检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Yan, Zirui Mukherjee, Arpan Varici, Burak Tajer, Ali Department of Electrical Computer and Systems Engineering Rensselaer Polytechnic Institute TroyNY United States

This paper investigates the robustness of causal bandits (CBs) in the face of temporal model fluctuations. This setting deviates from the existing literature's widely-adopted assumption of constant causal models. The focus is on causal systems with linear structural equation models (SEMs). The SEMs and the time-varying pre- and post-interventional statistical models are all unknown and subject to variations over time. The goal is to design a sequence of interventions that incur the smallest cumulative regret compared to an oracle aware of the entire causal model and its fluctuations. A robust CB algorithm is proposed, and its cumulative regret is analyzed by establishing both upper and lower bounds on the regret. It is shown that in a graph with maximum in-degree d, length of the largest causal path L, and an aggregate model deviation C, the regret is upper bounded by O (dL-1 2 ( √ T + C)) and lower bounded by Ω(d L2 -2 max{ √ T , d2C}). The proposed algorithm achieves nearly optimal O ( √ T) regret when C is o( √ T), maintaining sub-linear regret for a broad range of C. Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cyber-Resilient Control for a 100% Inverter-Based Microgrid: Analysis and Real-Time Simulation

Cyber-Resilient Control for a 100% Inverter-Based Microgrid:...

引用

International Conference on Intelligent Systems Applications to Power Systems (ISAP)

作者： Milad Beikbabaei Nguyen Khoa Nguyen Ali Mehrizi-Sani The Bradley Department of Electrical and Computer Engineering Virginia Polytechnic Institute and State University Blacksburg VA

ISBN: (数字)9798331531751

ISBN: (纸本)9798331531768

As the U.S. moves toward cleaner electricity generation, the number of installed inverter-based resources such as wind and photovoltaic (PV) are on the rise. These inverter-based resources (IBR) rely on communication to update their real and reactive power set point; however, it opens room for cyberattacks. Previous work proposed ways to detect and mitigate cyberattacks for fully inverter-based microgrids using software simulation, but the feasibility of these methods needs to be tested using control hardware-in-the-loop (CHIL). This work develops a CHIL testbed using Typhoon HIL 402, Raspberry Pi 4, and a network switch to implement a cyber-resilient inverter control against false data injection (FDI) attacks. The Raspberry Pi 4 receives the electrical measurements from the Typhoon HIL using user datagram protocol (UDP) communication, runs the LSTM-based detection and mitigation code using the received measurements and sends back the corrected set point if an FDI attack is detected. The proposed method is tested on a fully inverter-based microgrid with four inverters under various scenarios.

关键词： Reactive power Protocols Tropical cyclones Prevention and mitigation Electric variables measurement Microgrids Switches Control systems Inverters Real-time systems

来源：评论

学校读者我要写书评

暂无评论

引用

Annual Conference of Industrial Electronics Society

作者： Hossein Amini Ali Mehrizi-Sani The Bradley Department of Electrical and Computer Engineering Virginia Polytechnic Institute and State University Blacksburg VA

ISBN: (数字)9781665464543

ISBN: (纸本)9781665464550

Power system operation needs to match generation to load demand. Accurate load forecasting helps operators maintain the power balance, reducing generation costs and preventing outages. This paper proposes an improved fuzzy clustering load forecasting method based on similar day and normalization approaches, especially for short-term power system load forecasting. Simulation results utilizing data from PJM, demonstrate a reasonable forecast error compared to PJM day-ahead hourly load forecasts. The superiority of this method is the simple calculations and accuracy based on the historical data.

关键词： Accuracy Smoothing methods Load forecasting Simulation Weather forecasting Artificial neural networks Predictive models Power system reliability Reliability Load modeling

来源：评论

学校读者我要写书评

暂无评论

Development of a Two-Level, Four-Leg Smart Inverter for Microgrid Applications

Development of a Two-Level, Four-Leg Smart Inverter for Micr...

引用

IEEE International Symposium on Power Electronics for Distributed Generation Systems (PEDG)

作者： Buck F. Brown Jan Westman Johan Enslin Zheyu Zhang Department of Electrical and Computer Engineering Clemson University North Charleston SC USA Department of Electrical Computer and Systems Engineering Rensselaer Polytechnic Institute Troy NY USA

ISBN: (数字)9798350361001

ISBN: (纸本)9798350361018

Microgrids are growing at a rapid pace, and as a result, power electronic inverters are more necessary than ever. However, the development of an adaptable inverter based on a changing control objective that also contains grid-related functions is lacking. This paper investigates the development of a novel two-level, four-leg smart inverter for a microgrid that can solve this problem. First, the inverter topology is discussed, modeled, and controlled using a standard dual-loop voltage control. Second, grid-forming functions are investigated. Third, an additional layout and control system are created for the grid-following inverter. Fourth, a simulation is constructed, and the capabilities of the smart inverter are highlighted.

关键词： Legged locomotion Grid following Layout Microgrids Inverters Topology Distributed power generation

来源：评论

学校读者我要写书评

暂无评论

Extended Deep Learning Algorithm for Improved Brain Tumor Diagnosis System

引用

Intelligent Automation & Soft Computing 2024年第1期39卷 33-55页

作者： M.Adimoolam K.Maithili N.M.Balamurugan R.Rajkumar S.Leelavathy Raju Kannadasan Mohd Anul Haq Ilyas Khan ElSayed M.Tag El Din Arfat Ahmad Khan Department of Computer Engineering Government Polytechnic CollegeSevvapetTiruvallurTamil Nadu602025India Department of Computer Science and Engineering KG Reddy College of Engineering and TechnologyHyderabadTelangana500075India Department of Computer Science and Engineering Sri Venkateswara College of EngineeringSriperumbudurChennai602117India Department of Computer Science and Engineering Annamalai UniversityChidambaramTamil Nadu608002India Department of Computer Science and Engineering Aarupadai Veedu Institute of TechnologyVinayaka Mission Research FoundationPaiyanurTamil Nadu603104India Department of Electrical and Electronics Engineering Sri Venkateswara College of EngineeringSriperumbudur602117India Department of Computer Science College of Computer and Information SciencesMajmaah UniversityAl-Majmaah11952Saudi Arabia Department of Mathematics College of Science Al-ZulfiMajmaah UniversityAl-Majmaah11952Saudi Arabia Electrical Engineering Department Faculty of Engineering&TechnologyFuture University in EgyptNew Cairo11835Egypt Department of Computer Science College of ComputingKhon Kaen UniversityKhon Kaen40002Thailand

At present,the prediction of brain tumors is performed using Machine Learning(ML)and Deep Learning(DL)*** various ML and DL algorithms are adapted to predict brain tumors to some range,some concerns still need enhancement,particularly accuracy,sensitivity,false positive and false negative,to improve the brain tumor prediction system ***,this work proposed an Extended Deep Learning Algorithm(EDLA)to measure performance parameters such as accuracy,sensitivity,and false positive and false negative *** addition,these iterated measures were analyzed by comparing the EDLA method with the Convolutional Neural Network(CNN)way further using the SPSS tool,and respective graphical illustrations were *** results were that the mean performance measures for the proposed EDLA algorithm were calculated,and those measured were accuracy(97.665%),sensitivity(97.939%),false positive(3.012%),and false negative(3.182%)for ten *** in the case of the CNN,the algorithm means accuracy gained was 94.287%,mean sensitivity 95.612%,mean false positive 5.328%,and mean false negative 4.756%.These results show that the proposed EDLA method has outperformed existing algorithms,including CNN,and ensures symmetrically improved *** EDLA algorithm introduces novelty concerning its performance and particular activation *** proposed method will be utilized effectively in brain tumor detection in a precise and accurate *** algorithm would apply to brain tumor diagnosis and be involved in various medical diagnoses *** the quantity of dataset records is enormous,then themethod’s computation power has to be updated.

关键词： Brain tumor extended deep learning algorithm convolution neural network tumor detection deep learning

来源：评论

学校读者我要写书评

暂无评论

Mitigating False Data Injection Attacks on Inverter Set Points in a 100% Inverter-Based Microgrid

Mitigating False Data Injection Attacks on Inverter Set Poin...

引用

Innovative Smart Grid Technologies (ISGT)

作者： Milad Beikbabaei Mario Montano Ali Mehrizi-Sani Chen-Ching Liu The Bradley Department of Electrical and Computer Engineering Virginia Polytechnic Institute and State University Blacksburg VA

The increasing number of 100% inverter-based microgrids is introducing new challenges in their control and cybersecurity. Previous work has studied the cyber vulnerabilities of microgrids; however, very few work has studied methods to mitigate and detect cyberattacks in a 100% inverter-based microgrid. Attackers can utilize communication-based devices in a microgrid to launch false data injection (FDI) attacks and cause voltage and frequency instability. This paper studies the effects of FDI attacks on the real and reactive power set points of inverter-based resources (IBR) in a 100% inverter-based microgrid. This work co-simulates a power system using PSCAD and a communication system using Python to study FDI attacks. The communication system is modeled as a first in first out (FIFO) queue model. A long short-term memory (LSTM)based method is used to mitigate and detect ramp and bias FDI attacks. The proposed strategy is tested on a microgrid with four IBRs subject to different FDI attacks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Leveraging Large Language Models for Wireless Symbol Detection via In-Context Learning

arXiv

引用

arXiv 2024年

作者： Abbas, Momin Kar, Koushik Chen, Tianyi Department of Electrical Computer and Systems Engineering Rensselaer Polytechnic Institute TroyNY United States

Deep neural networks (DNNs) have made significant strides in tackling challenging tasks in wireless systems, especially when an accurate wireless model is not available. However, when available data is limited, traditional DNNs often yield subpar results due to underfitting. At the same time, large language models (LLMs) exemplified by GPT-3, have remarkably showcased their capabilities across a broad range of natural language processing tasks. But how LLMs can benefit challenging non-language tasks in wireless systems is not fully unexplored. In this work, we propose to leverage the in-context learning ability (a.k.a. prompting) of LLMs to solve wireless tasks in the low data regime without any training or fine-tuning, unlike DNNs which require training. We further demonstrate that the performance of LLMs varies significantly when employed with different prompt templates. To solve this issue, we employ the latest LLM calibration methods. Our results reveal that using LLMs via ICL methods generally outperforms traditional DNNs on the symbol demodulation task and yields highly confident predictions when coupled with calibration techniques. Copyright © 2024, The Authors. All rights reserved.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

Protection of Inverter-Based Resources Under Open-Circuit Breaker Malfunction

Protection of Inverter-Based Resources Under Open-Circuit Br...

引用

Innovative Smart Grid Technologies (ISGT)

作者： Brady Alexander Ali Mehrizi-Sani Ardavan Mohammadhassani The Bradley Department of Electrical and Computer Engineering Virginia Polytechnic Institute and State University Blacksburg VA

Power system protection ensures the safe and reliable delivery of electric power to customers. The increasing number of inverter-based resources (IBR) creates challenges for conventional power system protection as IBRs respond differently to faults than synchronous generators (SG). This means that protection schemes need to be modified to ensure proper power system protection. Currently, most of the proposed IBR protection schemes focus on short-circuit (SC) faults. However, open-circuit (OC) faults also occur in the power system and cause unbalanced currents, overvoltages, and degraded power quality. This paper proposes an OC fault protection scheme for an IBR connected in a transmission system. The IBR control system is studied first. The response of an IBR to an OC fault is studied next. Finally, a protection logic is proposed to detect and clear OC faults. The performance of the proposed scheme is evaluated under time-domain simulation case studies using PSCAD/EMTDC software package.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Femtosecond Filament Coupled with Structured Light for Free Space Optical Communication

Femtosecond Filament Coupled with Structured Light for Free ...

引用

CLEO: Science and Innovations, S and I 2022

作者： Reza, Saad Bin Ali Wang, Tianhong Buldt, Finn Bassène, Pascal N'Gom, Moussa Electrical Computer and Systems Engineering Department Rensselaer Polytechnic Institute TroyNY United States Department of Physics Applied Physics and Astronomy Rensselaer Polytechnic Institute TroyNY United States

We created a 4-bit communication channel for free-space optical communication (FSO) through a segmented space division multiplexing method using structured light coupled with a femtosecond-laser induced filament. ... 详细信息

ISBN: (纸本)9781557528209

关键词： Optical communication

来源：评论

学校读者我要写书评

暂无评论

Retrieving Masked Signal Through Tracking and Wavefront Shaping

Retrieving Masked Signal Through Tracking and Wavefront Shap...

引用

CLEO: Applications and Technology, A and T 2022

作者： Rumman, Nazifa Wang, Tianhong Jennings, Kaitlin Bassène, Pascal Buldt, Finn N'Gom, Moussa Electrical Computer and Systems Engineering Department Rensselaer Polytechnic Institute TroyNY United States Department of Physics Applied Physics and Astronomy Rensselaer Polytechnic Institute TroyNY United States

We present a novel approach that tracks and localizes hidden signal inside or behind scattering media. The method combines traditional feedback based wavefront shaping with a switch function that utilizes two differen...

ISBN: (纸本)9781957171050

关键词：

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：