检索结果-内蒙古大学图书馆

IEEE conference on Computer Communications (IEEE INFOCOM)

作者： Liu, Qiong Zhang, Tianzhu Linguaglossa, Leonardo Telecom Paris Inst Polytech Paris LTCI F-91120 Palaiseau France Nokia Bell Labs F-91300 Massy France

ISBN: (纸本)9798350383515;9798350383508

Modern telco networks have experienced a significant paradigm shift in the past decade, thanks to the proliferation of network softwarization. Despite the benefits of softwarized networks, the constituent software data planes cannot always guarantee predictable performance due to resource contentions in the underlying shared infrastructure. performance predictions are thus paramount for network operators to fulfill Service-Level Agreements (SLAs), especially in high-speed regimes (e.g., Gigabit or Terabit Ethernet). Existing solutions heavily rely on in-band feature collection, which imposes non-trivial engineering and data-path overhead. This paper proposes a non-invasive performance prediction approach, which complements state-of-the-art solutions by measuring and analyzing low-level features ubiquitously available in the network infrastructure. Accessing these features does not hamper the packet data path. Our approach does not rely on prior knowledge of the input traffic, VNFs' internals, and system details. We show that (i) low-level hardware features exposed by the NFV infrastructure can be collected and interpreted for performance issues, (ii) predictive models can be derived with classical ML algorithms, (iii) and can be used to predict performance impairments in real NFV systems accurately. Our code and datasets are publicly available (1).

关键词： network function virtualization performance prediction service function chaining

来源：评论

学校读者我要写书评

暂无评论

An Architecture for Industrial control Mimic systems Based on Component and Multi-level 2-Mode Judgment Algorithm 10

An Architecture for Industrial Control Mimic Systems Based o...

引用

10th IEEE International conference on High performance and Smart Computing (IEEE HPSC)

作者： Sun, Changhua Chen, Gang Sun, Xin Li, Qinyuan Lv, Pang Dai, Hua State Grid Zhejiang Elect Power Co Ltd Elect Power Res Inst Hangzhou Peoples R China State Grid Corp China Beijing Peoples R China

ISBN: (纸本)9798350389463;9798350389470

As industrial control systems become more prevalent, cybersecurity concerns have gained significant attention. Mimic defense technology, serving as an effective security measure, combats network threats by continuously switching between functionally identical entities. However, current mimic control systems still have various shortcomings in executor design and judgment techniques, such as fixed heterogeneous executors and inefficient arbitration processes. In response to these challenges, this study introduces a component-based architecture for mimic control systems, enabling dynamic executor generation through modularized communication while minimizing system invasiveness. Additionally, a multi-level 2-mode judgment algorithm is designed, consider both real-time performance and security requirements, dynamically balancing decision efficiency and result reliability. Simulation results demonstrate that the proposed approach not only enhances the decision efficiency of mimic industrial control systems but also improves the judgment efficiency of mimic systems.

关键词： Mimic Defense Mimic control System Component Construction 2-Mode Judgment Algorithm

来源：评论

学校读者我要写书评

暂无评论

A Robust Sliding Mode control for Electro-optical Stabilized Servo Tracking System Based on Extended State Observer and Adaptive Neural network 18

A Robust Sliding Mode Control for Electro-optical Stabilized...

引用

18th International conference on control Automation Robotics and Vision

作者： Feng, Bin Fan, Weihua Chen, Qingwei Nanjing Univ Sci & Technol Automat Sch Nanjing 210094 Jiangsu Peoples R China

ISBN: (纸本)9798331518509;9798331518493

The tracking performance and line-of-sight stabilization of electro-optical stabilized servo tracking systems are often affected by various disturbances and uncertainties. To address the problems, a robust motion control scheme is developed. The control strategy effectively amalgamates sliding mode control (SMC), extended state observer (ESO), and adaptive radial basis function (RBF) neural network. Specifically, an ESO is constructed to estimate unknown disturbances and uncertainties in the system. An RBF neural network is employed to correct the estimation accuracy of ESO for time-varying disturbances. Furthermore, the sliding model control strategy is combined with ESO and RBF neural network to mitigate the impact of multi-source disturbances and uncertainties on control precision. The asymptotic stability of the system is demonstrated through Lyapunov theory and LaSalle invariance principle. Finally, simulations are implemented to illustrate the superiority and effectiveness of the proposed control method compared to the traditional SMC-ESO method.

关键词： State estimation

来源：评论

学校读者我要写书评

暂无评论

Comparison of neural network architectures for feedforward active control of nonlinear systems 31

Comparison of neural network architectures for feedforward a...

引用

31st International conference on Noise and Vibration Engineering, ISMA 2024 and 10th International conference on Uncertainty in Structural Dynamics, USD 2024

作者： Pike, X. Cheer, J. ISVR University of Southampton University Road Highfield SouthamptonSO17 1BJ United Kingdom

ISBN: (纸本)9789082893175

In recent decades, advances in digital technologies have allowed for the development of increasingly complex active control solutions for both noise and vibration, which have been utilised in a wide range of applications from automotive to maritime. Such control systems commonly use linear digital filters that cannot fully capture the dynamics of the nonlinear systems under control. To overcome such issues, it has previously been demonstrated that replacing the conventional linear controllers with Neural networks (NNs) can improve control performance in the presence of nonlinearities in both the system plant and primary path. However, a key design decision in the implementation of such controllers is the choice of an appropriate NN architecture for the specific control application. In this paper, a method of training NN controllers for Single-Input-Single-Output (SISO) acoustic noise control is presented. Multilayer Perceptron (MLP), Elman Recurrent Neural network (RNN) and Long Short-Term Memory (LSTM) architectures are implemented as controllers in the presence of nonlinearities in the primary path. An analysis is presented of the relative control performance of the different architectures, and the computational cost in operation and network training is discussed. © 2024 Proceedings of ISMA 2024 - International conference on Noise and Vibration Engineering and USD 2024 - International conference on Uncertainty in Structural Dynamics. All rights reserved.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

control Plane Scalability of Software Defined networking

Control Plane Scalability of Software Defined Networking

引用

2024 ASU International conference in Emerging Technologies for Sustainability and Intelligent systems, ICETSIS 2024

作者： Sati, Salem Omar Sati, Mohamed Emshiheet, Moad Misurata University Information Technology Faculty Libya

ISBN: (纸本)9798350372229

Software Defined networks (SDN) present a novel network architecture designed to facilitate scalability and management. The SDN network comprises a control plane core responsible for governing and monitoring all SDN devices, which operate using the OpenFlow signaling protocol. However, the scalability of SDN networks poses a challenge. This research paper investigates the impact of network topology and size on the performance of the SDN control plane. The study employs performance metrics to compare three Java-based SDN controllers: Open network Operating System (ONOS), OpenDaylight (ODL), and Floodlight controllers. The paper assesses metrics such as topology discovery time and control plane message overhead. The comparison involves fat-tree and spine and leaf topologies. All simulations are conducted within a centralized Out-of-band SDN environment. The results of the study demonstrate that ONOS controllers outperform ODL and Floodlight controllers in terms of discovery time, while the ODL controller exhibits the lowest overhead. © 2024 IEEE.

关键词： controller Scalability Flood-light controller ODL controller ONOS controller performance Metrics Software Defined network

来源：评论

学校读者我要写书评

暂无评论

Event-Triggered Robust Path Tracking control Considering Roll Stability Under network-Induced Delays for Autonomous Vehicles

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION systems 2023年第12期24卷 14743-14756页

作者： Viadero-Monasterio, Fernando Nguyen, Anh-Tu Lauber, Jimmy Boada, Maria Jesus L. Boada, Beatriz L. Univ Carlos III Madrid Dept Mech Engn Leganes 28911 Madrid Spain Univ Polytech Hauts France LAMIH CNRS UMR 8201 F-59313 Valenciennes France INSA Hauts France F-59313 Valenciennes France

This paper proposes a multi-input multi-output (MIMO) method for path tracking control of autonomous vehicles under network-induced delays while taking into account the roll dynamics to improve both the driving safety and the passenger comfort. The steering control is directly applied to the front wheels, while the anti-roll moment is exerted by an active suspension. The asynchronous phenomenon caused by the sampling process and the time-varying vehicle speed are explicitly taken into account in the control design using a polytopic linear parameter-varying (LPV) control approach. Moreover, to avoid using costly vehicle sensors and complex control structures, a static output feedback (SOF) control scheme is considered. An effective event-triggering mechanism is also proposed to alleviate the communication burden of the vehicle networked control system. Based on augmented Lyapunov-Krasovskii functional, the control design conditions are derived to guarantee the vehicle closed-loop stability under the effects of transmission delays, event-triggered control signals and time-varying parameters. The design procedure is reformulated as an iterative optimization problem involving linear matrix inequality (LMI) constraints, which can be effectively solved with available numerical solvers. The proposed event-triggered SOF controller is evaluated with the vehicle dynamics simulation software CarSim under several dynamic scenarios. A comparative study with related vehicle control results is performance to emphasize the effectiveness of the control method in terms of path tracking performance, driving safety and comfort, and data communication efficiency of the vehicle networked control system.

关键词： Path tracking active suspension roll stability control networked control systems event-triggered control

来源：评论

学校读者我要写书评

暂无评论

Self-Tuning PID controller for an Arm-Angle Adjustable Quadrotor Using an Actor-Critic-Based Neural network 19

Self-Tuning PID Controller for an Arm-Angle Adjustable Quadr...

引用

19th Iranian conference on Intelligent systems, ICIS 2024

作者： Rezaei, Arshia Talaeizadeh, Amin Alasty, Aria Department of Mechanical Engineering Tehran Iran

ISBN: (纸本)9798331507565

The increasing prevalence of multirotors necessitates the development of new configurations for specific applications. Innovative morphing of multirotors has enhanced their stability, maneuverability, agility, and overall performance. The utilization of Artificial Intelligence (AI) in robotics has enabled robots to exhibit autonomous behaviors in areas such as control, path planning, state estimation, system identification, and image processing. This paper introduces a novel approach to improving the control system of an adjustable arm-Angle quadrotor through the integration of a self-Tuning Proportional-Integral-Derivative (PID) controller, utilizing an Actor-Critic-based Neural network (NN). Arm-Angle adjustable quadrotors, with their complex and variable dynamics, present challenges in achieving optimal control performance across different arm angles. Traditional PID controllers often struggle to adapt efficiently to these dynamics. To address this issue, the Actor-Critic framework from reinforcement learning is employed to develop a self-Tuning mechanism for the PID controller. The Actor network learns the optimal control actions, while the Critic network evaluates the performance of the control system, enabling continuous improvement. Extensive Software-in-The-Loop (SIL) and Hardware-in-The-Loop (HIL) tests demonstrate the effectiveness and feasibility of the proposed approach in achieving robust and adaptive control for tilt-Arm quadrotors under diverse operating conditions. The results highlight the superiority of the Actor-Critic-based self-Tuning PID controller over conventional methods, showcasing its potential for real-world devlopment in autonomous aerial systems. © 2024 IEEE.

关键词： Three term control systems

来源：评论

学校读者我要写书评

暂无评论

Scalable Real-Time control in Industrial Cyber-Physical systems 24

Scalable Real-Time Control in Industrial Cyber-Physical Syst...

引用

25th International conference on Distributed Computing and networking, ICDCN 2024

作者： Haque, Md Ashikul Ismail, Dali Saifullah, Abusayeed Wayne State University DetroitMI United States Binghamton University BinghamtonNY United States

ISBN: (纸本)9798400716737

Real-time communication and control performance are the precursor of industrial cyber-physical systems that employ Wireless networked control System (WNCS) in critical industrial applications including process control and smart manufacturing. control performance and real-time communication are interdependent in a WNCS. Hence, optimizing control performance under limited resource of network requires a cyber-physical codesign approach. A codesign approach needs to be online to take into account both the current network condition and the current control behavior. Leading industrial wireless standards such as WirelessHART and ISA100 adopt software-defined networking as a centralized routing mechanism. Hence, in current approach, transmission schedules of the entire network are created centrally at a network manager in advance and are then disseminated to the nodes. control performance optimization usually requires to update sampling rates and/or priorities of the control loops, thereby requiring to re-create the schedules. Thus, it becomes highly inefficient under the current fully centralized scheduling approach. In this paper, we propose to optimize control performance in an industrial WNCS through a scheduling-control codesign based on a local and online scheduling approach proposed in a recent work. We formulate the scheduling-control codesign problem to optimize the control performance based on model predictive control theory. Unlike existing offline solution, our codesign complies with online scheduling and entails a rolling optimization to take into account the current control performance to dynamically update the rates and priorities of the control loops. We propose a highly scalable solution of the codesign problem based on a local search approach used as an anytime algorithm. © 2024 ACM.

关键词： Cyber Physical System

来源：评论

学校读者我要写书评

暂无评论

GPU performance Optimization via Intergroup Cache Cooperation

引用

IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND systems 2024年第11期43卷 4142-4153页

作者： Wang, Guosheng Du, Yajuan Huang, Weiming Wuhan Univ Technol Sch Comp Sci & Technol Wuhan 430070 Peoples R China Wuhan Univ Technol Shenzhen Res Inst Shenzhen 518000 Peoples R China

Modern GPUs have integrated multilevel cache hierarchy to provide high bandwidth and mitigate the memory wall problem. However, the benefit of on-chip cache is far from achieving optimal performance. In this article, we investigate existing cache architecture and find that the cache utilization is imbalanced and there exists serious data duplication among L1 cache *** order to exploit the duplicate data, we propose an intergroup cache cooperation (ICC) method to establish the cooperation across L1 cache groups. According the cooperation scope, we design two schemes of the adjacent cache cooperation (ICC-AGC) and the multiple cache cooperation (ICC-MGC). In ICC-AGC, we design an adjacent cooperative directory table to realize the perception of duplicate data and integrate a lightweight network for communication. In ICC-MGC, a ring bi-directional network is designed to realize the connection among multiple groups. And we present a two-way sending mechanism and a dynamic sending mechanism to balance the overhead and efficiency involved in request probing and *** results show that the proposed two ICC methods can reduce the average traffic to L2 cache by 10% and 20%, respectively, and improve overall GPU performance by 19% and 49% on average, respectively, compared with the existing work.

关键词： Integrated circuits Design automation Graphics processing units Computer architecture Bidirectional control Bandwidth Benchmark testing System-on-chip Optimization Cache cooperation GPU hit ratio

来源：评论

学校读者我要写书评

暂无评论

Learning Robust Whole-Body control for Legged Manipulation via Learned Terrain Estimation 24

Learning Robust Whole-Body Control for Legged Manipulation v...

引用

24th International conference on control, Automation and systems

作者： Lim, Seonghyeon Lee, Hyeonwoo Lee, Seunghyun Myung, Hyun Sogang Univ Dept Mech Engn Seoul 04107 South Korea Korea Adv Inst Sci & Technol Sch Elect Engn Daejeon 34141 South Korea

ISBN: (纸本)9798331517939;9788993215380

Quadruped robots can perform various tasks across diverse terrains but face limitations due to the difficulty of interacting with environments. Adding manipulation capabilities allows these robots to handle more complex and varied tasks. However, designing a controller for legged manipulation is challenging due to the high degrees of freedom and model complexities, especially in challenging terrains. To address these issues, we present DreamTEAM, a novel framework for robust whole-body control in legged manipulation through learned terrain estimation. Utilizing deep reinforcement learning, DreamTEAM integrates an asymmetric actor-critic structure with a unified policy for both locomotion and manipulation, enabling quadruped robots to operate effectively using only proprioceptive sensors. Key features include a terrain estimator network that accurately estimates frontal terrain heights and an adaptive reward curriculum encouraging the robot to tackle more difficult manipulation tasks without compromising locomotion performance. The proposed method, DreamTEAM, validated its robustness and legged manipulation performance compared with other state-of-the-art methods through simulation experiments. Ablation studies highlight the importance of each module in the framework, showing how they contribute to overall stability and adaptability. This framework represents a substantial advancement in locomotion and manipulation, enhancing performance in challenging environments.

关键词： Legged manipulation Quadruped robot Reinforcement learning Whole-body control

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：