检索结果-内蒙古大学图书馆

International Conference on Parallel and Distributed systems (ICPADS)

作者： Long Cheng Haoyang He Yan Gu Qingzhi Liu Zhiming Zhao Fang Fang State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources School of Control and Computer Engineering North China Electric Power University Beijing China Information Technology Group Wageningen University and Research Netherlands Research Group of Multi-Scale Networked Systems University of Amsterdam Netherlands

ISBN: (数字)9798331515966

ISBN: (纸本)9798331515973

Scheduling workflows in hybrid cloud environments presents significant challenges due to the inherent complexity of workflows and the dynamic nature of cloud resources. This complexity is further increased when attempting to balance workflow performance with privacy protection. Recent efforts have leveraged deep reinforcement learning (DRL) to address these challenges. However, most of these approaches rely on single-agent models, which can lead to security issues and scalability problems due to their centralized processing. Specifically, the properties of workflows are transferred to the single agent, which risks leaking privacy information. Our paper addresses these issues by introducing MARS, a real-time workflow scheduling method that prioritizes privacy protection in hybrid clouds. MARS leverages multi-agent deep reinforcement learning (MADRL) to optimize the workflow scheduling of cloud virtual machines (VMs). The benefit of our solution is that it relies on the collaborative learning of multi-agents on multiple VMs, which could assign user data to specific cloud servers for privacy protection while sharing training experiences between agents. In our implementation, MARS aims to reduce workflow completion time and operational costs while complying with strict privacy protection guidelines. The experimental results demonstrate that MARS can significantly surpass existing methods, reducing makespan by an average of $53.18 \%$ and costs by $61.98 \%$ compared to basic techniques, and achieving $20.26 \%$ and $25.71 \%$ improvements over the latest advanced methods, respectively.

关键词： Training Cloud computing Privacy Costs Scalability Deep reinforcement learning Dynamic scheduling Real-time systems Complexity theory Protection

来源：评论

学校读者我要写书评

暂无评论

Formation control of Discrete-time Multi-agent systems Based on Distributed Filter Observer

Formation Control of Discrete-time Multi-agent Systems Based...

引用

Fully Actuated system Theory and Applications (CFASTA), Conference on

作者： Huanli Gao Wei Li Ming Qiu He Cai School of Automation Science and Engineering South China University of Technology Guangzhou China Key Laboratory of Autonomous Systems and Networked Control Ministry of Education Guangzhou China Guangdong Engineering Technology Research Center of Unmanned Aerial Vehicle Systems Guangzhou China Department of Shanhaiguan District People’s Armed Forces Qinhuangdao City China

ISBN: (数字)9798350373691

ISBN: (纸本)9798350373707

This paper explores the formation control of discrete multi-agent systems under external communication disturbance. Firstly, leveraging the modified algebraic Riccati equation, a disturbed output based discrete filter observer is proposed to minimize network information exchange and mitigate disturbance effects. Then, the formation control issue is transformed into a cooperative output regulation problem, which a certainty equivalent state feedback controller solves. The effectiveness of the control strategy is demonstrated by numerical simulations.

关键词： State feedback Riccati equations Observers Information filters Numerical simulation Filtering theory Formation control

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of a Group control Communication system for Intelligent Rubber Tapping Robots

Design and Implementation of a Group Control Communication S...

引用

第42届中国控制会议

作者： Fuchun Liu Dong Jiang Xiaoyang Chen Xujian Chen Shengfeng Huang School of Automation Science and Engineering South China University of Technology Key Laboratory of Autonomous Systems and Networked ControlMinistry of Education Unmanned Aerial Vehicle Systems Engineering Technology Research Center of Guangdong Beijing Normal University Hong Kong Baptist United International College

With the development and promotion of electric rubber tapping equipment,China has gradually mechanized rubber tapping,but the degree of automation could be *** paper designs an intelligent rubber tapping remote monitoring system based on Internet of Things(IoT) technology that is applied to single-motor driven rubber tapping robots and uploads the status data of robots in the rubber plantation to the cloud database for storage,data analysis,and display in the backend management system in order to realize the intelligent and digital upgrade of rubber tapping *** can achieve remote group control of the robots in the rubber plantation at the same time using a cloud-based human-machine *** system consists of a terminal electronic control subsystem,a communication subsystem,and a cloud-based backend management *** system uses LoRa RF technology and Narrowband IoT(NBIoT) technology to design a star-shaped network to connect the robots to the cloud for unified management and provide data support for later tapping decisions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Study of Data Augmentation for Imbalance Problem in Network Traffic

A Study of Data Augmentation for Imbalance Problem in Networ...

引用

Blockchain Technology and Information Security (ICBCTIS), International Conference on

作者： Xu Wang Shimin Sun Li Han School of Computer Science and Engineering Tianjin University of Technology Tianjin China Tianjin Key Laboratory of Autonomous Intelligent Technology and System School of Software Tiangong University Tianjin China National Engineering Laboratory for Computer Virus Prevention and Control Technology Tianjin China

The complexity and diversity of smart grid systems increase the likelihood of anomalies in communications between devices in the system, and how these anomalies are detected is critical to the security of the grid system. However, the distribution of traffic types in the grid is often highly unbalanced, with the total amount of normal traffic data often far outweighing the anomalous data. This imbalance compromises the effectiveness of the detection model and poses a significant threat to the overall security of the grid. This paper improves on traditional conditional generation adversarial neural networks and designs a new approach to overcome this obstacle and enhance the security of smart grid systems. In the generator part, the spatial features of the data are captured by convolutional neural networks, and the temporal features of the data are captured by gated recurrent units. By integrating these two components into the generative network, we can generate synthetic data with both temporal and spatial features, thus enhancing the minority class samples. By incorporating the augmented minority data into the training process, the proposed approach enables the detection model to understand the distribution of features of the minority anomaly samples more accurately. This improved learning accuracy translates into improved model performance, resulting in higher detection rates for previously under-represented anomalies. In addition, our approach effectively addresses the inherent bias towards traffic types with higher flows typically observed in asymmetric datasets, thus providing a more equitable and comprehensive security solution for smart grid systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AnyBipe: An End-to-End Framework for Training and Deploying Bipedal Robots Guided by Large Language Models

arXiv

引用

arXiv 2024年

作者： Yao, Yifei He, Wentao Gu, Chenyu Du, Jiaheng Tan, Fuwei Zhu, Zhen Lu, Junguo All authors are with Machine Vision and Autonomous System Laboratory Department of Automation School of Electrical Information and Electronic Engineering Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai200240 China University of Michigan Shanghai Jiao Tong University Joint Institute Shanghai Jiao Tong University Shanghai China

Training and deploying reinforcement learning (RL) policies for robots, especially in accomplishing specific tasks, presents substantial challenges. Recent advancements have explored diverse reward function designs, training techniques, simulation-to-reality (sim-to-real) transfers, and performance analysis methodologies, yet these still require significant human intervention. This paper introduces an end-to-end framework for training and deploying RL policies, guided by Large Language Models (LLMs), and evaluates its effectiveness on bipedal robots. The framework consists of three interconnected modules: an LLM-guided reward function design module, an RL training module leveraging prior work, and a sim-to-real homomorphic evaluation module. This design significantly reduces the need for human input by utilizing only essential simulation and deployment platforms, with the option to incorporate human-engineered strategies and historical data. We detail the construction of these modules, their advantages over traditional approaches, and demonstrate the framework’s capability to autonomously develop and refine controlling strategies for bipedal robot locomotion, showcasing its potential to operate independently of human intervention. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Optimization Charging Method of Lithium-Ion Battery Based on Multi-Objective Bbo Algorithm

SSRN

引用

SSRN 2024年

作者： Duan, Shuangming Xia, Kuifeng Li, Junhui Zhao, Zhiqiang Liu, Haojun Key Laboratory of Modern Power System Simulation Control and New Green Energy Technology Ministry of Education Northeast Electricity Power University Jilin Jilin132012 China State Grid Hami Power Supply Company Xinjiang Uygur Autonomous Region Hami839000 China

Currently, the charging strategy of lithium-ion battery is usually an open-loop method, which lacks feedback in the charging process. In order to obtain a suitable charging strategy for lithium-ion battery, a simple and easy PID closed-loop constant temperature control system is proposed, which takes the temperature of lithium-ion battery as the feedback quantity, and improves the charging speed under the condition that the maximum temperature rise of lithium-ion battery is consistent. Secondly, SOC-based Multistage Constant Current (SMCC) based on SOC segmentation is proposed and orthogonal experiments are constructed by Taguchi method to determine the constant current values of each SMCC segment. Then, taking charging time, charging efficiency and SOH (State of Health) decay as the charging objectives to be optimized, multi-objective biogeographic-based optimization (BBO) is used. The MBBO algorithm optimizes each charging current under different weight coefficient combinations. According to the optimization results, Pareto optimal frontier is used to select the most balanced charging strategy from the six proposed charging strategies. Finally, SMCC charging current optimized by MBBO algorithm is connected to PID closed-loop constant temperature control system, and compared with SMCC charging strategy without constant temperature control and traditional 1C-CCCV method, the results show that compared with 1C-CCV charging strategy, The algorithm optimized SMCC can significantly reduce the charging time and SOH loss of lithium-ion batteries, and the SMCC charging current can be connected to PID closed-loop constant temperature control to further improve the charging speed, and keep the charging efficiency basically equal to the SOH attenuation. © 2024, The Authors. All rights reserved.

关键词： Taguchi methods

来源：评论

学校读者我要写书评

暂无评论

A New Image Quality Database for Multiple Industrial Processes

arXiv

引用

arXiv 2024年

作者： Ma, Xuanchao Jiang, Yanlin Liu, Hongyan Zhou, Chengxu Gu, Ke Faculty of Information Technology Beijing University of Technology Beijing China Engineering Research Center of Intelligent Perception and Autonomous Control Ministry of Education Beijing Laboratory of Smart Environmental Protection China Beijing Key Laboratory of Computational Intelligence and Intelligent System China Beijing Artificial Intelligence Institute China School of Electronic & Information Engineering Liaoning University of Technology Liaoning China Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education Dalian University of Technology China

Recent years have witnessed a broader range of applications of image processing technologies in multiple industrial processes, such as smoke detection, security monitoring, and workpiece inspection. Different kinds of distortion types and levels must be introduced into an image during the processes of acquisition, compression, transmission, storage, and display, which might heavily degrade the image quality and thus strongly reduce the final display effect and clarity. To verify the reliability of existing image quality assessment methods, we establish a new industrial process image database (IPID), which contains 3000 distorted images generated by applying different levels of distortion types to each of the 50 source images. We conduct the subjective test on the aforementioned 3000 images to collect their subjective quality ratings in a well-suited laboratory environment. Finally, we perform comparison experiments on IPID database to investigate the performance of some objective image quality assessment algorithms. The experimental results show that the state-of-the-art image quality assessment methods have difficulty in predicting the quality of images that contain multiple distortion types. Copyright © 2024, The Authors. All rights reserved.

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

Multi-Objective Optimal control of Wastewater Treatment Processes Constrainted by Energy-Saving and Effluent Qualities

Multi-Objective Optimal Control of Wastewater Treatment Proc...

引用

Robotics, control and Automation Engineering (RCAE), International Conference on

作者： Jing Zhang Haoming Yan Hongtian Chen Shuiqing Xu Yiqi Liu Key Laboratory of Autonomous Systems and Networked Control Ministry of Education School of Automation Science & Engineering South China University of Technology Guangzhou China Department of Automation Shanghai Jiao Tong University Shanghai China College of Electrical Engineering and Automation Hefei University of Technology Hefei China

Considering the high energy consumption problem in the wastewater treatment process, this paper proposes a multi-objective optimization control scheme based on NSGA-II algorithm. The proposed scheme can not only ensures meet effluent quality requirements but also can achieves energy cost savings. This method takes the aeration energy consumption and pumping energy consumption of the system as the optimization goal with the effluent water quality being the constraint condition. At the same time, the adaptive fuzzy PID controller is designed to ensure the control accuracy and stability of the controlled system. The results of simulation experiments validated in benchmark simulation platform, BSM1, show that, compared with PI control and single-objective optimization control, the proposed optimization scheme in this paper can achieve the desired quality of the effluent water withmore energy-saving.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Perceptual Quality Evaluation of Corrupted Industrial Images 18th

Perceptual Quality Evaluation of Corrupted Industrial Images

引用

18th International Forum of Digital Multimedia Communication, IFTC 2021

作者： Gong, Yafei Peng, Chenchen Liu, Jing Zhou, Chengxu Liu, Hongyan Faculty of Information Technology Beijing University of Technology Beijing China Engineering Research Center of Intelligent Perception and Autonomous Control Ministry of Education Beijing China Beijing Laboratory of Smart Environmental Protection Beijing China Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing China Beijing Artificial Intelligence Institute Beijing China Faculty of Science Beijing University of Technology Beijing China

ISBN: (纸本)9789811922657

In recent years, computer vision applied in industrial application scenarios has been attracting attention. A lot of work has been made to present approaches based on visual perception, ensuring the safety during the processes of industrial production. However, much less effort has been done to assess the perceptual quality of corrupted industrial images. In this paper, we construct an Industrial Scene Image Database (ISID), which contains 3000 distorted images generated through applying different levels of distortion types to each of the 50 source images. Then, the subjective experiment is carried out to gather the subjective scores in a well-controlled laboratory environment. Finally, we perform comparison experiments on ISID database to investigate the performance of some objective image quality assessment algorithms. The experimental results show that the state-of-the-art image quality assessment methods have difficulty in predicting the quality of images that contain multiple distortion types. © 2022, Springer Nature Singapore Pte Ltd.

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

Multi-Loss Function for Distance-to-collision Estimation

Multi-Loss Function for Distance-to-collision Estimation

引用

2021 International Conference on Information, Cybernetics, and Computational Social systems, ICCSS 2021

作者： Zhang, Xiangzhu Zhang, Lijia Xu, DIng Pei, Hailong South China University of Technology Key Laboratory of Autonomous Systems and Networked Control Min. of Educ. Unmanned Aerial Vehicle Systems Engineering Technology Research Center of Guangdong Guangzhou China Guangdong University of Technology School of Computer Science and Technology Guangzhou China

ISBN: (纸本)9781665402453

Estimation of the drone's distance-to-collision is the key to the indoor autonomous obstacle avoidance and navigation of monocular UAVs. At present, the distance-to-collision model mainly uses regression loss or ordinal regression for training Regression loss utilizes the continuity of distance, and ordinal regression loss utilizes the order of distance. To improve the prediction performance of the model, this paper proposes a multi-loss function trained deep learning model based on the linear combination of ordinal regression loss and regression loss. The regression loss can be obtained by adding a distance decoder after the ordinal regression estimation, without changing the original structure of the model. Finally, we test the model performance in public datasets and obtain good results. © 2021 IEEE.

关键词： Regression analysis

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：