992","DOIUrl":"https://doi.org/10.1109/TIA.2024.3514992","url":null,"abstract":"Power flow forms the basis of many power system studies. With the increased penetration of renewable energy, grid planners tend to perform multiple power flow simulations under various operating conditions and not just selected snapshots at peak or light load conditions. Getting a converged AC power flow (ACPF) case remains a significant challenge for grid planners especially in large power grid networks. This paper proposes a two-stage approach to improve Newton-Raphson ACPF convergence and was applied to a 6102 bus Electric Reliability Council of Texas (ERCOT) system. The first stage utilizes a deep learning-based initializer with data re-training. Here a deep neural network (DNN) initializer is developed to provide better initial voltage magnitude and angle guesses to aid in power flow convergence. This is because Newton-Raphson ACPF is quite sensitive to the initial conditions and bad initialization could lead to divergence. The DNN initializer includes a data re-training framework that improves the initializer's performance when faced with limited training data. The DNN initializer successfully solved 3,285 cases out of 3,899 non-converging dispatch and performed better than random forest and DC power flow initialization methods. ACPF cases not solved in this first stage are then passed through a hot-starting algorithm based on homotopy continuation with switched shunt control. The hot-starting algorithm successfully converged 416 cases out of the remaining 614 non-converging ACPF dispatch. The combined two-stage approach achieved a 94.9% success rate, by converging a total of 3,701 cases out of the initial 3,899 unsolved cases.","PeriodicalId":13337,"journal":{"name":"IEEE Transactions on Industry Applications","volume":"61 2","pages":"2037-2046"},"PeriodicalIF":4.2,"publicationDate":"2024-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143769503","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}
{"title":"A Game Theory Based Approach to Investigate Cross-Subsidy in Loss Allocation in Power Distribution Network","authors":"Himesh Kumar;Dheeraj K. Khatod","doi":"10.1109/TIA.2024.3515005","DOIUrl":"https://doi.org/10.1109/TIA.2024.3515005","url":null,"abstract":"The losses occurring in a power distribution network are recovered from the users. For this, a loss allocation technique is employed to decide the contributions from the users in total losses. Apart from being fair and transparent, the loss allocation should also be free from cross-subsidy, <italic>i.e.</i>, any user should not be subsidized over others. It necessitates a mechanism to identify and quantify cross-subsidy in the results of loss allocation. This paper, therefore, investigates the cross-subsidy by modeling the problem of loss allocation in distribution network as a cooperative game. The separate coalition of loads or distributed generators is modeled as a surplus allocation game, while the coalition of loads and distributed generators is modeled as a cost allocation game. In these games, a subsidy-free allocation lies within the core, and the deviation from the core is utilized to determine the level of cross-subsidization. Using the proposed technique, cross-subsidy is quantified in the results of various loss allocation methods. The results are tested on two different test systems, and the findings are analyzed and discussed in this paper.","PeriodicalId":13337,"journal":{"name":"IEEE Transactions on Industry Applications","volume":"61 2","pages":"2047-2056"},"PeriodicalIF":4.2,"publicationDate":"2024-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143769506","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}
Yuan-Kang Wu;Ming Yang;Jianxiao Wang;Chin-Woo Tan;Guannan He;Zhenfei Tan;Javad Mohammadi;Leijiao Ge
{"title":"Guest Editorial: Knowledge-and Data-Driven Smart Energy Management in Distribution Networks","authors":"Yuan-Kang Wu;Ming Yang;Jianxiao Wang;Chin-Woo Tan;Guannan He;Zhenfei Tan;Javad Mohammadi;Leijiao Ge","doi":"10.1109/TIA.2024.3510472","DOIUrl":"https://doi.org/10.1109/TIA.2024.3510472","url":null,"abstract":"Distribution networks (DN) are gradually transformed into their active form due to increasing penetration of distributed generation and fast development of use-side flexible resources. Due to limited measurements and communication capability, conventional power system analysis methods based on analytical formulation become inadequate for the management of DNs with high uncertainties and complex interactions. The advancement of the Internet of Things and artificial intelligence (AI) technologies enables data-driven approaches for the forecasting, modeling, operation, and control of DNs. To address challenges in practical industrial applications, such as interpretability, reliability, security, portability, and lack of high-quality training data, the nexus of data-driven and knowledge-based analysis methods have attracted growing research interest. The objective of this special issue is to identify and disseminate cutting-edge research focusing on integrating data-driven and knowledge-based technologies to tackle emerging challenges in smart management of active distribution systems.","PeriodicalId":13337,"journal":{"name":"IEEE Transactions on Industry Applications","volume":"61 1","pages":"1326-1328"},"PeriodicalIF":4.2,"publicationDate":"2024-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143106874","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}
Mohamed R. Elkadeem;Kotb M. Kotb;Atif S. Alzahrani;Mohammad A. Abido
{"title":"Design and Global Sensitivity Analysis of a Power-to-Hydrogen-to-Power-Based Multi-Energy Microgrid Under Uncertainty","authors":"Mohamed R. Elkadeem;Kotb M. Kotb;Atif S. Alzahrani;Mohammad A. Abido","doi":"10.1109/TIA.2024.3510214","DOIUrl":"https://doi.org/10.1109/TIA.2024.3510214","url":null,"abstract":"The integration of hydrogen and renewable technologies is increasingly recognized as essential for developing reliable and economically viable energy systems in modern cities. This paper presents an integrated model for the design optimization and global sensitivity analysis (GSA) of a power-to-hydrogen-to-power (P2H2P)-based multi-energy microgrid (MEμG) considering generation and demand uncertainties. The proposed system is designed to fulfill the electricity, heating, and electric vehicle charging requirements of a hypothetical complex residential building. It incorporates photovoltaic, wind turbine, battery storage, fuel cell, electrolyzer, hydrogen storage, and a gas boiler. The P2H2P-MEμG model was developed, simulated, and optimized with the dual objectives of minimizing the system's lifecycle cost and maximizing the share of renewable energy while considering various operational constraints. The obtained results enable optimal capacity sizing and provide a comprehensive evaluation of the beneficial impacts of the P2H2P system on the operational, economic, and environmental performance of the MEμG, compared with alternative energy system configurations. Also, the GSA shows that the technology cost, load growth, and project lifetime have a substantial influence on investment decisions and system costs.","PeriodicalId":13337,"journal":{"name":"IEEE Transactions on Industry Applications","volume":"61 2","pages":"1811-1827"},"PeriodicalIF":4.2,"publicationDate":"2024-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143769561","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}