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

Shape Embedding and Knowledge Mining network for Generalized Few-Shot Remote Sensing Segmentation

引用

IEEE Geoscience and Remote Sensing Letters 2025年

作者： Qiu, Zifeng Liu, Hongyu Xiong, Hang Di, Chengliang Fang, Hao Cong, Runmin Beijing Jiaotong University Institute of Information Science Beijing100044 China The54th Research Institute of CETC Shijiazhuang050081 China China Communication System Co. Ltd. Hebei Branch Shijiazhuang050081 China Shandong University School of Control Science and Engineering Jinan250061 China Ministry of Education Key Laboratory of Machine Intelligence and System Control Jinan250061 China Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing100044 China

In recent years, generalized few-shot segmentation (GFSS) has received widespread attention from scholars by virtue of its superiority in low-data regimes. Most of the existing research focuses on natural image processing, and few studies have been devoted to the practical but challenging topic of remote sensing image (RSI) understanding. In this paper, we propose a Shape Embedding and Knowledge Mining network (SKNet) for generalized few-shot RSI segmentation. Specifically, the framework is divided into two key stages: (a) In the base class learning stage, shape representation embedding is introduced to enhance the network's ability to perceive remote sensing objects. Simultaneously, we introduce the self-reconstruction constraint to prevent new unseen classes from merging, thereby improving the representation uniqueness of these classes. (b) In the novel class learning stage, a base class knowledge mining mechanism is designed to update the prototypes of the novel class by using the prototype representation of the base class, so as to enhance the discrimination ability of the network. We validated our methods on the adapted version of OpenEarthMap and iSAID datasets. In comparison with existing GFSS methods, the proposed approach demonstrates an advancement. © 2004-2012 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

A scalable peer-to-peer indexing scheme for high dimensional nearest- neighbor search in massive datasets

引用

Journal of Convergence Information Technology 2011年第9期6卷 131-139页

作者： Liu, Dawei Zhu, Ming The Key Lab of Network Communication System and Control The Chinese Academy of Sciences University of Science and Technology of China China The Key Lab of Network Communication System and Control Anhui Department of Automation University of Science and Technology of China China

Nearest-Neighbor (NN) search is an increasingly important problem in many computer applications, in which high dimensional massive datasets are involved. In this paper, we propose a P2P distributed indexing scheme to perform NN search in massive datasets. We consider the locality sensitive hashing (LSH) scheme under lp-metric to support similarity search in high dimensional space and we put forward a novel mapping from the multi-dimensional LSH bucket space to the one dimension DHT key space using nun-uniform Hilbert Curve. We consider the requirements of both similarity search and the maintenance of P2P network. Our indexing scheme preserves the locality sensitive property of LSH indexes and guarantees load balance in DHT networks. We also show how to leverage the LSH indexing scheme to efficiently process NN search in P2P network. Experiments on real world data confirm the effectiveness and efficiency of our approach and show the scalability gains compared to state-of-the-art schemes.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

A dynamic programming algorithm for QoS-aware replica placement in distributed caching systems

引用

Journal of Convergence Information Technology 2012年第12期7卷 226-234页

作者： Wang, Biyao Wang, Jinlin Liu, Xue The Key Lab of Network Communication System and Control The Chinese Academy of Sciences The Key Lab of Network Communication System and Control Anhui Department of Automation University of Science and Technology China National Network New Media Engineering Research Center Institute of Acoustics Chinese Academy of Sciences China

The rapid growth of new information services, especially like new media services, providing content distribution to clients with good quality of service(QoS) while retaining efficient is a great challenge. This paper investigates the QoS-aware replica placement problem (QRPP) for distributed caching system. We propose a dynamic programming algorithm for the problem in general graph, it first ensures the QoS requirement is satisfied of each request, then places the replica along the request forward path to minimize the total cost. The simulation results show the dynamic programming algorithm can achive a good balance between the access latency and the requested availability. When the request is more concentrated, the dynamic programming algorithm can have better performance than the MODULO and LRU both in access latency and requested availability.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Enhanced Generalized Spatial Modulation for STAR-RIS-Aided Vehicular communication system

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Shang, Pingping Han, Xue Hou, Jia Li, Jun Wang, Shucheng Hubei University of Technology School of Electrical and Electronic Engineering Wuhan430068 China Hubei University of Technology Hubei Key Lab. for High-Efficiency Utiliz. of Solar Ener. and Oper. Control of Energy Storage System Wuhan430068 China Soochow University School of Electronic and Information Engineering Suzhou215000 China Guangzhou University School of Electronics and Communication Engineering Guangzhou510006 China Wuhan Maritime Communication Research Institute Wuhan430205 China

In this paper, a novel scheme is proposed by introducing the concept of generalized spatial modulation (GSM) and space-time block code (STBC) into simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) for vehicular communication system. To improve spectral efficiency and diversity gain of vehicular system, STAR-RIS array elements are categorized into reflective and transmissive blocks, establishing a mapping relationship with the index bits by using GSM. Subsequently, the modulated symbols are reflected or transmitted based on the predetermined allocation patterns of the blocks. Specifically, to enhance the reliability of signal reception, one of the most renowned STBC schemes, the Alamouti code, is employed at the STAR-RIS surface by receiving and detecting signals across two consecutive time slots. Furthermore, the new design of leveraging STAR-RIS as an access point (AP) is proposed, which plays the role of source in the communication scenario. The mathematical formulas and theoretical average bit error rate (BER) of the scheme are derived based on preceding analysis. According to simulation results, the suggested scheme can outperform conventional schemes in terms of BER performance. In addition, the proposed redesigned scheme further improves the BER performance with better channel conditions, exhibiting excellent performance advantages. © 1975-2011 IEEE.

关键词： Space-time block coding (STBC)

来源：评论

学校读者我要写书评

暂无评论

Synchronous locating for multi-view video broadcast with time-shifted functionality

Synchronous locating for multi-view video broadcast with tim...

引用

2010 International Conference on Biomedical Engineering and Computer Science, ICBECS 2010

作者： Zhou, Jun Zhu, Ming Li, ZiMian Key Laboratory of Network Communication System and Control Anhui Key Laboratory of Network Communication System and Control USTC Hefei Anhui 230027 China

ISBN: (纸本)9781424453153

The prototype of time-shifted system on multi-view video is proposed for the first time in this paper. Synchronous locating of multi-view video streams is one of the key issues in supporting time-shifted function. In time-shifted system, video streams are forever lasting, the relative time, as the traditional locating index, now is meaningless to clients, as they would never know when the real moment the video stream has play to. We propose to use the Absolute Globe Time (AGT) as locating index. The AGT index is created for each stream at encoding stage respectively. The proposed synchronous capture scheme ensures the multi-view video streams are aligned frame by frame and sharing identical start time. Thus the frames with identical AGT index between multi-view video streams are synchronous captured groups. To locate inner single stream, frame-level seeking is deployed with AGT index, the exact frame is found. Packet-level seeking is launched with both AGT index and sequence number of RTP header, and the right packet is confirmed. With the proposed scheme, locating between multi-view video streams can be done with respective locating of each stream. ©2010 IEEE.

关键词： Video streaming

来源：评论

学校读者我要写书评

暂无评论

AN improved Ant Colony Optimization Algorithm for QoS-Aware Dynamic Web Service Composition

AN improved Ant Colony Optimization Algorithm for QoS-Aware ...

引用

International Conference on Industrial control and Electronics Engineering (ICICEE)

作者： Zhao Shanshan Ma Lin Wang Lei Wen Zepeng Department of Automation USTC Key laboratory of network communication system and control Anhui Department of Electronic Engineering & Information Science USTC Key laboratory of network communication system and control Anhui

ISBN: (纸本)9780769547923

A lot of work have been carried out to find the efficient algorithms for QoS-aware dynamic web service composition. The multi-objective multi-choice problem as an evolutive multi-dimension multi-objective 0-1 knapsack problem (MMKP) can be reduced into the web service composition with multiple QoS constraints, while many approaches based on ant colony optimization (AOC) have been introduced in order for solving MMKP. This paper presents a novel QoS-aware dynamic web service composition optimization algorithm with improved AOC. The essence of the algorithm is that the problem of dynamic web service selection with QoS global optimality is transformed into a multi-objective multi-choice QoS-aware web services composition optimization (an evolutive MMKP), for the final purpose of our algorithm is to achieve Pareto Optimality.

关键词： Multi-objective multi-choice problem AOC QoS service composition

来源：评论

学校读者我要写书评

暂无评论

A multimedia streaming system with self-healing infrastructure

A multimedia streaming system with self-healing infrastructu...

引用

2010 2nd IEEE International Conference on Information Management and Engineering, ICIME 2010

作者： Zimian, Li Ming, Zhu Jun, Li Key Laboratory of Network Communication System and Control USTC CAS Hefei Anhui 230027 China Anhui Key Laboratory of Network Communication System and Control USTC Hefei Anhui 230027 China

ISBN: (纸本)9781424452644

This paper proposes a feedback-loop infrastructure attached to our legacy multimedia streaming system to continually monitor its activities and performance and rapidly recover the system from failures or error states. Our infrastructure consists of four components: monitors with sensors to measure and record the activities and state of among the components of the running system, analyzer to interpret and abstract the logged data, planner to decide what action to take for reported situations and executants to adjust and reconfigure the system via effectors. An event-based schema is proposed to efficiently deliver recorded system information among our infrastructure components. We summarize our successful examples using this approach in dynamically self-healing for our streaming application. © 2010 IEEE.

关键词： Feedback

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

A branch convergence approach to distributed dynamic service composition

A branch convergence approach to distributed dynamic service...

引用

International Conference on Advanced Computer Theory and Engineering

作者： Ma, Lin Zhu, Ming Wang, Lei Department of Electronic Engineering and Information Science Key Laboratory of Network Communication System and Control CAS Hefei China Department of Automation Key Laboratory of Network Communication System and Control CAS Hefei China

ISBN: (纸本)9781424465408

Web Service composition is a very promising way to generate new services on service oriented architecture (SOA). It will come across subsequent branch convergence problem when implementing parallel process in the distributed environment, which is some parallel branches can't converge at one executive node. In this paper, we introduce a Branch Convergence Approach based on Common Node (BCACN) to solve this problem. A common node which is chosen before branches converging, make a decision to choose a convergent node, such that all subsequent branches can merge into an executive node. Experimental studies demonstrate the effectiveness of the proposed approach. © 2010 IEEE.

关键词： Information services

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：