检索结果-内蒙古大学图书馆

Collaborative Task Offloading Based on Deep Reinforcement Learning in Heterogeneous Edge Networks 20

Collaborative Task Offloading Based on Deep Reinforcement Le...

20th IEEE International Wireless Communications and Mobile Computing (IEEE IWCMC) - Green and Intelligent Communications

作者： Du, Yupeng Huang, Zhenglei Yang, Shujie Xiao, Han Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing Peoples R China Res Inst China Mobile Beijing Peoples R China

ISBN: (纸本)9798350361261;9798350361278

The field of multimedia video has shown a vigorous development trend in recent years. The massive heterogeneous data computing tasks generated by new multimedia applications cause user experience to face two major challenges: latency and energy consumption. The emergence of multimedia edge networks allows users' computing tasks to be offloaded to edge servers for execution, which will greatly reduce communication delays. But on the contrary, multimedia edge networks also face problems such as limited communication and computing resources, unknown global system information and difficulty in multi-agent collaboration. In this paper, we first describe a multimedia edge network architecture. In this architecture, multiple edge servers use communication base stations to provide multimedia computing services to a large number of users. Then a multi-agent collaborative decision-making model is proposed, which ensures that agents with different strategies can ultimately achieve consistent decision-making. Finally, we provide a distributed computing task scheduling algorithm based on deep reinforcement learning. A large number of simulation experiments have proven the superiority of this method in minimizing delay, energy consumption and convergence.

关键词： multimedia task offloading network multi agent deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Space-Terrestrial Integrated Time-Sensitive Networks: Architecture, Challenges, and Open Issues

引用

IEEE NETWORK 2025年第3期39卷 140-147页

作者： Peng, Guoyu Wang, Shuo Li, Guizhen Huang, Tao Huang, Yudong Liu, Yunjie Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China China Mobile Chengdu Inst Res & Dev Chengdu 610000 Peoples R China Purple Mt Labs Nanjing 211111 Peoples R China

Space-terrestrial integrated network (STIN) has been recognized as a novel network paradigm to offer global seamless coverage and enhanced service capacity in emerging 6G networks. Being a promising technology, time-sensitive networking (TSN) has been deemed essential for supporting delay sensitivity and driving service perception in STIN. However, most of the existing works in TSN-enabled STIN focus on migrating terrestrial TSN mechanisms to satellite networks, with little attention given to the feasibility of delay-oriented task processing across earth-space domains. Furthermore, the problem of hierarchical TSN platform integration architecture design and heterogeneous time-sensitive clusters cooperative communication, have not been fully considered. Thus, different from previous studies, this article presents a novel network architecture named space-terrestrial time-sensitive network (STTSN), which integrates space, aerial, and terrestrial TSN clusters to provide ubiquitous coverage, predictable low-latency connectivity, and quality of experience (QoE)-driven service continuity. The key functional modules of the STTSN are detailed, and we propose the promising technical challenges, including Internet of Things (IoT) service slicing, multi-domain cooperative communication, mobility management, and dynamic configuration. Finally, some potential research issues for future research are discussed.

关键词： Internet of Things Computer architecture Satellites Delays 6G mobile communication Real-time systems Processor scheduling Collaboration Ultra reliable low latency communication Quality of experience Space-air-ground integrated networks Time-sensitive networking space-terrestrial integrated networks 6G network architecture

来源：评论

学校读者我要写书评

暂无评论

Semantic information processing for interoperability in the Industrial Internet of Things

引用

Fundamental Research 2024年第1期4卷 8-12页

作者： Shengshi Yao Yanpeng Lu Kai Niu Jincheng Dai Chao Dong Ping Zhang Key Laboratory of Universal Wireless Communications Ministry of EducationBeijing University of Posts and TelecommunicationsBeijing 100876China The State Key Laboratory of Networking and Switching Technology Beijing University of Posts and TelecommunicationsBeijing 100876China

With the advent of the Internet of Everything(IoE),the concept of fully interconnected systems has become a reality,and the need for seamless communication and interoperability among different industrial systems has become more pressing than ever *** address the challenges posed by massive data traffic,we demonstrate the potentials of semantic information processing in industrial manufacturing processes and then propose a brief framework of semantic processing and communication system for industrial *** particular,the scheme is featured with task-orientation and collaborative *** illustrate its applicability,we provide examples of time series and images,as typical industrial data sources,for practical tasks,such as lifecycle estimation and surface defect *** results show that semantic information processing achieves a more efficient way of information processing and exchanging,compared to conventional methods,which is crucial for handling the demands of future interconnected industrial networks.

关键词： Semantic communication Intelligent manufacturing Signal processing Industrial Internet Task-oriented communication

来源：评论

学校读者我要写书评

暂无评论

Harmony: An Eco-Friendly Adaptive Rate Control Scheme for Video-on-Demand in Low Earth Orbit Satellite Internet

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO technology 2025年第4期35卷 3867-3881页

作者： Li, Zitong Xu, Changqiao Xiao, Han Fang, Chuxing Zhong, Lujie Yang, Shujie Muntean, Gabriel-Miro Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China Capital Normal Univ Informat Engn Coll Beijing 100048 Peoples R China Dublin City Univ Sch Elect Engn Performance Engn Lab Dublin 9 Ireland

This paper addresses the rate control issue for Video-on-Demand (VoD) services in Low Earth Orbit (LEO) satellite Internet. LEO systems employ long-distance Non-Orthogonal Multiple Access (NOMA), where the transmission rate of the last hop directly determines the Quality of Experience (QoE) levels for the VoD users and the satellite's energy consumption. Our research identifies two primary issues: (i) determining the transmission rate to ensure high user QoE while minimizing energy consumption, and (ii) ensuring fairness among users within the satellite coverage area. To address these issues, we model the multi-user VoD viewing process as a Partially Observable Markov Process (POMDP) and describe the interactions among users using a cooperative coalition game framework. We propose Harmony, a distributed and dynamic improvement solution based on the Deep Deterministic Policy Gradient (DDPG) approach. Harmony intelligently determines each user's transmission rate by combining feedback from user applications and MEC server metrics, ensuring superior QoE levels, energy efficiency, and fairness. The trained Harmony can be adapted to various Adaptive BitRate (ABR) algorithms, providing scalability and immediate applicability in existing LEO networks. It can also achieve improved performance in dynamic user environments. Simulation results demonstrate that Harmony improves energy efficiency and fairness, while maintaining high QoE levels and reducing MEC traffic overhead by 28.1% to 62.6%.

关键词： LEO satellite internet video-on-demand non-orthogonal multiple access transmission rate decision dynamic cooperative reinforcement learning LEO satellite internet video-on-demand non-orthogonal multiple access transmission rate decision dynamic cooperative reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

CSMA/PJ: A Protective Jamming Based MAC Protocol to Harmonize the Long and Short Links

引用

IEEE-ACM TRANSACTIONS ON networking 2023年第1期31卷 118-132页

作者： Zhu, Shaopeng Zheng, Xiaolong Liu, Liang Ma, Huadong Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China Beijing Univ Posts & Telecommun Sch Comp Sci Beijing 100876 Peoples R China

WiFi-based Long Distance (WILD) networks are promising to cover the rural and remote regions. But the explosive short-range Wail deployments result in the long-short coexistence. Due to CSMA is ignorance of propagation delay, its carrier sensing is too short to detect long links, leading to the temporal hidden terminal problem that causes serious performance degradation and even starvation of long links. Existing methods for traditional hidden terminal problem are inefficient to cope with this problem because of the different causes. In this paper, we propose CSMA with Protective Jamming (CSMA/PJ), a new WiLD MAC protocol that solves the temporal hidden terminal problem with the minimized influence on uncontrollable short links. The key is generating protective jamming at the WILD receiver that is sensible to the short links. By leveraging the asymmetric propagation delay of the WiLD transmitter and receiver, we make the jamming protective rather than destructive. We precisely control the jamming right before the arrivals of WiLD packets to set aside channel time for short links. We implement and evaluate CSMA/PJ on commercial devices. The experimental results show that CSMA/PJ can improve the throughput of the WiLD link by 6x and 5x compared with the CSMA/CA and RTS/CTS methods.

关键词： WiFi-based long distance coexistence MAC protocol

来源：评论

学校读者我要写书评

暂无评论

Improving unified named entity recognition by incorporating mention relevance

引用

NEURAL COMPUTING & APPLICATIONS 2023年第30期35卷 22223-22234页

作者： Ji, Lijun Yan, Danfeng Cheng, Zhuoran Song, Yan Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China Shanghai Int Studies Univ Sch Business & Management Shanghai 200092 Peoples R China

Named entity recognition (NER) is a fundamental task for natural language processing, which aims to detect mentions of real-world entities from text and classifying them into predefined types. Recently, research on overlapped and discontinuous named entity recognition has received increasing attention. However, we note that few studies have considered both overlapped and discontinuous entities. In this paper, we proposed a novel sequence-to-sequence model that is capable of recognizing both overlapped and discontinuous entities based on machine reading comprehension. The model utilizes machine reading comprehension formulation to encode significant inferior information about the entity category. Then input sequence passes through a question-answering model to predict the mention relevance of the given source sentences to the query. Finally, we incorporate the mention relevance into the BART-based generation model. We conducted experiments on three type of NER datasets to show the generality of our model. The experimental results demonstrate that our model beats almost all the current top-performing baselines achieves a vast amount of performance boost over current SOTA models on overlapped and discontinuous NER datasets.

关键词： Named entity recognition Sequence-to-sequence model Machine reading comprehension Mention relevance attention

来源：评论

学校读者我要写书评

暂无评论

An Energy Saving Strategy for IoT Wristband Terminals Combined with Human Activity Laws 13th

An Energy Saving Strategy for IoT Wristband Terminals Combin...

引用

13th International Conference on Computer Engineering and Networks, CENet 2023

作者： Chen, Yu Yang, Shaojie Guo, Shaoyong Zhi, Cai Yao, Hui Xiong, Ao State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications Beijing1008764 China Technology Co. Ltd. Beijing100036 China

ISBN: (纸本)9789819992386

With the rapid development of 5G and Internet of Things (IoT), the objects connected by 5G have expanded from people to everything, and smaller and lighter IoT terminals are involved in people's production and life. The IoT wristband terminal is a kind of popular wearable devices with functions of monitoring human exercise intensity, sleep quality and daily health. The operating energy consumption of the heart rate sensor and global positioning system (GPS) in the IoT wristband terminal is the main source of energy consumption of the wristband terminal. The limited battery capacity leads to the problem of limited energy and short endurance of the IoT wristband terminal, which cannot realize long time human health monitoring. In order to achieve energy saving while ensuring the health monitoring functions and performance of the IoT wristband terminal, we research the user requirements and human daily activity laws, use the anomaly detection algorithm based on binary Gaussian distribution to fit the relationship between acceleration and heart rate in human activities and propose the energy-saving strategies for heart rate sensor, and then use the decision tree algorithm to obtain the human activity state classification model and the energy-saving strategies for GPS is then proposed. Simulation experiments show that the proposed energy-saving strategies can more intelligently adjust the sampling frequency and working mode of the heart rate sensor and GPS, reduce the power consumption of high-power sensors and improve the endurance of the IoT wristband terminal. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Visual Sensing-Based Path Loss Prediction Method 99

Visual Sensing-Based Path Loss Prediction Method

引用

IEEE 99th Vehicular technology Conference (VTC-Spring)

作者： Tian, Yixuan Sun, Yutong Yu, Li Zhang, Jianhua Zhang, Yuxiang Liu, Guangyi Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing Peoples R China China Mobile Res Inst Beijing Peoples R China

ISBN: (纸本)9798350387414

Traditional path loss methods typically employ statistical or empirical models, without fully considering the dynamic propagation environment. In this paper, we introduce a method called Visual Sensing-Based Path Loss Prediction (VSB-PLM), which predicts path loss using visual data obtained from multi-view sensing cameras. Specifically, we deploy multi-view cameras in real-world scenarios. Then, a Convolutional Neural Network (CNN) is designed to integrate environmental image features, the existence of the Line-Of-Sight (LOS) path, and the distance between the Transmitter (Tx) and Receiver (Rx) for path loss prediction. Finally, optimal path loss prediction results are obtained utilizing a multi-view selection algorithm. Simulation results demonstrate that the proposed algorithm has successfully improved path loss prediction accuracy by 9% compared to single-view sensing, achieving a Root Mean Squared Error (RMSE) of 3.66 dB.

关键词： Path loss prediction environment sensing convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

VCOMP: An Efficient Probe Selection Method for 5G OTA Testing with MPAC Setup 16

VCOMP: An Efficient Probe Selection Method for 5G OTA Testin...

引用

16th International Conference on Wireless Communications and Signal Processing, WCSP 2024

作者： Li, Zhaoting Ma, Nan Qin, Xiaoqi Chang, Huigang Li, Nan Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology Beijing China Research Institute Co. Ltd Beijing China

ISBN: (纸本)9798350390643

The multi-probe anechoic chamber (MPAC) method is considered the most promising approach for over-the-air (OTA) testing of 5G massive multiple-input multiple-output (MIMO) devices. Since the cost of the MPAC system is directly influenced by the number of ports on the channel emulator, which corresponds to the number of OTA probes, the selection of probes is crucial for OTA testing. However, the classical convex-optimization-based probe selection method has become prohibitively complex due to the time-consuming computation of constrained weights and the ever-increasing number of candidate probes. Therefore, this paper proposes a variable step-size constrained orthogonal matching pursuit (VCOMP) algorithm. The proposed algorithm includes a constraint handling approach that combines closed-form solution with an iterative method, and a novel probe selection method with variable step-size initial screening and correction. Simulation results indicate that, compared with existing algorithms, the proposed algorithm achieves higher channel reconstruction accuracy in a shorter time, making it more suitable for massive MIMO testing scenarios. © 2024 IEEE.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Integrated Localization and Communication for IRS-Assisted Multi-User mmWave MIMO Systems

引用

IEEE TRANSACTIONS ON COMMUNICATIONS 2024年第8期72卷 4725-4740页

作者： Peng, Xingyu Hu, Xiaoling Gao, Jiabao Jin, Richeng Chen, Xiaoming Zhong, Caijun Zhejiang Univ Coll Informat Sci & Elect Engn Hangzhou 310027 Peoples R China Zhejiang Prov Key Lab Informat Proc Commun & Netw Hangzhou 310007 Peoples R China Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China

This paper delves into the potential of intelligent reflecting surfaces (IRSs) in enabling integrated sensing and communication (ISAC) in multi-user multi-path scenarios. We introduce a three-dimensional (3D) multi-user ISAC framework with distributed IRSs, which offers simultaneous signal demodulation, channel estimation, and localization. The transmission is divided into a user access stage and a downlink transmission stage. In the first stage, we propose an algorithm for simultaneous uplink signal demodulation and angles of arrival (AoA) estimation at the semi-passive IRS. Moreover, a joint active and passive beamforming scheme inspired by radar-communication, is proposed to enhance both communication and localization performance in the downlink stage, while eliminating the need for distinct localization reference signals. Numerical results demonstrate that the proposed ISAC framework achieves centimeter-level localization accuracy while maintaining comparable communication performance to communication-only systems, thus validating its effectiveness.

关键词： Sensors Array signal processing Location awareness Robot sensing systems Downlink Interference Channel estimation Intelligent reflecting surface (IRS) integrated sensing and communication (ISAC) beamforming localization

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：