检索结果-内蒙古大学图书馆

Advanced Voltage Stability Assessment in Renewable-Powered Islanded Microgrids Using Machine Learning Models

ENERGIES 2025年第8期18卷 2047-2047页

作者： Abbass, Muhammad Jamshed Lis, Robert Rebizant, Waldemar Wroclaw Univ Sci & Technol Fac Elect Engn 27 Wybrzeze Stanislawa Wyspianskiego PL-50370 Wroclaw Poland

The assessment of voltage stability within a microgrid is essential to ensure that all buses in the system can maintain the required voltage levels. Recent research has focused on developing modern voltage stability estimation equipment rather than identifying optimal locations for integrating inverter-based resources (IBRs) within the network. This study analyzes and evaluates voltage stability in power systems with increasing levels of IBRs using modal analysis methodologies that consider active power (PV) and reactive power (QV). It examines the impact of load flow when integrating IBRs into the weakest-and strongest-load buses. Additionally, this study introduces a support vector machine (SVM) approach to assessing voltage stability in a microgrid. The results indicate that the proposed SVM approach achieved an optimal accuracy of 95.10%. Using the IEEE 14-bus scheme, the methodology demonstrated the effective and precise determination of the voltage stability category of the system. Furthermore, the analysis was conducted using the modified DES power system. The core contribution of this research lies in evaluating and identifying the locations that are the most and least favorable for integrating IBRs within the simplified DES power system network, utilizing modal analysis for both QV and solar photovoltaics (SPVs). The results of the load flow analysis suggest that integrating IBR is significantly more beneficial in the most substantial bus, as it minimally impacts other load buses assessed as the least reliable bus within the system.

关键词： optimization techniques sustainable energy systems smart grid optimization active power (PV) reactive power (QV) solar photovoltaics (SPVs) support vector machine (SVM) smart grid

来源：评论

学校读者我要写书评

暂无评论

Enhanced efficiency in smart grid energy systems through advanced AI-based thermal modeling

引用

THERMAL SCIENCE AND ENGINEERING PROGRESS 2024年 53卷

作者： Krishna, B. V. Santhosh Pauline, S. Sivakumar, S. Palagan, C. Anna Talasila, Vamsidhar Krishna, M. Masthan Siva New Horizon Coll Engn Dept CSE Bengaluru Karnataka India Govt Coll Engn Dept Civil Engn Tirunelveli 627007 India Vel Tech Rangarajan Dr Sagunthala R&D Inst Sci & T Dept Elect & Elect Engn Avadi 600062 Tamilnadu India Saveetha Engn Coll Dept Elect & Commun Engn Chennai 602105 Tamilnadu India Koneru Lakshmaiah Educ Fdn Dept Comp Sci & Engn Vaddeswaram AP India Aditya Coll Engn Dept Comp Sci & Engn Surampalem India

Integrating smart grid (SG) and artificial intelligence (AI) technologies can potentially enhance energy efficiency and sustainability in sports facilities. This research presents an innovative AI-based thermal modeling approach that utilizes machine learning algorithms and an attention mechanism to accurately predict and optimize energy consumption in real-time. By identifying patterns in operational indicators and anomalies in electrical grid devices, the proposed model aims to optimize power usage using real-world data. The attention mechanism enhances the model's generalization capabilities by focusing on informative time periods and capturing dependent relationships within patterns. The model was tested and validated using four datasets with diverse technological and environmental characteristics: REDD, HPC, GPP, and ISO-NE. It demonstrated superior performance compared to state-of-the-art approaches, achieving high accuracy, precision, recall, and F1 scores across multiple datasets while exhibiting computational efficiency through reduced inference and training times. Ablation studies confirmed the impact of the attention mechanism on energy consumption forecasting. The proposed AI- thermal modeling has the potential to improve energy efficiency in sports facilities, mitigate temperature distortion, and facilitate efficient maintenance scheduling, contributing to the long-term sustainability of the sports industry. This approach showcases the scalability of the model to various grid configurations and sizes, offering an intelligent framework to support more efficient, effective, and cost-effective energy management strategies. This study serves as a reliable reference for future research efforts in advanced grid systems.

关键词： Energy Efficiency AI-Based Thermal Modelling Energy Systems Thermal Management smart grid optimization Predictive Modelling and Machine Learning

来源：评论

学校读者我要写书评

暂无评论

A Graph-Based Neural Approach to Linear Sum Assignment Problems

引用

INTERNATIONAL JOURNAL OF NEURAL SYSTEMS 2024年第3期34卷 2450011-2450011页

作者： Aironi, Carlo Cornell, Samuele Squartini, Stefano Univ Politecn Marche Dept Informat Engn Ancona Italy

Linear assignment problems are well-known combinatorial optimization problems involving domains such as logistics, robotics and telecommunications. In general, obtaining an optimal solution to such problems is computationally infeasible even in small settings, so heuristic algorithms are often used to find near-optimal solutions. In order to attain the right assignment permutation, this study investigates a general-purpose learning strategy that uses a bipartite graph to describe the problem structure and a message passing Graph Neural Network (GNN) model to learn the correct mapping. Comparing the proposed structure with two existing DNN solutions, simulation results show that the proposed approach significantly improves classification accuracy, proving to be very efficient in terms of processing time and memory requirements, due to its inherent parameter sharing capability. Among the many practical uses that require solving allocation problems in everyday scenarios, we decided to apply the proposed approach to address the scheduling of electric smart meters access within an electricity distribution smart grid infrastructure, since near-real-time energy monitoring is a key element of the green transition that has become increasingly important in recent times. The results obtained show that the proposed graph-based solver, although sub-optimal, exhibits the highest scalability, compared with other state-of-the-art heuristic approaches. To foster the reproducibility of the results, we made the code available at https://***/aircarlo/GNN_LSAP.

关键词： Linear sum assignment graph neural networks deep neural networks smart meters scheduling smart grid optimization

来源：评论

学校读者我要写书评

暂无评论

Optimizing urban energy flows: Integrative vehicle-to-building strategies and renewable energy management

引用

ENERGY CONVERSION AND MANAGEMENT-X 2025年 26卷

作者： Yeoh, Jian Hern Lo, Kai-Yun Hsieh, I-Yun Lisa Natl Taiwan Univ Dept Civil Engn 1Sec 4Roosevelt Rd Taipei 106319 Taiwan Natl Taiwan Univ Dept Chem Engn 1Sec 4Roosevelt Rd Taipei 106319 Taiwan

The increasing integration of electric vehicles (EVs) into urban centers poses significant challenges for electrical grids, particularly in terms of energy management within buildings. This study introduces a scalable, multiobjective optimization model that utilizes Vehicle-to-Building (V2B) interactions to mitigate grid load by leveraging EVs as mobile energy storage units. This approach enhances grid stability and resilience while optimizing energy consumption, reducing peak loads, and minimizing emissions. We employ a weighted-sum method for flexible adaptability, allowing system priorities to be adjusted according to varying needs. The optimization tasks are handled using the Sequential Least Squares Programming (SLSQP) algorithm, which is well-suited for managing quadratic objective functions, nonlinear constraints, and bounded variables. Conducted at selected facilities at National Taiwan University (NTU), the model's effectiveness is demonstrated across four scenarios-each evaluating the contributions of photovoltaics (PV), V2B strategy, and an energy storage system (ESS) both individually and collectively. The results reveal significant benefits: a 46.79% annual reduction in grid energy consumption, along with notable decreases in daily peak load (63.49%), electricity costs (51.15%), and carbon emissions (45.99%) compared to a control setup. Additionally, our economic analysis underscores the cost-effectiveness of integrating PV with V2B technology, achieving a cost reduction of 40.83%. Although the inclusion of ESS incurs higher initial costs, it significantly improves peak load management by an additional 14.11%. This study not only underscores the practicality and economic viability of the model but also highlights its potential as a flexible tool in advancing sustainable urban energy solutions. Through comprehensive cost assessments and sensitivity analysis, this research enhances the capacity for intelligent, adaptable, and resourceefficient energy mana

关键词： Urban Energy Systems V2B Integration Renewable Energy Management smart grid optimization Carbon Emission Reduction

来源：评论

学校读者我要写书评

暂无评论

Air Conditioning Load Cluster Electricity Aggregation Model Based on Multi-dimensional Clustering and Double Decomposition 9

Air Conditioning Load Cluster Electricity Aggregation Model ...

引用

9th International Conference on Power and Renewable Energy

作者： Luo, Peng Wang, Sheng Ouyang, Lilin Luo, Cong Yang, Guangliang State Grid Digital Technol Holding Co Ltd Beijing Peoples R China Langfang Normal Univ Langfang Peoples R China North China Elect Power Univ Sch Elect & Elect Engn Beijing Peoples R China

ISBN: (纸本)9798350377477;9798350377460

The participation of multi-type air conditioning (AC) load aggregation in power grid demand response can better help the power grid to suppress the peak-valley difference and absorb renewable energy generation. Considering the strong correlation between AC power consumption and environmental data, an AC load power aggregation model based on multi-dimensional clustering and double decomposition is proposed in this paper. First of all, data preprocessing is carried out on the obtained AC power consumption data and use environment data. Secondly, grey relation analysis (GRA) is used to select the factors with strong correlation with the power consumption of AC load as input variables, and then partitioning and selecting clusters (PSC) -Kmeans ++ clustering method is used to aggregate the original data after screening. Then IVMD-PE-CEEMDAN, an innovative algorithm synthesizing the improved variational mode decomposition, permutation entropy, and complete ensemble empirical mode decomposition with adaptive noise methods was used for secondary decomposition to ensure the decomposition effect, mining the data characteristics, and improving the aggregation effect of the model. This method aims to improve the accuracy and reliability of the air conditioning load aggregation model for smart grid applications.

关键词： Multi-dimensional Clustering Double Decomposition Air Conditioning Load Aggregation smart grid optimization

来源：评论

学校读者我要写书评

暂无评论

Enhancing Electric Load Forecasting (ELF) in smart grids Using Neuro-Fuzzy Models: A Focus on Accuracy and Decision Process Transparency 2

Enhancing Electric Load Forecasting (ELF) in Smart Grids Usi...

引用

2nd IEEE International Conference on Communication, Security and Artificial Intelligence, ICCSAI 2023

作者： Mishra, Saket Chitkara University Institute of Engineering and Technology Chitkara University Centre for Interdisciplinary Research in Business and Technology Punjab India

ISBN: (纸本)9798350369960

In the domain of smart grid technologies, the capacity to forecast energy loads with high precision is crucial for the optimization of grid management and the promotion of sustainable energy practices. Traditional models for Energy Load Forecasting (ELF) often fail to fully comprehend the non-linear dependencies and unpredictable nature of energy consumption within these advanced systems. Addressing this gap, the current research introduces an innovative Neuro-Fuzzy approach, designed to enhance ELF within smart grid frameworks. This approach harnesses the predictive power of neural networks, renowned for their proficiency in learning from historical data, and combines it with the versatile reasoning capabilities of fuzzy logic systems, which excel in managing uncertainty and imprecision. By integrating these two computational paradigms, the proposed model exhibits a remarkable ability to navigate the complex and erratic patterns of energy usage, learning adaptively and accounting for the unpredictable variables that affect load demands. Empirical assessments conducted on datasets derived from actual smart grid implementations reveal the superior performance of the Neuro-Fuzzy model over contemporary forecasting methods. It not only delivers enhanced accuracy but also brings robustness to ELF. The model's intrinsic interpretability also plays a pivotal role in decision-making processes, allowing grid operators to transform intricate data analyses into practical, executable strategies. © 2023 IEEE.

关键词： Electric Load Forecasting Neural Networks Neuro-Fuzzy Systems smart grid optimization Transparency in AI Decision-Making

来源：评论

学校读者我要写书评

暂无评论

A Dynamic Framework for Multiobjective Mixed-Integer Optimal Power Flow Analyses

引用

TECHNOLOGY AND ECONOMICS OF smart gridS AND SUSTAINABLE ENERGY 2021年第1期6卷 1-10页

作者： Torelli, Francesco Vaccaro, Alfredo Pepiciello, Antonio Politecn Bari Bari Italy Univ Sannio Benevento Italy

This paper proposes a reliable and computationally efficient framework for solving multiobjective mixed-integer Optimal Power Flow problems. The main idea is to apply the interior point theory and the goal-attainment method to recast a generic OPF problem with both real and integer decision variables by an equivalent scalar optimization problem with equality constraints. Then, thanks to the adoption of the Lyapunov theory, an asymptotically stable dynamic system is designed such that its equilibrium points coincide with the stationary points of the Lagrangian function of the equivalent problem. Thanks to this approach, the OPF solutions can be promptly and reliably obtained by solving a set of ordinary differential equations, rather than using an iterative Newton-based scheme, which can fail to converge due to several numerical issues. Detailed numerical results are presented and discussed in order to prove the effectiveness of the proposed framework in solving real world problems.

关键词： smart grid optimization Power system computing Power system analysis

来源：评论

学校读者我要写书评

暂无评论

A hybrid Bayesian network-based deep learning approach combining climatic and reliability factors to forecast electric vehicle charging capacity

引用

Heliyon 2025年第4期11卷 e42483页

作者： Li, David Chunhu Information Technology and Management Program Ming Chuan University Taoyuan City 33321 Taiwan

The increasing adoption of electric vehicles (EVs) necessitates advanced predictive models to accurately forecast charging demand and ensure reliable infrastructure planning. This study introduces a novel analytical framework that integrates queuing network and Bayesian network models to enhance the prediction accuracy and reliability of EV charging demand. The objective is to develop a comprehensive system that accounts for various influencing factors, such as meteorological conditions and charging pile failure rates, to optimize EV infrastructure. The methodology involves creating a hybrid Bayesian Network-based deep learning (HBNDL) system architecture. This architecture uses extensive transaction data and climate analysis to build a detailed model of EV charging pile reliability. Additionally, two algorithms are designed to assess the usage and reliability of charging stations. The framework's effectiveness is tested through a series of experiments evaluating its performance in short-, medium-, and long-term prediction scenarios. The results demonstrate that the HBNDL framework significantly improves prediction accuracy and infrastructure reliability. The integration of queuing theory and Bayesian network models with deep learning techniques results in a robust system adaptable to various conditions. Experimental validation shows that the proposed framework outperforms existing models in forecasting EV charging demand, particularly under varying environmental influences. © 2025 The Author(s)

关键词： Charging station reliability Deep learning Electric vehicle infrastructure Environmental impact Predictive modeling smart grid optimization

来源：评论

学校读者我要写书评

暂无评论

Virtual Power Plant optimization in smart grids: A Narrative Review

引用

FUTURE INTERNET 2022年第5期14卷

作者： Goia, Bianca Cioara, Tudor Anghel, Ionut Tech Univ Cluj Napoca Dept Comp Sci Memorandumului 28 Cluj Napoca 400114 Romania

Virtual power plants (VPPs) are promising solutions to address the decarbonization and energy efficiency goals in the smart energy grid. They assume the coordination of local energy resources such as energy generation, storage, and consumption. They are used to tackle problems brought by the stochastic nature of renewable energy, lack of energy storage devices, or insufficient local energy flexibility on the demand side. VPP modeling, management, and optimization are open to research problems that should consider, on one side, the local constraints in the operation of the energy resources and power flows and the energy grid's sustainability objectives on the other side. There are multiple goals to create a VPP, such as to deliver energy services on a market or to the grid operator, to operate a microgrid in autonomy decoupled from the main grid, or to sustain local energy communities. In this paper, we present the results of a narrative review carried out on the domain of VPP optimization for the local energy grid integration. We have defined a search strategy that considers highly rated international databases (i.e., Elsevier, IEEE, and MDPI) in a six-year timeframe and applied objective inclusion/exclusion criteria for selecting articles and publications for the review;95 articles have been analyzed and classified according to their objectives and solutions proposed for optimizing VPP integration in smart grids. The results of the study show that VPP concepts and applications are well addressed in the research literature, however, there is still work to be done on: engaging prosumers and citizens in such a virtual organization, developing heuristics to consider a wider range of local and global constraints and non-energy vectors, and to decentralize and make transparent the services delivery and financial settlement towards community members. This study can help researchers to understand the current directions for VPP integration in smart grids. As a next step we

关键词： virtual power plants smart grid optimization energy efficiency narrative review

来源：评论

学校读者我要写书评

暂无评论

Machine learning-driven intelligent voltage control in renewable energy grids

引用

Electric Power Systems Research 2025年 248卷

作者： Murugesan, A. Durgadevi, K. Contractor, Dipen Rathod, Yagnik Tamil Nadu India Department of ECE SRM Valliammai Engineering College Chennai India Department of Computer Engineering Government Engineering College Dahod India

The growing high penetration of renewable energy sources (RES) into modern power grids poses deep challenges concerning voltage stability and minimum power losses. Voltage control by optimization methods is useless for the current design in nonlinear and dynamic power systems. Consequently, we propose a Graph Neural Networks (GNN)-Multi-Agent Reinforcement Learning (MARL) framework for real-time and adaptive voltage regulation in RES-integrated grids. Indeed, GNNs are excellent models of spatiotemporal dependencies in power networks, as concerns reasonably accurate voltage control riding on topologies themselves. Together with these factors, MARL leaves open decentralized and cooperative decision-making, which runs into adjustments for swaying voltages. The results of the simulations yielded 42 % less than average voltage deviations, a deterioration of 17 %, reduced the losses of the system, and a 30 % speed-up for standard optimization techniques. The test of the algorithms was executed under MATLAB with a Python-based grid simulation environment to affirm its real-world applicability and scalability. These results show the capability of this proposed GNN-MARL framework to completely change the voltage control strategy of future intelligent power grids. © 2025

关键词： and Real-Time grid adaptation Graph neural networks (GNN) Multi-Agent reinforcement learning (MARL) Renewable energy integration smart grid optimization Voltage stability control Voltage stabilization

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：