检索结果-内蒙古大学图书馆

Intelligent Orchestrating of IoT Microservices Based on Reinforcement Learning

Chinese Journal of Electronics 2022年第5期31卷 930-937页

作者： WU Yuqin SHEN Congqi CHEN Shuhan WU Chunming LI Shunbin WEI Ruan College of Computer Science and Technology Zhejiang University College of Information and Electrical Engineering Ningde Normal University Zhejiang Lab College of Control Science and Engineering Zhejiang University

With the recent increase in the number of Internet of things(IoT) services, an intelligent scheduling strategy is needed to manage these services. In this paper, the problem of automatic choreography of microservices in IoT is explored. A type of reinforcement learning(RL) algorithm called TD3 is used to generate the optimal choreography policy under the framework of a softwaredefined network. The optimal policy is gradually reached during the learning procedure to achieve the goal, despite the dynamic characteristics of the network environment. The simulation results show that compared with other methods, the TD3 algorithm converges faster after a certain number of iterations, and it performs better than other non-RL algorithms by obtaining the highest reward. The TD3 algorithm can effciently adjust the traffic transmission path and provide qualified IoT services.

关键词： software-defined network telecommunication scheduling intelligent orchestrating nonRL algorithms reinforcement learning software defined networking optimal choreography policy reinforcement learning algorithm Internet of things services network environment IoT microservices TD3 algorithm traffic transmission path Internet of Things qualified IoT services intelligent scheduling strategy dynamic characteristics

来源：评论

学校读者我要写书评

暂无评论

Modeling and analysis of colored petri net based on the semi-tensor product of matrices

引用

Science China(Information Sciences) 2018年第1期61卷 70-85页

作者： Jiantao ZHAO Zengqiang CHEN Zhongxin LIU College of Computer and Control Engineering Nankai University Key Laboratory of Intelligent Robotics of Tianjin Nankai University

This paper applies the model petri net method based on the semi-tensor product of matrices to colored petri net. Firstly, we establish the marking evolution equation for colored petri net by using the semitensor product of matrices. Then we define the concept of controllability and the control-marking adjacency matrix for colored petri net. Based on the marking evolution equation and control-marking adjacency matrix, we give the necessary and sufficient condition of reachability and controllability for colored petri net. The algorithm to verify the reachability of colored petri net is given, and we analyze the computational complexity of the algorithm. Finally, an example is given to illustrate the effectiveness of the proposed theory. The significance of the paper lies in the application of the model petri net method based on the semitensor product of matrices to colored petri net. This is a convenient way of verifying whether one marking is reachable from another one as well as finding all firing sequences between any two reachable ***, the method lays the foundations for the analysis of other properties of colored petri net.

关键词： colored petri net reachability controllability marking evolution equation semi-tensor product of matrices

来源：评论

学校读者我要写书评

暂无评论

A novel matrix approach for the stability and stabilization analysis of colored Petri nets

引用

Science China(Information Sciences) 2019年第9期62卷 102-115页

作者： Jiantao ZHAO Zengqiang CHEN Zhongxin LIU College of Computer and Control Engineering Nankai University Key Laboratory of Intelligent Robotics of Tianjin Nankai University

In this study, the stability and stabilization problem of a colored Petri net based on the semitensor product of matrices is investigated. First, the marking evolution equation of the colored Petri net in a Boolean algebra framework is established, and the necessary and sufficient condition for the stability of the equilibrium point of the colored Petri net is given. Then, the concept of the pre-k steps reachability set is defined and is used to study the problem of marking feedback stabilization. Some properties of the pre-k steps reachability set are developed. The condition of the stabilization of the colored Petri net is given. The algorithm of the optimal marking feedback controller is designed. The proposed method in this paper could judge the stability and stabilization of the colored Petri net by matrix approach. The obtained results are simple and easy to implement by computer. An example is provided to illustrate the effectiveness of the proposed method.

关键词： discrete event system colored Petri net semi-tensor product of matrices stability equilibrium point stabilization

来源：评论

学校读者我要写书评

暂无评论

An adaptive approach for multi-agent formation control in MANET based on CPS perspective

引用

Journal of Networks 2014年第5期9卷 1169-1177页

作者： Lin, Jinzhi Wu, Ying Wu, Gongyi Xu, Jingdong College of Computer and Control Engineering Nankai University Tianjin 300071 China

From Cyber Physical System (CPS) perspective, it is nature for the system to tightly couple the communications and computing aspects with its physical dynamics. In this paper, we investigate this characteristic for multi-agent formation control in Mobile Ad-hoc Network (MANET). We manage to measure the real time wireless network congestion, implement a wireless QoS mechanism to provide different network channel access priorities and come up with the emergency calculation. Based on these, we present our adaptive approach for formation control. To examine the benefit of our approach, we use a co-simulation tool that we have developed for evaluating networked control & cyber physical system to study a specific scenario, in which five follower agents plus one leader perform a specific formation within a MANET with different congestion conditions. Through simulation experiments, it is showed that our approach could adaptively adjust sample periods and network channel access priorities according to real time dynamics emergencies and the network traffics condition, so as to optimize network utilization and improve the formation control performance. © 2014 ACADEMY PUBLISHER.

关键词： Cyber Physical System

来源：评论

学校读者我要写书评

暂无评论

Characteristic Model-based Generalized Predictive control for Electro-hydraulic System with Dead-zones and Parameter Uncertainty

引用

IFAC-PapersOnLine 2018年第20期51卷 287-294页

作者： Liu, Shengfei Sun, Qinglin Chen, Zengqiang Dong, Fangyou College of Computer and Control Engineering Nankai University Tianjin300350 China

In the paper, the electro-hydraulic system (EHS) is regulated by the proportional directional valve (PDV) which has nonlinearities such as the dead-zone. Furthermore, the effective bulk modulus varies with the temperature and the entrained air in EHS; there exist the nonlinear friction forces and the unmodeled dynamics as well as the square root relationship between the flow rate and the pressure in EHS. All these factors make it difficult to design the controller for EHS. The characteristic model (CM) is used to describe the relationship between input and output of EHS whose exact mathematical model is difficult to obtain. The gradient method through projection modification is utilized to estimate parameters of the CM. The CM-based controller with generalized predictive control (GPC) is designed to make the load track the desired position precisely. Simulations demonstrate that the CM-based GPC controller has a better performance in dead-zone compensation and adaptation with parameter variation than the proportional integral derivative (PID) controller. © 2018

关键词： controllers Friction Gradient methods Hydraulic equipment Model predictive control Predictive control systems Proportional control systems Two term control systems Characteristic model Dead zones Electro hydraulic system Generalized predictive control parameter variation

来源：评论

学校读者我要写书评

暂无评论

A novel node localization algorithm of wireless sensor network based on Delaunay triangular subdivision

引用

Journal of Information and Computational Science 2014年第2期11卷 623-630页

作者： Li, Cheng Zhang, Honglie Ge, Haimia College of Computer and Control Engineering Qiqihar University Qiqihar 161006 China

This paper proposes a node localization algorithm of wireless sensor network based on Delaunay triangular subdivision, which is referred to as the Delaunay Rank Localization (DRL) algorithm. The algorithm constructs the Delaunay graph by adopting the anchor node that is deployed in localization space as the vertex, and the midpoint of each edge of each triangle in the Delaunay graph is marked as the virtual anchor node to join in the localization of the unknown node. And the rank sequence from the anchor node to the sensor node is set up, and the location of the unknown sensor node is estimated according to the rank sequence. The simulation results show that compared with Dv-Hop algorithm and Centroid algorithm, the DRL algorithm estimates the location of the node more precisely, which improves the localization accuracy. Copyright © 2014 Binary Information Press.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

引用

Chinese Journal of Electronics 2021年第5期30卷 876-884页

作者： QIAO Sibo PANG Shanchen WANG Min ZHAI Xue DAI Feng College of Computer Science and Technology China University of Petroleum College of Control Science and Engineering China University of Petroleum College of Information Science and Engineering Shandong University of Science and Technology

Popularity prediction of online video is widely used in many different scenarios. It can not only help video service providers to schedule video web sites,but also bring considerable profits on investment for both providers and advertisers if popularity of online video is predicted accurately. However, online video popularity prediction still cannot have a satisfactory result, due to the complexity of many crucial factors especially of video distribution network. In this article, we extract seven factors from huge amounts of data about user behavior,establishing a new multiple linear regression model to initially predict online video popularity. After that, a multichannel video popularity dynamic scheduling model is proposed to schedule videos on which channel and what time to be broadcast, according to its popularity predicted by multiple linear regression model, ensuring that maximum the sum value of online video popularity of each channel. Experimental results on dataset obtained from Sohu Video, a video service provider in China, and real-world video flow in Sohu Video demonstrate that the proposed model is robust and has promising performance in predicting online video popularity, which is helpful for video service providers to schedule videos on web sites effectively in the future.

关键词： regression analysis video communication Internet video signal processing Web sites real-world video flow online video popularity regression prediction model video service provider Sohu Video video distribution network user behavior video Web sites dynamic scheduling multichannel video popularity dynamic scheduling model multiple linear regression model

来源：评论

学校读者我要写书评

暂无评论

Multi-variant network address hopping to defend stealthy crossfire attack

引用

Science China(Information Sciences) 2020年第6期63卷 241-243页

作者： Boyang ZHOU Gaoning PAN Chunming WU Kai ZHU Wei RUAN Zhejiang Lab College of Computer Science Zhejiang University College of Control Science and Engineering Zhejiang University

Dear editor,Recently, crossfire attack has been witnessed as a new distributed denial-of-service (DDoS) weapon that can effectively cut off the data connections between the chosen target area (wd) of servers and the end hosts (H). The attack is launched by a network of bot (botnet) to drain bandwidth of persistent routes (PRs) in the indirect and lowrate data flooding towards the decoys that are located in upstream to the target, where the PRs are

关键词： TTL Multi-variant network address hopping to defend stealthy crossfire attack

来源：评论

学校读者我要写书评

暂无评论

Diff9D: Diffusion-Based Domain-Generalized Category-Level 9-DoF Object Pose Estimation

arXiv

引用

arXiv 2025年

作者： Liu, Jian Sun, Wei Yang, Hui Deng, Pengchao Liu, Chongpei Sebe, Nicu Rahmani, Hossein Mian, Ajmal National Engineering Research Center for Robot Visual Perception and Control Technology College of Electrical and Information Engineering School of Robotics State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body Hunan University Changsha410082 China Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an710049 China Department of Information Engineering and Computer Science University of Trento Trento38123 Italy School of Computing and Communications Lancaster University LA1 4YW United Kingdom Department of Computer Science The University of Western Australia WA6009 Australia

Nine-degrees-of-freedom (9-DoF) object pose and size estimation is crucial for enabling augmented reality and robotic manipulation. Category-level methods have received extensive research attention due to their potential for generalization to intra-class unknown objects. However, these methods require manual collection and labeling of large-scale real-world training data. To address this problem, we introduce a diffusion-based paradigm for domain-generalized category-level 9-DoF object pose estimation. Our motivation is to leverage the latent generalization ability of the diffusion model to address the domain generalization challenge in object pose estimation. This entails training the model exclusively on rendered synthetic data to achieve generalization to real-world scenes. We propose an effective diffusion model to redefine 9-DoF object pose estimation from a generative perspective. Our model does not require any 3D shape priors during training or inference. By employing the Denoising Diffusion Implicit Model, we demonstrate that the reverse diffusion process can be executed in as few as 3 steps, achieving near real-time performance. Finally, we design a robotic grasping system comprising both hardware and software components. Through comprehensive experiments on two benchmark datasets and the real-world robotic system, we show that our method achieves state-of-the-art domain generalization performance. Our code will be made public at https://***/CNJianLiu/Diff9D. Copyright © 2025, The Authors. All rights reserved.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Progressive iterative channel estimation in fast time-varying OFDM systems

引用

The Journal of China Universities of Posts and Telecommunications 2014年第4期21卷 8-14页

作者： YANG Rui-zhe YE Si-yang ZHANG Yan-hua SUN Yan-hua YU Richard College of Electronics Information and Control Engineering Beijing University of Technology Department of Systems and Computer Engineering Carleton University

Considering the joint channel estimation and data detection in time-varying orthogonal frequency division multiplexing （OFDM） and addressing transmission performance degradation induced by the severe inter-carrier interference （ICI） at very high speed, a new progressive iterative channel estimation scheme is proposed. To alleviate the error propagation of the inaccurate data due to ICI, the measurement subcarriers in the Kalman filter is designed to be extended from pilots subcarriers to all the subcarriers progressively through the iterations. Furthermore, in iteration process, the interference of the non-pilot data to the measurement subcarriers is considered to be part of noise in the modified Kalman filter, which improves the estimation accuracy. Simulation indicates that the proposed scheme improves the performance in fast time-varying situation.

关键词： time-varying OFDM channel estimation ICI progressive Kalman

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：