检索结果-内蒙古大学图书馆

14th IEEE international symposium on Power Electronics for distributed Generation systems, PEDG 2023

作者： Xing, Ling Wei, Qiang Li, Ryan Yunwei University of Alberta Department of Electrical and Computer Engineering Edmonton Canada Lakehead University Department of Electrical Engineering Thunder Bay Canada

ISBN: (纸本)9798350328233

The current source converter (CSC)-based wind energy conversion system is a good candidate for next-generation wind systems. To ensure control objectives, a large dc-link current is used in existing CSC-based wind systems. In this work, a dc current reduction scheme is proposed. It ensures control objectives and reduces the dc current, resulting in a significant power loss reduction. The proposed dc-link current reduction scheme is presented, and its effectiveness is verified by simulations. © 2023 IEEE.

关键词： Wind power

来源：评论

学校读者我要写书评

暂无评论

EdgeVPN: Self-organizing layer-2 virtual edge networks

引用

FUTURE GENERATION computer systems-THE international JOURNAL OF ESCIENCE 2023年 140卷 104-116页

作者： Subratie, Kensworth Aditya, Saumitra Figueiredo, Renato J. Univ Florida Elect & Comp Engn ECE Dept Adv Comp & Informat Syst ACIS Lab 968 Ctr Dr Gainesville FL 32611 USA

The advent of virtualization and cloud computing has fundamentally changed how distributed applications and services are deployed and managed. With the proliferation of IoT and mobile devices, virtualized systems akin to those offered by cloud providers are increasingly needed geographically near the network's edge to perform processing tasks in proximity to the data sources and sinks. Latency-sensitive, bandwidth-intensive applications can be decomposed into workflows that leverage resources at the edge - a model referred to as fog computing. Not only is performance important, but a trustworthy network is fundamental to guaranteeing privacy and integrity at the network layer. This paper describes Bounded Flood, a novel technique that enables virtual private Ethernet networks that span edge and cloud resources - including those constrained by NAT and firewall middleboxes. Bounded Flood builds upon a scalable structured peer-to-peer overlay, and is novel in how it integrates overlay tunnels with SDN software switches to create a virtual network with dynamic membership - supporting unmodified Ethernet/IP stacks to facilitate the deployment of edge applications. Bounded Flood has been implemented as the core of the EdgeVPN open-source virtual private network software system for edge computing. Experiments with the software demonstrate its functionality and scalability - one of which includes Kubernetes with Flannel across Raspberry Pi 4 edge devices behind different NATs.(c) 2022 The Author(s). Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://***/licenses/by-nc-nd/4.0/).

关键词： Edge computing Fog computing Virtualization Overlay networks Peer-to-peer Software-defined networks

来源：评论

学校读者我要写书评

暂无评论

Decentralized and distributed Control Strategies for Microgrids: A Review of Key Techniques and Applications

Decentralized and Distributed Control Strategies for Microgr...

引用

2025 IEEE international Students' Conference on Electrical, Electronics and computer Science, SCEECS 2025

作者： Sarathkumar, D. Maheswari, P. Manivel, Murugesan Jayakumar, T. Sivakumar, R. Parrthipan, B.K. Kongu Engineering College Department of Electrical and Electronics Engineering Tamil Nadu 638060 India Excel Engineering College Department of Electrical and Electronics Engineering Tamil Nadu 638052 India Karpagam Institute of Technology Department of Electrical and Electronics Engineering Tamilnadu Coimbatore641021 India Nandha Engineering College Department of Electrical and Electronics Engineering Tamil Nadu 638052 India V.S.B Engineering College Department of Electrical and Electronics Engineering Tamil Nadu 639111 India Kamaraj College of Engineering and Technology Department of Mechanical Engineering Tamil Nadu Vellakulam625701 India

ISBN: (纸本)9798331529833

Microgrids have emerged as a key solution for enhancing the flexibility, reliability, and sustainability of power systems. As the penetration of renewable energy sources and distributed generation increases, effective control strategies are essential for ensuring stable and efficient microgrid operation. This paper presents a comprehensive review of decentralized and distributed control strategies for microgrids, highlighting their significance in enabling scalability, robustness, and resilience. Key techniques, such as primary, secondary, and tertiary control layers, are discussed, with a focus on the transition from centralized to decentralized paradigms. The review explores the application of advanced algorithms like multi-agent systems (MAS), consensus-based control, and artificial intelligence (AI) for optimizing power sharing, voltage regulation, frequency stability, and energy management in islanded and grid-connected modes. Additionally, the paper analyzes the challenges and opportunities in implementing decentralized and distributed control, with real-world case studies and simulation-based insights to demonstrate their effectiveness in various microgrid configurations. Finally, potential future research directions are suggested to address emerging trends such as peer-to-peer energy trading, blockchain-based energy systems, and the integration of electric vehicles (EVs) into microgrid networks. © 2025 IEEE.

关键词： Decentralized control

来源：评论

学校读者我要写书评

暂无评论

A Novel Nash-Based Matching Approach for Multirobot Task Allocation in distributed Robotic networks 7th

A Novel Nash-Based Matching Approach for Multirobot Task All...

引用

7th EAI international Conference on Robotics and networks, ROSENET 2023

作者： Hamidoğlu, Ali Gül, Ömer Melih Gültekin, Gökhan Koray Kadry, Seifedine Nimer Department of Mathematics Bahcesehir University İstanbul Turkey Department of Computer Engineering Bahçeşehir University İstanbul Turkey Department of Electrical-Electronics Engineering Ankara Yıldırım Beyazıt University Ankara Turkey Department of Applied Data Science Noroff College Kristiansand Norway Ajman University Ajman United Arab Emirates

ISBN: (纸本)9783031644948

Efficiency is paramount in distributed robotic networks, where multiple autonomous robots collaborate to perform complex tasks. In this context, the identification of the most efficient path for robots, considering both distance and cost, plays a crucial role in the development of an effective matching algorithm for addressing multirobot task allocation (MRTA) challenges. This study presents a novel cooperative Nash game framework that serves as a distributed matching method for addressing the task allocation problem in a distributed robotic network consisting of robots and tasks. A particular MRTA problem is investigated where each robot moves at a constant speed determined by maximizing energy harvesting while minimizing energy consumption during the motion. In this framework, Nash equilibrium is established as a near-optimal approach for matching based on distance. In the numerical experiments, the performances are assessed for various scenarios involving 10 robots and 20 robots with the same number of tasks. Here, the Hungarian algorithm is used as an optimal benchmark algorithm to demonstrate the reliability of the theoretical findings and the robustness of the proposed model. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： distributed systems Energy harvesting Game theory Multirobot systems Task allocation

来源：评论

学校读者我要写书评

暂无评论

distributed No-Regret Learning for Multi-Stage systems with End-to-End Bandit Feedback 24

Distributed No-Regret Learning for Multi-Stage Systems with ...

引用

2024 international symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile networks and Mobile Computing, MobiHoc 2024

作者： Hou, I-Hong Department of ECE Texas A& M University College StationTX United States

ISBN: (纸本)9798400705212

This paper studies multi-stage systems with end-to-end bandit feedback. In such systems, each job needs to go through multiple stages, each managed by a different agent, before generating an outcome. Each agent can only control its own action and learn the final outcome of the job. It has neither knowledge nor control on actions taken by agents in the next stage. The goal of this paper is to develop distributed online learning algorithms that achieve sublinear regret in adversarial environments. The setting of this paper significantly expands the traditional multi-armed bandit problem, which considers only one agent and one stage. In addition to the exploration-exploitation dilemma in the traditional multi-armed bandit problem, we show that the consideration of multiple stages introduces a third component, education, where an agent needs to choose its actions to facilitate the learning of agents in the next stage. To solve this newly introduced exploration-exploitation-education trilemma, we propose a simple distributed online learning algorithm, Ε−EXP3. We theoretically prove that the Ε−EXP3 algorithm is a no-regret policy that achieves sublinear regret. Simulation results show that the Ε−EXP3 algorithm significantly outperforms existing no-regret online learning algorithms for the traditional multi-armed bandit problem. © 2024 Copyright held by the owner/author(s).

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Live Births Prediction using Legendre Memory Unit: A case study for the health regions of Goias 36

Live Births Prediction using Legendre Memory Unit: A case st...

引用

36th IEEE international symposium on computer-Based Medical systems (CBMS)

作者： Diogenes, Gabriela Kaori de Sousa Vitoria, Arthur Ricardo Silva, Diogo Fernandes Costa Pagotto, Daniel do Prado Sousa, Rafael Teixeira Galvao Filho, Arlindo Rodrigues Univ Fed Goias CLIA Inst Informat Goiania Go Brazil Univ Brasilia Dept Adm Goiania Go Brazil Univ Fed Mato Grosso CEIA Inst Exact & Earth Sci Barra Do Garcas Mato Grosso Brazil

ISBN: (纸本)9798350312249

The use of forecasting models is becoming even more common in healthcare and administration applications because it can be a reliable decision support tool. Live birth rate is a health index that is directly linked with maternal and newborn health and its prediction can assist health managers to anticipate resources destined for obstetric and pediatric services. Thus, the objective of this work is to forecast the number of live births in the state of Goi ' as (Brazil) for a 24-month horizon, providing useful information to support the planning and implementation of public policies. The model suggested is the Legendre Memory Unit (LMU) which is applied to data provided by the information system on live births of the information department of the single health system (SINASC-DATASUS). The dataset is composed of 252 monthly records of the number of live births for the 18 health regions of Goi ' as. The results were measured in prediction ability by Mean Absolute Percentual Error (MAPE) and Mean Absolute Error (MAE). The average MAPE and MAE were 6.4614 and 19.9136, respectively.

关键词： Legendre Memory Unit Univariate time series forecast Birth prediction Recurrent Neural networks

来源：评论

学校读者我要写书评

暂无评论

OCT Image Synthesis through Deep Generative Models 36

OCT Image Synthesis through Deep Generative Models

引用

36th IEEE international symposium on computer-Based Medical systems (CBMS)

作者： Melo, Tania Cardoso, Jaime Carneiro, Angela Campilho, Aurelio Mendonca, Ana Maria Inst Engn Sistemas & Comp Tecnol & Ciencia Rua Dr Roberto Frias P-4200465 Porto Portugal Univ Porto Fac Engn Dept Engn Eletrotecn Comp Rua Dr Roberto Frias P-4200465 Porto Portugal Univ Porto Fac Med Dept Cirurgia & Fisiol Alameda Prof Hernani Monteiro P-4200319 Porto Portugal Ctr Hosp Univ Sao Joao Alameda Prof Hernani Monteiro P-4200319 Porto Portugal

ISBN: (纸本)9798350312249

The development of accurate methods for OCT image analysis is highly dependent on the availability of large annotated datasets. As such datasets are usually expensive and hard to obtain, novel approaches based on deep generative models have been proposed for data augmentation. In this work, a flow-based network (SRFlow) and a generative adversarial network (ESRGAN) are used for synthesizing high-resolution OCT B-scans from low-resolution versions of real OCT images. The quality of the images generated by the two models is assessed using two standard fidelity-oriented metrics and a learned perceptual quality metric. The performance of two classification models trained on real and synthetic images is also evaluated. The obtained results show that the images generated by SRFlow preserve higher fidelity to the ground truth, while the outputs of ESRGAN present, on average, better perceptual quality. Independently of the architecture of the network chosen to classify the OCT B-scans, the model's performance always improves when images generated by SRFlow are included in the training set.

关键词： OCT image generation normalizing flow models generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Harnessing Knowledge-Distillation for Lightweight AI-Implementation on Resource-Constrained Device 10

Harnessing Knowledge-Distillation for Lightweight AI-Impleme...

引用

10th IEEE international symposium on Smart Electronic systems, iSES 2024

作者： Yadav, Abhishek Gupta, Vyom Kumar Kumar, Binod IIT Jodhpur Dept. of EE Rajasthan India IIIT Allahabad Dept. of ECE Prayagraj India

ISBN: (纸本)9798331533229

Smart wearable devices benefit from lightweight deep neural networks (DNNs) with small silicon footprints for efficient real-time processing. While compression techniques are often applied to heavier models, achieving lightweight DNNs for wearable technology, particularly in real-time applications, has been underexplored. This work proposes a knowledge-distillation approach to derive a lightweight student model from a pre-trained teacher model, which maintains high performance. Tested on real-world ECG data, the student DNN achieves 89% classification accuracy, matching the teacher model, with a 93.12% memory reduction. Furthermore, deployment on resource-constrained devices like Coral TPU shows a 2 to 6.5-fold throughput improvement compared to other devices. © 2024 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

HeterPS: distributed deep learning with reinforcement learning based scheduling in heterogeneous environments

引用

FUTURE GENERATION computer systems-THE international JOURNAL OF ESCIENCE 2023年第1期148卷 106-117页

作者： Liu, Ji Wu, Zhihua Feng, Danlei Zhang, Minxu Wu, Xinxuan Yao, Xuefeng Yu, Dianhai Ma, Yanjun Zhao, Feng Dou, Dejing Baidu Inc Beijing Peoples R China Univ Sci & Technol China Hefei Peoples R China

Deep neural networks (DNNs) exploit many layers and a large number of parameters to achieve excellent performance. The training process of DNN models generally handles large-scale input data with many sparse features, which incurs high Input/Output (IO) cost, while some layers are computeintensive. The training process generally exploits distributed computing resources to reduce training time. While heterogeneous computing resources, e.g., CPUs, GPUs of multiple types, are available for the distributed training process, the scheduling of multiple layers to diverse computing resources remains critical for the training process. To efficiently train a DNN model using the heterogeneous computing resources, we propose a distributed framework, i.e., Heterogeneous Parameter Server (HeterPS), composed of a distributed architecture and a Reinforcement Learning (RL)-based scheduling method. The advantages of HeterPS are three-fold compared with existing frameworks. First, HeterPS enables efficient training process of diverse workloads with heterogeneous computing resources. Second, HeterPS exploits an RL-based method to efficiently schedule the workload of each layer to appropriate computing resources to minimize the cost while satisfying throughput constraints. Third, HeterPS manages data storage and data communication among distributed computing resources. We carry out extensive experiments to show that HeterPS significantly outperforms state-of-the-art approaches in terms of throughput (14.5 times higher) and monetary cost (312.3% smaller).& COPY;2023 Elsevier B.V. All rights reserved.

关键词： Deep neural network distributed system Heterogeneous environment Scheduling distributed machine learning Parallel system

来源：评论

学校读者我要写书评

暂无评论

Hashgraph consensus-based simultaneous, asynchronous and big-data supported blockchain mechanism for IT-OT enabled critical infrastructure sectors

引用

Journal of Ambient Intelligence and Humanized Computing 2025年 1-13页

作者： Hasan, Mohammad Kamrul Ghazal, Taher M. Issa, Ghassan Islam, Shayla Ismail, Ahmad Fadzil Kabir, S. Rayhan Bangi43600 Malaysia Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman11937 Jordan School of Computing Skyline University College University City Sharjah Skyline University College Sharjah1797 United Arab Emirates Institue of Computer Science and Digitial Innovation UCSI University Malaysia Kuala Lumpur56000 Malaysia Department of Electrical and Computer Engineering International Islamic University of Malaysia Kuala Lumpur53000 Malaysia

Critical Infrastructure (CI) refers to the essential areas made up of public, private, and business sectors for the security of a country's development, such as electricity, water, health, education, etc. where information technologies (ITs) and operational technologies (OTs) enable automation services of CI. Currently, blockchain is being experimented in various CI sectors and any CI sector accumulates the data of millions of people in a country or nation from which big data is being generated. Big data connections are seen with large-scale blockchain networks because as the size of the blockchain network increases, so does the amount of connected data. Typically, the blockchain does not support asynchronous and simultaneous processes that indicate multiple block compilation does not allow at the same time for the blockchain systems. That is why high energy consumption, high bandwidth dependency, long-time computation, high mining process, and system slowness issues are seen on large-scale blockchain networks where big data is also connected. However, Hashgraph is an alternative distributed ledger technology (DLT) to blockchain and is also considered a consensus method that supports Asynchronous Byzantine Fault Tolerance (ABFT) as well as simultaneous process. Moreover, Hashgraph does not need mining and network node verification processes which saves bandwidth. In this research, we proposed a Hashgraph-enabled blockchain model for reducing the above issues and illustrated the adoption of IT-enabled OT to support CI. In addition, this manuscript discusses how the proposed model can create positive impacts in CI areas by replacing traditional blockchain systems. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Critical infrastructures

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：