检索结果-内蒙古大学图书馆

Stochastic programming based multi-arm bandit offloading strategy for internet of things

Digital Communications and Networks 2023年第5期9卷 1200-1211页

作者： Bin Cao Tingyong Wu Xiang Bai State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications Beijing100876China National Key Laboratory of Science and Technology on Communications University of Electronic Science and Technology of ChinaChengdu611731China China Electrics Technology Cyber Security Co..Ldt Chengdu611731China

In order to solve the high latency of traditional cloud computing and the processing capacity limitation of Internet of Things(IoT)users,Multi-access Edge Computing(MEC)migrates computing and storage capabilities from the remote data center to the edge of network,providing users with computation services quickly and *** this paper,we investigate the impact of the randomness caused by the movement of the IoT user on decision-making for offloading,where the connection between the IoT user and the MEC servers is *** uncertainty would be the main obstacle to assign the task ***,if the assigned task cannot match well with the real connection time,a migration(connection time is not enough to process)would be *** order to address the impact of this uncertainty,we formulate the offloading decision as an optimization problem considering the transmission,computation and *** the help of Stochastic Programming(SP),we use the posteriori recourse to compensate for inaccurate ***,in heterogeneous networks,considering multiple candidate MEC servers could be selected simultaneously due to overlapping,we also introduce the Multi-Arm Bandit(MAB)theory for MEC *** extensive simulations validate the improvement and effectiveness of the proposed SP-based Multi-arm bandit Method(SMM)for offloading in terms of reward,cost,energy consumption and *** results showthat SMMcan achieve about 20%improvement compared with the traditional offloading method that does not consider the randomness,and it also outperforms the existing SP/MAB based method for offloading.

关键词： Multi-access computing Internet of things Offloading Stochastic programming Multi-arm bandit

来源：评论

学校读者我要写书评

暂无评论

DBT-PDP:Provable data possession with outsourced data batch transfer based on blockchain

引用

High-Confidence Computing 2024年第2期4卷 62-72页

作者： Chengming Yi Hua Zhang Weiming Sun Jun Ding State key Laboratory of Networking and Switching Technology Beijing University of Posts and TelecommunicationsBeijing 100876China Zhe Jiang Computer Network Emergency Response Technical Team Hangzhou 310052China

In the scenario of large-scale data ownership transactions,existing data integrity auditing schemes are faced with security risks from malicious third-party auditors and are inefficient in both calculation and communication,which greatly affects their *** paper proposes a data integrity audit scheme based on blockchain where data ownership can be traded in batches.A data tag structure which supports data ownership batch transaction is adopted in our *** update process of data tag does not involve the unique information of each data,so that any user can complete ownership transactions of multiple data in a single transaction through a single transaction auxiliary *** the same time,smart contract is introduced into our scheme to perform data integrity audit belongs to third-party auditors,therefore our scheme can free from potential security risks of malicious third-party *** analysis shows that our scheme is proved to be safe under the stochastic prediction model and k-CEIDH *** with similar schemes,the experiment shows that communication overhead and computing time of data ownership transaction in our scheme is ***,the communication overhead and computing time of our scheme is similar to that of similar schemes in data integrity audit.

关键词： Data integrity Cloud outsourcing audit Data ownership batch transaction Blockchain Smart contract

来源：评论

学校读者我要写书评

暂无评论

Near-Field Sensing of mmWave XL-MIMO Systems through Joint Parabolic Interpolation and Barycenter Calibration 2

Near-Field Sensing of mmWave XL-MIMO Systems through Joint P...

引用

2nd IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2024

作者： Zhao, Baoyue Liu, Xiqing Wang, Zhaoqi Peng, Mugen State Key Laboratory of Networking and Switching Technology School of Information and Communication Engineering Beijing University of Posts and Telecommunications China

ISBN: (纸本)9798331515669

The pursuit of higher data rates in next-generation mobile communications necessitates the use of higher frequency bands and larger antenna arrays. These shifts will extend the Rayleigh distance, resulting in near-field effects, where traditional far-field algorithms for source sensing yield considerable errors. Moreover, near-field spatial spectrum estimation algorithms require multi-dimensional spectral peak searches, which lead to high computational complexity and necessitate a trade-off between sensing accuracy and real-time performance. To address these issues, we propose the joint parabolic interpolation and barycenter calibration (PI-BC) algorithm, a calibration method for near-field spectral peak searches. The joint PI-BC algorithm significantly boosts sensing accuracy while maintaining low computational complexity, thus providing a real-time, efficient solution for near-field sensing. © 2024 IEEE.

关键词： Interpolation

来源：评论

学校读者我要写书评

暂无评论

Improved MAPPO-based Collaborative Computing Offloading Algorithm in Broadband Mobile Internet

Improved MAPPO-based Collaborative Computing Offloading Algo...

引用

2023 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting, BMSB 2023

作者： Hu, Hao Yang, Yang Guo, Yanpeng Gao, Zhipeng Rui, Lanlan Beijing University of Posts and Telecommunication State Key Laboratory of Networking and Switching Technology Beijing China

ISBN: (纸本)9798350321524

Collaborative computation offloading technology can offload computational tasks from mobile devices to mobile edge servers and idle devices, thus breakthrough the performance bottleneck of MEC computation offloading systems and providing a new idea to meet the needs of computation-intensive mobile applications. In collaborative computation offloading systems, variations in the number of mobile devices cause changes of their state space and action space, and traditional deep reinforcement learning-based computation offloading decision algorithms (e.g., MADDPG) are usually unavailable at this case. A computational offloading algorithm based on improved MAPPO is proposed to transform variable dimensional input information into fixed dimensional aggregated information through the attention mechanism, ensuring that the input dimensions of the policy network and value network do not change with the number of smart devices, which meet the demand for flexibility and scalability of computational offloading decision algorithms in collaborative computational offloading systems. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Shooting and Bouncing Rays Method for Ray-Tracing Channel Modeling Assisted by Environmental Prior Information for 6G 35

An Adaptive Shooting and Bouncing Rays Method for Ray-Tracin...

引用

35th IEEE International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC 2024

作者： Luo, Yubin Yu, Li Miao, Yinghe Zhang, Yuxiang Zhang, Jianhua Beijing University of Posts and Telecommunications State Key Lab of Networking and Switching Technology China

ISBN: (纸本)9798350362244

Due to the fact that the scale and construction of 6G communication systems are progressing toward unprecedentedly large and complex, accuracy and robustness of channel modeling method are vital to ensure that communication systems can work efficiently. Ray-Tracing (RT), as a precise deterministic modeling method, can meet most of these requirements. Shooting and Bouncing Rays (SBR) is a forward RT algorithm with high efficiency and wide usage. Traditional SBR utilizes environmental prior information, like distribution of scatters, only in path-finding. Channel parameters like quantity of rays are determined artificially, which affects SBR's performance especially in 6G systems. In order to enable SBR to conduct 6G modeling stably and efficiently, we propose an advanced SBR algorithm that utilizes environmental prior information globally for both path-finding progress and parameter-determination. Space-division, face-classification are some environmental-information-assisted processes of the proposed algorithm, which help to calculate channel parameters quantitatively. Additionally, our new algorithm accelerates path-finding progress by decreasing unnecessary intersections through space-division. Simulation reveals our new algorithm reduces computational complexity by 34.53% in comparison of traditional SBR. Furthermore, with Image Method (IM) as a standard, new algorithm has smaller Normalized Mean Squared Error (NMSE) of 78.09% less in LOS-path ignoring power-receiving, compared to traditional SBR. Other metrics such as Power-Delay Profile (PDP) are also demonstrated in our work. © 2024 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Lightweight Cloud Native Application Management Platform 24

Lightweight Cloud Native Application Management Platform

引用

7th International Conference on Software Engineering and Information Management, ICSIM 2024

作者： Chen, Yanpiao Peng, Shan State Key Lab of Networking and Switching Technology Beijing University of Post and Telecommunications China

ISBN: (纸本)9798400709197

In order to achieve comprehensive management and integration necessary for digital transformation, a large number of enterprises are now seeking solutions to establish an application management *** analyzing the development of application management platforms, it has been observed that they face numerous challenges and issues. One of the major challenges is the significant diversity in the environments where different applications operate. Various applications may be based on different technology frameworks, programming languages, or rely on different underlying infrastructures, leading to the complexity and difficulty in managing these diverse applications. However, the introduction of cloud-native technology has provided important solutions and opportunities to address this *** have implemented a lightweight cloud-native application management platform specifically designed for small and medium-sized enterprises. This management platform aims to provide various types of application runtime environments for different digital applications within an enterprise, supporting container-level application execution and offering comprehensive application management functionalities. By supporting multi-layered application templates (including Helm Chart templates, native YAML templates, etc.), it simplifies application deployment, achieving lightweight application deployment. Leveraging this application management platform, enterprises can rapidly establish and maintain their infrastructure for digital transformation. © 2024 ACM.

关键词： Containers

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning for Resource Allocation With Mixed Traffic in NOMA System

Deep Reinforcement Learning for Resource Allocation With Mix...

引用

2023 IEEE/CIC International Conference on Communications in China, ICCC 2023

作者： Liu, Miao Meng, Yue Zhang, Zhi Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology Beijing China

ISBN: (纸本)9798350345384

The non-orthogonal multiple access (NOMA) system with mixed traffic has emerged as a promising solution to satisfy the requirements of various services while mitigating the spectrum scarcity issue. In this paper, we investigate the resource allocation problem with mixed traffic in an uplink NOMA system, which consists of real-time (RT) users with strict quality-of-service (QoS) requirements on rate and latency, and best-effort (BE) users that aim to achieve a balance between throughput and fairness. In order to account for the diverse requirements of different users, we propose a utility function and formulate the resource allocation problem. To address this mixed integer non-convex problem, a deep reinforcement learning (DRL) algorithm is proposed which consists of two parts. Specifically, we design a deep Q network (DQN) to generate subcarrier assignment policies and a deep deterministic policy gradient (DDPG) network to generate power allocation policies. Simulation results demonstrate that the proposed algorithm outperforms existing algorithms in the proposed utility function. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Boosting DNN Cold Inference on Edge Devices 23

Boosting DNN Cold Inference on Edge Devices

引用

21st Annual International Conference on Mobile Systems, Applications and Services, MobiSys 2023

作者： Yi, Rongjie Cao, Ting Zhou, Ao Ma, Xiao Wang, Shangguang Xu, Mengwei State Key Laboratory of Networking and Switching Technology Beijing China Microsoft Research Beijing China

ISBN: (纸本)9798400701108

DNNs are ubiquitous on edge devices nowadays. With its increasing importance and use cases, it's not likely to pack all DNNs into device memory and expect that each inference has been warmed up. Therefore, cold inference, the process to read, initialize, and execute a DNN model, is becoming commonplace and its performance is urgently demanded to be optimized. To this end, we present NNV12, the first on-device inference engine optimizing cold inference. NNV12 is built atop three novel optimization knobs: selecting a proper kernel (i.e., operator implementation) for each DNN operator, bypassing the weights transformation process by caching the post-transformed weights on disk, and pipelined execution of many kernels on asymmetric processors. To tackle with the huge search space, NNV12 employs a heuristic-based scheme to obtain a near-optimal kernel scheduling plan. We fully implement a prototype of NNV12 and evaluate its performance across extensive experiments. It shows that NNV12 achieves up to 15.2× speedup compared to the state-of-the-art DNN engines on edge CPUs and 401.5× speedup on edge GPUs, respectively. © 2023 Owner/Author(s).

关键词： Engines

来源：评论

学校读者我要写书评

暂无评论

Logical-Cluster-Based Personalized Federated Multi-Task Learning for Internet of Vehicles

Logical-Cluster-Based Personalized Federated Multi-Task Lear...

引用

2023 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting, BMSB 2023

作者： Zhang, Biao Xu, Siya Qiu, Xusong Tian, Jingyue Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology Beijing China

ISBN: (纸本)9798350321524

Federated learning (FL) is an emerging distributed machine learning paradigm that emphasizes user privacy. The majority of current federated learning systems are oriented for single task while participants in the Internet of Vehicles (IoV) demand to train different models for multiple intelligent services simultaneously. As one of transfer learning methods, multi-task learning (MTL) has the potential to integrate with federated learning to realize personalized local training. However, the existing federated multi-task learning (FMTL) algorithms are faced with the problems of high implementation complexity and communication overhead. To solve the above issues, we propose a logical-cluster-based personalized federated multi-task learning framework named pFMTL. In the framework, the multi-task model is decomposed into a basic module for extracting features and K task-specific modules for outputting inferences. We leverage logical clusters and multi-task learning to enhance the personalization and generalization capability of task models, respectively. To improve the communication efficiency further, we also design a module-wise task scheduling strategy, which supports both user module scheduling and cluster aggregation scheduling to ensure the convergence of multi-task model with less communication overhead. Finally, the simulation results imply that pFMTL can increase task accuracy and reduce communication latency compared with other benchmarks. © 2023 IEEE.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

Trusted Content Distribution Mechanism in Vehicular Ad-Hoc Networks 11

Trusted Content Distribution Mechanism in Vehicular Ad-Hoc N...

引用

11th Joint International Information technology and Artificial Intelligence Conference, ITAIC 2023

作者： Liang, Chenghao Qiu, Xuesong Ren, Yinlin Qi, Yuanyuan Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology Beijing China

ISBN: (纸本)9798350333664

Vehicular Ad-hoc Networks (VANETs) play a crucial role in enhancing road safety through real-time information exchange. However, the fast-paced mobility of vehicles and the ever-present security threats during data interactions present substantial challenges to the practical deployment of VANETs. In response, this paper introduces a novel approach by integrating blockchain technology with Named Data networking (NDN). We propose an enhanced NDN protocol stack that shifts from traditional key data packet requests to a blockchain-based data registration system, allowing data retrieval by requesters. We also introduce a cache value sampling method for probability-based cache data sampling, and we present a cache replacement strategy that takes cache value into account, leveraging deep reinforcement learning techniques. Experimental results demonstrate that this improved NDN protocol stack, when combined with vehicular networks, achieves higher throughput and improved cache efficiency. © 2023 IEEE.

关键词： Blockchain Cache Replacement Strategy Deep Reinforcement Learning Named Data networking Vehicular Ad-hoc Networks

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：