检索结果-内蒙古大学图书馆

2024 International conference on Artificial Intelligence of Things and systems, AIoTSys 2024

作者： Qiu, Dongmeng Liu, Mengxiang Zhang, Xin University of Sheffield Department of Automatic Control and Systems Engineering Sheffield United Kingdom

ISBN: (纸本)9798331507886

The rapid digitalisation process in power system has greatly benefited the large-scale integration of distributed energy resources (DERs), essentially accelerating the progress towards net zero. However, numerous cyber attacks such as false data injection (FDI) attacks are impeding the normal control and operation activities. This paper aims to establish a real-Time microgrid co-simulation platform to fully study the impacts of realistic attack events on micorgrid's control performance. Although there exist a large number of power-communication co-simulation platforms for the power system, they are designed to mainly provide validation services for control and operation algorithms and little attention has been paid to the cyber security. In the established microgrid platform, power and communication parts are simulated in Typhoon Hardware-in-The-loop(HIL) 602+ and EXata network Simulator, respectively, and a dedicated synchronisation scheme is developed and embedded in Raspberry Pis to achieve master-slave data exchange between them. Based on the advanced cyber libraries provided by EXata, realistic FDI and packet drop attacks are mounted against the mapped communication links within EXata. The results indicate that these cyber attacks can severely influence the microgrid control performance including destabilising system states and specific state deviations, further demonstrating the necessity of deploying effective cyber-resilience enhancement mechanisms. © 2024 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

Multiscale Attention Recurrent network for Storage Estimation of Lithium-Ion Batteries 43

Multiscale Attention Recurrent Network for Storage Estimatio...

引用

43rd Chinese control conference, CCC 2024

作者： Bai, Xiaojie Chen, Xu Cui, Wenyue Qin, Linxiao Wu, Hanqing Zhang, Shou Dalian University of Technology The Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education Dalian116024 China The Electric Power Science Research Institute of State Grid Inner Mongolia East Electric Power Co. Ltd Tongliao028000 China

ISBN: (纸本)9789887581581

The state-of-health of batteries is crucial for ensuring their optimal performance. This paper presents a novel multiscale attention recurrent network, which is designed to enhance the accuracy and efficiency of state-of-health estimation in lithiumion batteries. Distinct from traditional models, this approach initially processes raw charge-discharge data across various time scales, employing feature fusion to more effectively capture temporal information. This method enhances model performance by introducing attention mechanisms following the residual network. The key innovation lies in the adept use of feature fusion for multiscale analysis of battery data, together with an attention mechanism to focus on informative features, which significantly enhances the accuracy of battery storage estimation. Research findings demonstrate that, based on historical operational data, this model can provide more precise and reliable predictions of battery health status, thereby significantly surpassing traditional methods. © 2024 Technical Committee on control Theory, Chinese Association of Automation.

关键词： State of charge

来源：评论

学校读者我要写书评

暂无评论

Value of Information in Remote Estimation Subject to Delay and Packet Dropouts 62

Value of Information in Remote Estimation Subject to Delay a...

引用

62nd IEEE conference on Decision and control (CDC)

作者： Wang, Siyi Hirche, Sandra Tech Univ Munich Chair Informat Oriented Control ITR Munich Germany

ISBN: (纸本)9798350301243

Emerging cyber-physical systems impel the development of advanced network scheduling schemes to utilize communication and computation resources efficiently. This paper investigates the event-based schedule for remote state estimation in networked control systems (NCSs) subject to delay and packet dropouts. The scheduler decides whether or not to send out a local estimate according to the Value of Information (VoI) metric, which measures the relative importance of an information update. In addition, we model the triggering intervals as a Markov chain and analyze the tradeoff between the estimation performance and communication cost under the proposed VoI-based scheduling for the first-order system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Review of Vehicular Adhoc network Routing and Congestion control

A Review of Vehicular Adhoc Network Routing and Congestion C...

引用

2024 International conference on Advancements in Power, Communication and Intelligent systems, APCI 2024

作者： Kori, Kaveri Sridevi, H. Sharnbasva University Department of Computer Science and Engineering Karnataka Kalaburagi585103 India Sharnbasva University Department of Artificial Intelligence and Machine Learning Karnataka Kalaburagi585103 India

ISBN: (数字)9798350363289

ISBN: (纸本)9798350363289

In VANET, the efficiency of the RSUs positioned beside the roadways is crucial for both transportation and service provision. Direct communication between vehicles and infrastructure is supported by the network (V2V and V2I, correspondingly). The architecture of a VANET should satisfy several requirements to function properly and enable dependable real-time communication between vehicles while considering their low-power radio transmission of units, dynamic topology, and high mobility. Numerous routing protocols are suggested and assessed for VANETs. There are very few testbeds worldwide since they need a large count of wireless devices to test routing protocols with genuine VANETs and MANETs prototypes. By examining 25 publications, this survey aims to create a brief summary of VANET routing. In the current work, it offers an analysis of reliable routing models based on optimization algorithms. The best outcomes will be displayed once the performance metrics of the works that were examined are examined. © 2024 IEEE.

关键词： Congestion control (communication)

来源：评论

学校读者我要写书评

暂无评论

Distributed Moving Horizon Estimation Over Wireless Sensor networks: A Matrix-Weighted Consensus Approach

引用

IEEE TRANSACTIONS ON CIRCUITS AND systems ii-EXPRESS BRIEFS 2023年第4期70卷 1665-1669页

作者： Huang, Zenghong Guo, Yuru Peng, Hui Xu, Yong Guangdong Univ Technol Sch Automat Prov Key Lab Intelligent Decis & Cooperat Control Guangzhou 510006 Peoples R China

This brief proposes a novel approach to distributed moving horizon estimation for linear discrete-time systems over a wireless sensor network. A distributed moving horizon estimator is presented by minimizing a cost function involving consensus steps on the prediction. A matrix-weighted rule for the consensus steps is designed by combining an orthogonal matrix with a stochastic matrix, where the orthogonal matrix is obtained from the observability decomposition rule. The proposed estimator only requires that each node transmits one state vector over the network, which reduces the communication burden. The estimation error of the proposed estimator is bounded by choosing an appropriate scalar parameter and a sufficiently large consensus step. Finally, a distributed target tracking example is presented to verify the performance of the developed results.

关键词： Observability Matrix decomposition Linear matrix inequalities Costs State estimation Noise measurement Cost function Moving horizon estimation observability decomposition consensus matrix weight boundedness

来源：评论

学校读者我要写书评

暂无评论

Designing a Communication Relay network for Multi-Domain Maritime Operations

Designing a Communication Relay Network for Multi-Domain Mar...

引用

2024 Military Communications conference

作者： Wakayama, Cherry Y. Plate, Randall S. Morey, Danielle F. Zabinsky, Zelda B. NIWC Pacific San Diego CA 92152 USA Univ Washington Seattle WA 98195 USA

ISBN: (纸本)9798350374247;9798350374230

Maritime operations are inherently distributed and involve systems and assets that are geographically dispersed across all domains of sea, land, air and space. Designing a communication relay network to support and facilitate mission command and control (C2) over large geographic areas is an important part of the mission planning and execution process to enhance the overall mission success of multi-domain maritime operations. In this paper, we study a topology design problem in which the C2 nodes located in different domains (land, ocean surface and underwater) are linked via a communication relay network. The objective of this research is to evaluate, characterize and perform a trade-off analysis on various relay network configurations consisting of underwater, surface, above-water and satellite nodes. We use a multiple-model approach in which packet-level network simulations are combined with network flow and queueing models to characterize the connectivity and traffic metrics of a given network topology configuration. We develop a custom simulation tool named TOMO-sim, which includes network configuration generation incorporating acoustic and radio frequency (RF) propagation models, discrete-event network simulation based on SimPy framework and wsnSimpy, and a global transmit scheduler to explore efficient transmission packing, to gather detailed simulation evaluations on configurations. network flow and queueing models provide additional insight into network connectivity and traffic flows under simplifying assumptions and are useful to perform sensitivity analysis. Our study demonstrates that adding assets, such as underwater nodes and gliders, only improves performance when they are well-placed according to the complex acoustic propagation environment.

关键词： network topology multi-domain network simulation network flows queueing model maritime operations

来源：评论

学校读者我要写书评

暂无评论

Dynamic Active Distribution network Reconfiguration Considering Aging Mitigation of Enrichable Battery Energy Storage systems 7

Dynamic Active Distribution Network Reconfiguration Consider...

引用

7th International conference on Energy, Electrical and Power Engineering (CEEPE)

作者： Chen, Fengchao Qiu, Zejian He, Zhipei Zhao, Ruifeng Xu, Ruifeng Su, Xin Yan, Wei Power Grid Co Ltd Dongguan Power Supply Bur Dongguan Guangdong Peoples R China Guangdong Power Grid Co Ltd Power Dispatching & Control Ctr Guangzhou Guangdong Peoples R China Chongqing Univ State Key Lab Power Transmiss Equipment & Syst Se Chongqing Peoples R China

ISBN: (纸本)9798350375794;9798350375800

To avoid worldwide climate change effects, decarbonization initiatives transit the distribution systems to be mixed with a high penetration of distributed energy resources (DERs) and enrichable battery energy storage systems (BESS) units. Since the degradation of BESS units is highly relevant to their discharging/charging operations, this paper considers constructing the dynamic DNR model with the aging mitigation of BESS units. This can extend the reaming useful life of BESS units, whilst achieving the minimization loss and smoothing power fluctuations of DERs. For the BESS aging cost, we derive the linearized hyperplanes to approximately quantify the battery life loss, which facilities for the solvability of the dynamic DNR model as a mixed integer second-order conic programming (MISOCP) problem. Case studies demonstrate that this proposed dynamic DNR model can achieve these merits with satisfactory performance.

关键词： dynamic distribution network reconfiguration battery energy storage systems aging mitigation

来源：评论

学校读者我要写书评

暂无评论

Calibrating the Converted Spiking Reinforcement Learning 20th

Calibrating the Converted Spiking Reinforcement Learning

引用

20th International conference on Intelligent Computing (ICIC)

作者： Song, Jian Yang, Xiangfei Zhang, Xuetao Wang, Donglin Westlake Univ Hangzhou 310024 Peoples R China Xi An Jiao Tong Univ Xian 710049 Peoples R China

ISBN: (纸本)9789819755806;9789819755813

Spiking reinforcement learning (SRL) widely receives attention due to its ultra-low power consumption. Since it is hard to train SRL directly, converting Deep Neural network into Spiking Neural network (DNN2SNN) has been a commonly used method to train. However, the conversion error exists with deep reinforcement learning (DRL), resulting in performance degradation of SRL. Inspired by the success of calibrated conversion method in classification tasks, we introduce this method into SRL to further improve the performance of the converted SRL. Specifically, we calibrate the number of spikes fired by converted SNN policy through adjusting the initial membrane potential. Experimental results on MuJoCo robot control tasks demonstrate the effectiveness of Conversion + Calibration method in SRL.

关键词： Spiking Reinforcement Learning Spiking Neural network Calibration

来源：评论

学校读者我要写书评

暂无评论

2D Human Pose Estimation with Residual Upsampling and Spatial Feature Enhancement 43

2D Human Pose Estimation with Residual Upsampling and Spatia...

引用

43rd Chinese control conference, CCC 2024

作者： Li, Shanbin Zheng, Xishan South China University of Technology School of Automation Science and Engineering Guangzhou China Changji University School of Energy and Control Engineering Xinjiang China

ISBN: (纸本)9789887581581

Computer vision, which has been extensively used in intelligent monitoring, self-driving, medical assistance, sports analysis, and other fields, includes human pose estimation as a key component. Human pose estimation algorithms have been appearing nonstop in recent years, and as they get more complex and structured, it becomes harder to analyze and actually implement the algorithms. SBL network is surprisingly efficient for such a simple design. This study makes several modifications based on SBL to further enhance its performance. In order to fuse rich features from the feature extraction stage to the upsampling phase, we first introduce the residual upsampling module (RUSM). This guarantees that more detailed, high-resolution information can be utilized to upsampling features, significantly increasing the accuracy of joint recognition in the human body. Additionally, we present the spatial feature enhancement module (SFEM), which utilizes the spatial attention mechanism with the residual structure. It is employed to boost spatial features of the upsampling phase and further increase the detection precision of the network. Lastly, we conduct numerous experiments on the LSP dataset, which amply illustrates the enhanced functionality of the extra modules and the better performance of our suggested network. © 2024 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Neuronal networks for Visual Inspection of Assembly Completeness and Correctness in Manufacturing 7th

Neuronal Networks for Visual Inspection of Assembly Complete...

引用

7th International conference on Green Technology and Sustainable Development

作者： Baykar, Ali Omer Kural, Ayhan Lambrecht, Jens Turkish German Univ Istanbul Turkiye Tech Univ Berlin Berlin Germany Istanbul Tech Univ Istanbul Turkiye

ISBN: (纸本)9783031761966;9783031761973

The conformity of the quality with the desired specifications in production must be controlled quickly, reliably and accurately. Cost reduction and efficiency studies in production quality control stages are of great importance today. For this reason, non-human and intelligent automated systems are the main research subjects as a solution method in quality control stages. In this study, the final visual inspection of fastening elements of an industrial product is addressed. The inspection of connection elements, such as screws, as one of these quality control stages, is presented through a framework utilizing a camera and learnable neural network, replacing human-eye control. Fasteners can be counted as small objects in the images obtained. Therefore, in this study, object detectors based on different CNN backbones (ResNet 50-101) and proposals are discussed and their performance in detecting these small objects is compared to achieve the high detection speed, accuracy and reliability. To address the challenges at an industrial level for object detection methods, a non-processed image dataset has been created. This dataset aims to represent various lighting conditions, including dark-bright fields and diffuse reflection, as well as occlusion and restricted camera angles. During the training phase, hyperparameter-tuning optimization of deep networks such as YOLOv8, Faster-RCNN with ResNet50&101 and lastly Sparse-RCNN with a different set of learned object proposals is evaluated, which can be most suitable for the detection of screw connection. Experimental results show that the pretrained Faster-RCNN and Sparse RCNN has over the % 85 success rate of detection of small objects in an industrial environment.

关键词： Visual Inspection Convolutional Neural network Object Detection Screw Connection Small Object Detection

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：