检索结果-内蒙古大学图书馆

6th International Conference on Power and Energy Technology, ICPET 2024

作者： Haolin, Tang Lin, Chenhui Wu, Wenchuan Yuan, Qihai Department of Electrical Engineering Tsinghua University Beijing China NARI Group Beijing Kedong Power Control System Co. Ltd Beijing China

ISBN: (纸本)9798350375855

Security-Constrained Unit Commitment (SCUC) stands as a critical challenge within power systems. With the continual expansion of power networks, SCUC encounters substantial hurdles in terms of computational time. In practical scenarios, given the imperative of electricity market clearance, this dilemma necessitates frequent resolution throughout the day despite minor alterations in input data. In this study, leveraging machine learning techniques, we present an approach aimed at harnessing previous data effectively to forecast active constraints, thus expediting solutions to the SCUC problem. We introduce a novel methodology for generating training data to predict the active transmission constraint set, ensuring the trained model achieves full prediction coverage. Through extensive computational simulations, our approach demonstrates a remarkable acceleration in computation speed, achieving up to 8 times the efficiency in large-scale scenarios. © 2024 IEEE.

关键词： Mixed-integer linear programming

来源：评论

学校读者我要写书评

暂无评论

Dynamic Equivalence Study of Direct-drive Wind Farm

Dynamic Equivalence Study of Direct-drive Wind Farm

引用

2024 IEEE International Conference on Electrical Energy Conversion systems and control, IEECSC 2024

作者： Cui, Xiaodan Wang, Yanpin Wu, Jialong Wang, Shilu Fen, Jiaqi Deng, Kui Power System Stability Control Technology Branch Company Nari Group Corporation Nanjing China College of Electrical Engineering Dalian University of Technology Dalian China

ISBN: (纸本)9798350389357

The large-scale integration of wind farms poses challenges to the safe and stable operation of power systems. Establishing a simulation model that accurately reflects the dynamic characteristics of wind farms is essential for power system analysis. However, detailed electromagnetic transient models of wind farms are computationally intensive and hinder further analysis. This paper addresses this issue by proposing an equivalent model that captures the response characteristics of wind farms. It examines the structure and control methods of direct-drive wind turbines, develops electromagnetic transient models for various wind turbines using PSCAD/EMTDC software, and constructs a model of an actual wind farm. The paper compares and analyzes three equivalent methods, evaluates their performance under different wind speeds and fault scenarios, and elucidates the advantages and disadvantages of these methods for wind farms with diverse turbine types. © 2024 IEEE.

关键词： Electromagnetic transients

来源：评论

学校读者我要写书评

暂无评论

Diagnosis of Disc Space Variation Fault Degree of Transformer Winding Based on K-Nearest Neighbor Algorithm

引用

Energy engineering 2023年第10期120卷 2273-2285页

作者： Song Wang Fei Xie Fengye Yang Shengxuan Qiu Chuang Liu Tong Li Department of Power and Electrical Engineering Northwest A&F UniversityYangling712100China NARI Group Beijing Kedong Electric Power Control System Co.Ltd.Beijing100000China Huangling Mining Group Co. Ltd.Shanxi Coal and Chemical Industry GroupHuangling716000China

Winding is one of themost important components in power *** the health state of the winding is of great importance to the stable operation of the power *** efficiently and accurately diagnose the disc space variation(DSV)fault degree of transformer winding,this paper presents a diagnostic method of winding fault based on the K-Nearest Neighbor(KNN)algorithmand the frequency response analysis(FRA)***,a laboratory winding model is used,and DSV faults with four different degrees are achieved by changing disc space of the discs in the ***,a series of FRA tests are conducted to obtain the FRA results and set up the FRA ***,ten different numerical indices are utilized to obtain features of FRA curves of faulted ***,the 10-fold cross-validation method is employed to determine the optimal k-value of *** addition,to improve the accuracy of the KNN model,a comparative analysis is made between the accuracy of the KNN algorithm and k-value under four distance *** getting the most appropriate distance metric and kvalue,the fault classificationmodel based on theKNN and FRA is constructed and it is used to classify the degrees of DSV *** identification accuracy rate of the proposed model is up to 98.30%.Finally,the performance of the model is presented by comparing with the support vector machine(SVM),SVM optimized by the particle swarmoptimization(PSO-SVM)method,and randomforest(RF).The results show that the diagnosis accuracy of the proposed model is the highest and the model can be used to accurately diagnose the DSV fault degrees of the winding.

关键词： Transformer winding frequency response analysis(FRA)method K-Nearest Neighbor(KNN) disc space variation(DSV)

来源：评论

学校读者我要写书评

暂无评论

Learning control Applied to a Digital-to-analogue Converter

Learning Control Applied to a Digital-to-analogue Converter

引用

2023 IEEE Conference on control Technology and Applications, CCTA 2023

作者： Van Rijt, Noa Faza, Ahmad Oomen, Tom Eielsen, Arnfinn A. Eindhoven University Control System Technology Research Group EindhovenAZ 5612 Netherlands Stavanger University Department of Energy and Petroleum Engineering Stavanger4021 Norway

ISBN: (纸本)9798350335446

Digital-to-analogue converters (DACs) exhibit several non-ideal effects that deteriorate performance. Methods in feedback control can reduce such effects. Due to implementation limitations, the feedback signal in existing schemes is produced by open-loop observers, known as ΔΣ-modulation, that mitigate the observed adverse effects only partially. Measurement feedback can compensate for non-ideal behaviour and disturbances that are difficult to model. Learning control (LC) is introduced to overcome practical problems of measurement feedback in DACs, therewith omitting the need for accurate open-loop observers. Experimental results demonstrate a 95% improvement in RMS error when using LC with measurement feedback, compared to ΔΣ-modulation using observer feedback. © 2023 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

A fast power control method based on high-speed communication for the continuous co-phase traction power system

引用

iEnergy 2022年第4期1卷 395-399页

作者： Mingrui Li Yingdong Wei Yunzhi Lin Xiaoqian Li Chao Lu Changle Wang Zhanhe Li State Key Laboratory of Power System Operation and Control Department of Electrical EngineeringTsinghua UniversityBeijing 100084China China Railway Electrification Engineering Group Co. Ltd.Beijing 100036China

Continuous co-phase traction power system is an effective method to eliminate neutral sections and provide high quality power for both the public grid and the *** substations have the ability to provide cooperative support to each other to reduce capacity and improve system reliability.A fast power control method for substations is needed due to rapid load changes and low overload capability of the *** paper proposes a fast power control method based on high-speed communication between substations,with additional transient power control to significantly improve the dynamic response of the system.

关键词： Continuous co-phase traction power system cooperative power control dynamic response high-speed communication

来源：评论

学校读者我要写书评

暂无评论

Research on the logic monitoring method for the cloud computing based safety computer

引用

Transportation Safety and Environment 2023年第2期5卷 79-87页

作者： Yaran Yang Lianchuan Ma Tao Tang Huan Ding Zhen Liu School of Electronic and Information Engineering Beijing Jiaotong UniversityBeijing 100044China National Engineering Research Center of Rail Transportation Operation and Control System Beijing Jiaotong UniversityBeijing 100044China State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong UniversityBeijing 100044China CRSC Research&Design Institute Group Co.Ltd. Beijing 100070China

With the development of railway construction in China,the computing demand of the train control system is increasing day by *** application of cloud computing technology on the rail transit signal system has become a research hotspot in recent *** to improve the safety and availability of the safety computer platform in the cloud computing environment is the key problem when applying cloud computing to the train operation control *** the cloud platform is in an open network environment,fac-ing many security vulnerabilities and malicious network attacks,it is necessary to monitor the operation of computer programmes through edge safety ***,this paper encrypts the logical monitoring method,and then proposes a secure computer de fence model based on the dynamic heterogeneous redundancy *** the continuous time Markov chain(CTMC)is used to quantitatively solve the stable probability of the system,and the influence of different logical monitoring methods on the anti-attack performance of the system is ***,the experiment proves that the dynamic heterogeneous redundancy structure composed of encryption logic monitoring can guarantee the safe and stable operation of the safety computer more effectively.

关键词： safety computer logical monitoring method continuous time Markov modelling(CTMC) cloud computing anti-aggression analysis

来源：评论

学校读者我要写书评

暂无评论

MARS: Multi-Agent Deep Reinforcement Learning for Real-Time Workflow Scheduling in Hybrid Clouds with Privacy Protection 30

MARS: Multi-Agent Deep Reinforcement Learning for Real-Time ...

引用

30th IEEE International Conference on Parallel and Distributed systems, ICPADS 2024

作者： Cheng, Long He, Haoyang Gu, Yan Liu, Qingzhi Zhao, Zhiming Fang, Fang North China Electric Power University State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources School of Control and Computer Engineering Beijing China Wageningen University and Research Information Technology Group Netherlands University of Amsterdam Research Group of Multi-Scale Networked Systems Netherlands

ISBN: (纸本)9798331515966

Scheduling workflows in hybrid cloud environments presents significant challenges due to the inherent complexity of workflows and the dynamic nature of cloud resources. This complexity is further increased when attempting to balance workflow performance with privacy protection. Recent efforts have leveraged deep reinforcement learning (DRL) to address these challenges. However, most of these approaches rely on single-agent models, which can lead to security issues and scalability problems due to their centralized processing. Specifically, the properties of workflows are transferred to the single agent, which risks leaking privacy information. Our paper addresses these issues by introducing MARS, a real-time workflow scheduling method that prioritizes privacy protection in hybrid clouds. MARS leverages multi-agent deep reinforcement learning (MADRL) to optimize the workflow scheduling of cloud virtual machines (VMs). The benefit of our solution is that it relies on the collaborative learning of multi-agents on multiple VMs, which could assign user data to specific cloud servers for privacy protection while sharing training experiences between agents. In our implementation, MARS aims to reduce workflow completion time and operational costs while complying with strict privacy protection guidelines. The experimental results demonstrate that MARS can significantly surpass existing methods, reducing makespan by an average of 53.18% and costs by 61.98% compared to basic techniques, and achieving 20.26% and 25.71% improvements over the latest advanced methods, respectively. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Issues of Using Unsaturated Heating Time for Transient Thermal Measurement 22

Issues of Using Unsaturated Heating Time for Transient Therm...

引用

22nd International Conference on Electronics Packaging, ICEP 2023

作者： Hara, Tomoaki Fukunaga, Shuhei Funaki, Tsuyoshi Siemens K.K. Osaka University System and Control Engineering Lab. Power Device Group Div. Electrical Electronic and Infocommunications Eng. Graduate School of Eng Japan

ISBN: (纸本)9784991191152

"Heating time must be long enough to reach the thermal static equilibrium."This is a basic rule for transient thermal measurement of semiconductor devices. However, there are some situations when it is difficult to follow the rule. In this paper, the issues when violating the rule is discussed. The best measurement time setting with the limited total transient thermal measurement time will be discussed as well. © 2023 Japan Institute of Electronics Packaging.

关键词： SPICE

来源：评论

学校读者我要写书评

暂无评论

OptiTwin: Data-Driven Machining Process Optimization Platform for SMEs 29

OptiTwin: Data-Driven Machining Process Optimization Platfor...

引用

29th IEEE International Conference on Emerging Technologies and Factory Automation, ETFA 2024

作者： Abadía, José Joaquín Peralta Barrenechea, Felix Larrinaga Zabaljauregui, Mikel Cuesta Aiestaran, Xabier Badiola Zubiaurre, Aitor Duo Mendia, Gorka Olalde Lázare, Txema Pérez Mondragon Goi Eskola Politeknikoa Software and System Engineering Research Group Arrasate Spain Mondragon Goi Eskola Politeknikoa High Performance Machining Research Group Arrasate Spain Mondragon Goi Eskola Politeknikoa Electronic Power Systems Applied to the Control Electric Energy Research Group Arrasate Spain Mondragon Goi Eskola Politeknikoa Data Analysis and Cybersecurity Research Group Arrasate Spain

ISBN: (纸本)9798350361230

The manufacturing industry is constantly seeking innovative solutions to optimize machining processes. However, there is a lack of efficient digital platforms that fully meet the flexibility, service composition, and affordability needs of the manufacturing industry, in particular for small and mediumsized enterprises (SMEs). This paper introduces the OptiTwin platform, a novel data-driven system designed to enhance machining process optimization for SMEs. The OptiTwin platform was developed with a focus on data acquisition, management, and analysis based on data driven models. The functionalities of the platform were validated through a drilling use case at Mondragon University's high-performance machining laboratory, demonstrating its effectiveness in real-time tool condition monitoring. The results showcase the potential of OptiTwin in optimizing machining processes and empowering SMEs with data-driven insights for enhanced productivity and quality assurance. © 2024 IEEE.

关键词： Machining centers

来源：评论

学校读者我要写书评

暂无评论

Adversarially Robust Reinforcement Learning for Urban Traffic Signal control 5

Adversarially Robust Reinforcement Learning for Urban Traffi...

引用

5th IEEE International Conference on Technology, Informatics, Management, engineering and Environment, TIME-E 2024

作者： Hamzah, Muhammad Shafly Joelianto, Endra Sutarto, Herman Yoseph Putri, Adiyana Institut Teknologi Bandung Instrumentation and Control Master Program Bandung Indonesia Institut Teknologi Bandung Instrumentation Control and Automation Research Group Bandung Indonesia PT. Pusat Riset Energi Department of Intelligent System Bandung Indonesia Institut Teknologi Bandung Doctoral Program of Engineering Physics Bandung Indonesia

ISBN: (纸本)9798350364743

Urban traffic congestion presents critical challenges, resulting in delays, environmental pollution, and significant economic costs. While traditional traffic control methods, such as fixed-time and adaptive systems, have been widely implemented, they often fail in unpredictable conditions, particularly when confronted with noisy or inaccurate data. This research proposes a robust reinforcement learning (RL) solution for traffic signal control using the RADIAL-DQN (Robust Adversarial Loss DQN) algorithm. Integrating adversarial training enhances the system's robustness to real-world uncertainties. Evaluations conducted using a SUMO traffic simulation show that the robust agent produced an increase of only 60.71% in queue length under a projected gradient descent (PGD) adversarial attack, outperforming standard RL agents, which experienced an 89% increase. These results demonstrate the potential of robust RL to improve both the reliability and scalability of urban traffic control systems. © 2024 IEEE.

关键词： Traffic signals

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：