检索结果-内蒙古大学图书馆

A pipelining task offloading strategy via delay-aware multi-agent reinforcement learning in Cybertwin-enabled 6G network

引用

Digital Communications and networks 2025年第1期11卷 92-105页

作者： Haiwen Niu Luhan Wang Keliang Du Zhaoming Lu Xiangming Wen Yu Liu Beijing Laboratory of Advanced Information Networks Beijing Univ.of Posts&TelecomBeijing 100876China Beijing Key Lab of Network System Architecture and Convergence Beijing Univ.of Posts&TelecomBeijing 100876China School of Information and Communication Engineering Beijing Univ.of Posts&TelecomBeijing100876China

Cybertwin-enabled 6th Generation(6G)network is envisioned to support artificial intelligence-native management to meet changing demands of 6G ***-Agent Deep Reinforcement Learning(MADRL)technologies driven by Cybertwins have been proposed for adaptive task offloading ***,the existence of random transmission delay between Cybertwin-driven agents and underlying networks is not considered in related works,which destroys the standard Markov property and increases the decision reaction time to reduce the task offloading strategy *** order to address this problem,we propose a pipelining task offloading method to lower the decision reaction time and model it as a delay-aware Markov Decision Process(MDP).Then,we design a delay-aware MADRL algorithm to minimize the weighted sum of task execution latency and energy ***,the state space is augmented using the lastly-received state and historical actions to rebuild the Markov ***,Gate Transformer-XL is introduced to capture historical actions'importance and maintain the consistent input dimension dynamically changed due to random transmission ***,a sampling method and a new loss function with the difference between the current and target state value and the difference between real state-action value and augmented state-action value are designed to obtain state transition trajectories close to the real *** results demonstrate that the proposed methods are effective in reducing reaction time and improving the task offloading performance in the random-delay Cybertwin-enabled 6G networks.

关键词： Cybertwin Multi-Agent Deep Reinforcement Learning(MADRL) Task offloading Pipelining Delay-aware

来源：评论

学校读者我要写书评

暂无评论

Dual-layer efficiency enhancement for future passive optical network

引用

Science China(Information Sciences) 2016年第2期59卷 172-184页

作者： Yuefeng JI Xiaoxiong WANG Shizong ZHANG Rentao GU Tonglu GUO Zhaozhi GE State Key Lab of Information Photonics and Optical Communications Beijing University of Posts and Telecommunications Beijing Key Laboratory of Network System Architecture and Convergence School of Information and Communication Engineering Beijing University of Posts and Telecommunications

Ever-increasing demands on bandwidth compel us to improve the bandwidth utilization of access networks. It is more important to enhance the efficiency of passive optical networks(PON) than other access technologies, as they are the primary solutions to various access scenarios. To satisfy the demands of improved bandwidth efficiency, we propose a dual-layer(data link layer and network layer) efficiency enhancement scheme for future PON system. Under this architecture, a data-link-layer flexible coding scheme is introduced to extend the downstream link throughput, and a network-layer centralized active queue management(AQM) scheme is introduced to increase bandwidth efficiency. Both of these technologies are designed to suit the future centralized cooperative control mode. The results of an experimental demonstration of the network coding PON scheme reveal the efficiency of the proposed architecture. The results of simulations show that the centralized AQM scheme has a positive influence on queuing delay and jitter. To the best of our knowledge, this is the first time that a data link layer mechanism and a network layer policy have been integrated to provide high efficiency and quality of service in access networks.

关键词： passive optical network bandwidth efficiency network coding active queue management centralized control

来源：评论

学校读者我要写书评

暂无评论

ML-SLD:A message-level stateless design for cloud-native 5G core network

引用

Digital Communications and networks 2023年第3期9卷 743-756页

作者： Keliang Du Luhan Wang Xiangming Wen Yu Liu Haiwen Niu Shaoxin Huang Beijing Laboratory of Advanced Information Networks China Beijing Key Lab of Network System Architecture and Convergence China School of Information and Communication Engineering Beijing Univ.of Posts&TelecomBeijing100876China

The Internet of Things(IoTs)has become an essential component of the 5th Generation(5G)network and beyond,accelerating the transition to digital *** increasing signaling traffic generated by billions of IoT devices has placed significant strain on the 5G Core network(5GC)control *** address this issue,the 3rd Gener-ation Partnership Project(3GPP)first proposed a Service-Based architecture(SBA),intending to create a flexible,scalab.e,and agile cloud-native ***,considering the coupling of protocol states and functions,there are still many challenges to fully utilize the benefits of the cloud computing and orchestrate the 5GC in a cloud-native *** propose a Message-Level StateLess Design(ML-SLD)to provide a cloud-native 5GC from an architectural standpoint in this ***,we propose an innovative mechanism for servitization of the N2 interface to maintain the connection between Radio Access network(RAN)and the 5GC,avoiding interruptions and dropouts of large-scale user ***,we propose an On-demand Message Forwarding(OMF)al-gorithm to reduce the impact of cloud fluctuations on the performance of cloud-native ***,we create a prototype that is based on the OpenAirInterface(OAI)5G core network projects,with all network Functions(NFs)packaged in dockers and deployed in a kubernetes-based cloud *** experiments have been built with UERANSIM and Chaosblade simulation *** findings demonstrate the viability and efficiency of our proposed methods.

关键词： Cloud-native 5G core network service Based architecture Stateless OpenAirInterface

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Joint NOMA and JT-CoMP Based on Stienen Model

引用

IEEE Transactions on Wireless Communications 2025年

作者： Chen, Yunpei Haenggi, Martin Zhu, Qi Guo, Caili Yuan, Yifei Hu, Zhuhua Li, Xiaohui Hainan Tropical Ocean University School of Marine Information Engineering Yazhou Bay Innovation Institute Sanya572022 China Nanjing University of Posts and Telecommunications School of Communication and Information Engineering Nanjing210003 China China Information Consulting and Designing Institute Company Ltd Chief Engineer's Office Nanjing210000 China University of Notre Dame Department of Electrical Engineering Notre DameIN46556 United States Nanjing University of Posts and Telecommunications Jiangsu Key Laboratory of Wireless Communications Nanjing210003 China Beijing University of Posts and Telecommunications Beijing Key Laboratory of Network System Architecture and Convergence School of Information and Communication Engineering Beijing100876 China China Mobile Research Institute Future Mobile Technology Lab Beijing100053 China Hainan University School of Information and Communication Engineering Haikou570228 China

For fifth-generation wireless networks to transition to sixth-generation wireless networks, the integration of coordinated multipoint (CoMP) and non-orthogonal multiple access (NOMA) techniques is expected to overcome new challenges and enhance performance compared to the CoMP or NOMA scheme. The joint-transmission CoMP (JT-CoMP) technique is a typical technical implementation of the CoMP scheme. In this study, we investigate a downlink network with a joint JT-CoMP-NOMA scheme. Based on the generalized Stienen model from stochastic geometry, we divide far and near NOMA user equipment (UE) and develop a theoretical framework to analyze the system performance. Expressions for the coverage probabilities and average achievable rates of two types of UEs (named CoMP and non-CoMP UEs) are derived. By comparing analytical results with Monte Carlo simulations, we show that the approximations in the analytical derivations are tight. The impact of certain network parameters, such as the power allocation coefficient, on the system performance is also studied. Notably, the developed transmission scheme is shown to outperform the NOMA-only and the JT-CoMP-only schemes. © 2002-2012 IEEE.

关键词： Monte Carlo methods

来源：评论

学校读者我要写书评

暂无评论

Combination of Polarization and OAM Multiplexing by a Single Reflective Metasurface in Terahertz Regime 9

Combination of Polarization and OAM Multiplexing by a Single...

引用

9th IEEE Asia-Pacific Conference on Antennas and Propagation, APCAP 2020

作者： He, Xiaoyuan Deng, Li Beijing University of Posts and Telecommunications Beijing Lab. of Advanced Information Networks Beijing Key Lab. of Network System Architecture and Convergence School of Information and Communication Engineering Beijing100876 China

ISBN: (数字)9781728198057

ISBN: (纸本)9781728198057

For achieving more multiplexing degrees, a method to generate and multiplex dual-polarized electromagnetic waves carrying orbital angular momentum(OAM) by a single reflective metasurface is proposed in this paper. Base on this method, a dual-polarized reflective metasurface that can generate eight OAM beams combined into a coaxial beam in terahertz regime is properly designed and simulated to verify this method. According to the simulation results, the proposed method provides an efficient way for a metasurface to generate and multiplex dual-polarized electromagnetic waves carrying OAM. © 2020 IEEE.

关键词： Electromagnetic wave polarization

来源：评论

学校读者我要写书评

暂无评论

TAX-B2BREC: Multi-Stage Cascade Downstream Company Recommender system Based on Taxation Data 7

TAX-B2BREC: Multi-Stage Cascade Downstream Company Recommend...

引用

7th IEEE International Conference on network Intelligence and Digital Content, IC-NIDC 2021

作者： Wang, Shengmin Chu, Yi Qiao, Zhenhao Ma, Lan Zhang, Hao Wang, Zehao Qiao, Yuanyuan Beijing University of Posts and Telecommunications Beijing Lab. of Adv. Info. Networks Beijing Key Lab. of Network System Architecture and Convergence Beijing100876 China The Technology Research Institute Aisino Corporation Beijing100195 China

ISBN: (纸本)9781665405829

The public crisis triggered by the COVID-19 pandemic has disastrous effects for B2B markets. With the supply chain and trade disrupted, the benefits of the company have been affected to varying degrees. In order to help companies find potential customers and recover the supply chain, we propose a multi-stage cascade downstream company recommender system based on taxation data. The proposed system can recommend potential buyers for upstream companies, which can help upstream companies find new sales channels. This system includes data processing, matching module, ranking module and system deployment. In the match module, we propose a hybrid recall algorithm to generate the candidate enterprises. In the ranking module, we use DCNV2 model to rank the candidate companies. Moreover, the multistage cascade recommendation algorithm achieves better results compared with the traditional algorithm in B2B recommender system. © 2021 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

WiFi band-stop FSS for increased privacy protection in smart building 6

WiFi band-stop FSS for increased privacy protection in smart...

引用

6th IEEE International Symposium on Microwave, Antenna, Propagation, and EMC Technologies, MAPE 2015

作者： Xiong, Xiong Hong, Weijun Zhao, Zhentao Li, Deng Li, Shufang College of Electronic and Information Engineering South China University of Technology Guangzhou China Beijing Key Lab. of Network System Architecture and Convergence Beijing Univ. of Posts and Telecommunications Beijing China

ISBN: (纸本)9781467374415

This paper proposes a periodic double ring strip frequency selective surface (FSS) with dual-band stop behavior. The FSS elements are designed to be etched on the transparent coating of glass substrate in smart buildings, which acts as a dual-band notch filter on 2.45GHz and 5.4GHz to avoid the leakage of WiFi signal outside the building. All the simulation parts are simulated by using High Frequency Structure Simulator (HFSS). The proposed FSS possesses 450MHz and 960MHz bandwidth with insertion loss more than -10dB around the two central operating frequencies 2.45GHz and 5.45GHz, respectively. Furthermore, the unit-cell structure provides a stable performance for both TE and TM polarizations with incident angles 0°-60 °. A prototype of the proposed FSS is fabricated and measured. Good agreement between the simulated and measured results is obtained. © 2015 IEEE.

关键词： Frequency selective surfaces

来源：评论

学校读者我要写书评

暂无评论

Exploiting Pose Mask Features for Video Action Recognition 5

Exploiting Pose Mask Features for Video Action Recognition

引用

5th IEEE International Conference on Computer and Communications, ICCC 2019

作者： Miao, Junqing Xia, Hailun Zeng, Zhimin Beijing University of Posts and Telecommunications Beijing Key Laboratory of Network System Architecture Convergence Beijing Lab. of Adv. Info. Networks Sch. of Info. and Communication Engineering Beijing China

ISBN: (纸本)9781728147437

Existing state-of-the-art approaches in video action recognition mostly adopt RGB images and optical flows as input and neglect the abundant information provided by human poses. In this paper, we present a novel method that highlights the essential area of human body and takes it as complementary input for existing action recognition pipelines. The method, called Pose Mask network (PMN), leverages a 2D pose estimator to extract heatmaps from frames and utilizes them as Pose Masks on the original images. The Pose Masks are robust to the variance of background and focus on key information of human body. Experiments show that our Pose Mask yields a result far exceeding that of using simple pose representations. More importantly, PMN acts as a supplement to other RGB-based approaches. Combining our PMN with Temporal Segment network, we obtain state-of-the-art performance on the HMDB51 and JHMDB datasets. © 2019 IEEE.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

Design of intelligent capabilities in SDN 4

Design of intelligent capabilities in SDN

引用

2014 4th International Conference on Wireless Communications, Vehicular Technology, Information Theory and Aerospace and Electronic systems, VITAE 2014 - Co-located with Global Wireless Summit

作者： Cui, Hongyan Zhu, Yabo Yao, Yuan Yufeng, Li Liu, Yunjie Beijing Key Lab. of Network System Architecture and Convergence Beijing University of Posts and Telecommunications Beijing China State Key Lab. of Networking and Switching Technology Beijing University of Posts and Telecommunications Beijing China Information Engineering University of the People's Liberation Army Zhenzhou China

ISBN: (纸本)9781479946266

Software-Defined networking (SDN) is an innovative and programmable networking architecture, representing the direction of the future network evolution. In this paper, we propose an architecture to introduce traffic classification techniques into the OpenFlow-based SDN network, which enables the network to be application-aware, so the network could distinguish various applications flows and know the requirements of different flows. Our new architecture also take advantage of the new intelligence to make the network forward traffic flows based flows' demands on bandwidth and delay, which could improve Quality of Service (QoS) of applications and optimize resource allocation all over the network. © 2014 IEEE.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

A Design of Decision Engine for 5G Auto-driving Based on Ontology Slice 5

A Design of Decision Engine for 5G Auto-driving Based on Ont...

引用

5th IEEE International Conference on Computer and Communications, ICCC 2019

作者： Zhang, Chenyu Wen, Xiangming Zheng, Wei Lu, Zhaoming Wang, Luhan Beijing Laboratory of Advanced Information Networks China Beijing Key Lab of Network System Architecture and Convergence China School of Information and Communication Engineering Beijing Univ. of Posts and Telecom Beijing100876 China

ISBN: (纸本)9781728147437

With the access to 5G network, auto-driving vehicles can upload their sensors' information to Mobile Edge Computing (MEC) and get driving decision results relaying on the powerful computing ability of MEC. This article presents an architecture of intelligent decision engine running on MEC for 5G auto-driving (IDEA) by adopting the concept of ontology slice. IDEA constructs an ontoligy slice for every vehicle including sensor information, vehicle status, rule bases, etc. and provides logical isolated resources to prevent interference between ontologies. This paper gives out the method of implementing and managing of the ontology slices and method of scheduling reasoner. Besides, to make better and safer decisions, this paper also proposes an algorithm, combining an analytic strategy algorithm (WADD) and a heuristic strategy algorithm (TTB), considering both vehicle's velocity and sensors' refresh rate, to deal with incomplete information before making decesions. With simulation, it is shown that IDEA can provide efficient and reliable auto-driving decision service with low processing time. © 2019 IEEE.

关键词： Ontology

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：