检索结果-内蒙古大学图书馆

TSCompiler: efficient compilation framework for dynamic-shape models

science China(information sciences) 2024年第10期67卷 67-84页

作者： Xiang LUO Chen ZHANG Chenbo GENG Yanzhi YI Jiahui HU Renwei ZHANG Zhen ZHANG Gianpietro CONSOLARO Fan YANG Tun LU Ning GU Li SHANG School of Computer Science Fudan University School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University School of Computer Science and Technology Harbin Institute of Technology Huawei Technologies Co. Ltd. Huawei Paris Research Center School of Microelectronics Fudan University

Today's deep learning models face an increasing demand to handle dynamic shape tensors and computation whose shape information remains unknown at compile time and varies in a nearly infinite range at runtime. This shape dynamism brings tremendous challenges for existing compilation pipelines designed for static models which optimize tensor programs relying on exact shape values. This paper presents TSCompiler, an end-to-end compilation framework for dynamic shape models. TSCompiler first proposes a symbolic shape propagation algorithm to recover symbolic shape information at compile time to enable subsequent optimizations. TSCompiler then partitions the shape-annotated computation graph into multiple subgraphs and fine-tunes the backbone operators from the subgraph within a hardware-aligned search space to find a collection of high-performance schedules. TSCompiler can propagate the explored backbone schedule to other fusion groups within the same subgraph to generate a set of parameterized tensor programs for fused cases based on dependence analysis. At runtime, TSCompiler utilizes an occupancy-targeted cost model to select from pre-compiled tensor programs for varied tensor shapes. Extensive evaluations show that TSCompiler can achieve state-of-the-art speedups for dynamic shape models. For example, we can improve kernel efficiency by up to 3.97× on NVIDIA RTX3090, and 10.30× on NVIDIA A100 and achieve up to five orders of magnitude speedups on end-to-end latency.

关键词： machine learning tensor compilers dynamic shape operator fusion code generation auto-tuning

来源：评论

学校读者我要写书评

暂无评论

Multi-user reinforcement learning based task migration in mobile edge computing

引用

Frontiers of Computer science 2024年第4期18卷 161-173页

作者： Yuya CUI Degan ZHANG Jie ZHANG Ting ZHANG Lixiang CAO Lu CHEN Tianjin Key Lab of Intelligent Computing and Novel Software Technology Tianjin University of TechnologyTianjin 300384China School of Internet of Things Engineering Jiangsu Vocational College of Information TechnologyWuxi 214153China School of Electronic and Information Engineering Beijing Jiaotong UniversityBeijing 100044China School of Sports Economics and Management Tianjin University of SportTianjin 301617China

Mobile Edge Computing(MEC)is a promising *** service migration is a key technology in *** order to maintain the continuity of services in a dynamic environment,mobile users need to migrate tasks between multiple servers in real *** to the uncertainty of movement,frequent migration will increase delays and costs and non-migration will lead to service ***,it is very challenging to design an optimal migration *** this paper,we investigate the multi-user task migration problem in a dynamic environment and minimizes the average service delay while meeting the migration *** order to optimize the service delay and migration cost,we propose an adaptive weight deep deterministic policy gradient(AWDDPG)*** distributed execution and centralized training are adopted to solve the high-dimensional *** show that the proposed algorithm can greatly reduce the migration cost and service delay compared with the other related algorithms.

关键词： mobile edge computing mobility service migration deep reinforcement learning deep deterministic policy gradient

来源：评论

学校读者我要写书评

暂无评论

A Novel Containment Control Design Scheme for Second-Order Multi-agent Systems with Adjustable Reference Signals

引用

IAENG International Journal of Applied Mathematics 2024年第6期54卷 1048-1052页

作者： Jiang, Mengyi Gao, Chuang Yang, Yonghui Pogodaev, Anatolii K. School of Electronic and Information Engineering University of Science and Technology Liaoning Liaoning Anshan114051 China School of Electronic and Information Engineering University of Science and Technology Liaoning Anshan114051 China Department of Applied Mathematics Lipetsk State Technical University Lipetsk398055 Russia

Due to the flexibility issue in existing containment control schemes for second-order multi-agent systems, we design an innovative control scheme. The proposed scheme involves the generation of a set of adjustable reference signals, and arbitrary adjustments of the reference signals are allowed. The innovative scheme not only enhances the flexibility of multi-agent systems, but also significantly decreases the likelihood of collision among multiple agents during their movements. Furthermore, the effectiveness of the proposed scheme is confirmed through simulation results. The proposed scheme addresses a critical issue in existing containment control schemes and presents a promising solution for improving the overall performance and safety of multi-agent systems. © (2024), (International Association of Engineers). All rights reserved.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Resource allocation in vehicular network based on sparrow search algorithm and hyper-graph in the presence of multiple cellular users

引用

International Journal of Intelligent Computing and Cybernetics 2024年第2期17卷 415-435页

作者： Lin Kang Jie Wang Junjie Chen Di Yang School of Electronic and Information Engineering Taiyuan University of Science and TechnologyTaiyuanChina China United Network Communication Co. Ltd.Software Research InstituteBeijingChina

Purpose-Since the performance of vehicular users and cellular users(CUE)in Vehicular networks is highly affected by the allocated resources to *** purpose of this paper is to investigate the resource allocation for vehicular communications when multiple V2V links and a V2I link share spectrum with CUE in uplink communication under different Quality of Service(QoS).Design/methodology/approach-An optimization model to maximize the V2I capacity is established based on slowly varying large-scale fading channel *** V2V links are clustered based on sparrow search algorithm(SSA)to reduce ***,a weighted tripartite graph is constructed by jointly optimizing the power of CUE,V2I and V2V ***,spectrum resources are allocated based on a weighted 3D matching ***-The performance of the proposed algorithm is *** results show that the proposed algorithm can maximize the channel capacity of V2I while ensuring the reliability of V2V and the quality of service of ***/value-There is a lack of research on resource allocation algorithms of CUE,V2I and multiple V2V in different *** solve the problem,one new resource allocation algorithm is proposed in this ***,multiple V2V links are clustered using SSA to reduce ***,the power allocation of CUE,V2I and V2V is jointly ***,the weighted 3D matching algorithm is used to allocate spectrum resources.

关键词： V2V V2I CUE Resource allocation Sparrow search algorithm 3D matching

来源：评论

学校读者我要写书评

暂无评论

A Fixed-Point Iterative Method for Discrete Tomography Reconstruction Based on Intelligent Optimization

引用

Computer Modeling in engineering & sciences 2023年第1期134卷 731-745页

作者： Luyao Yang Hao Chen Haocheng Yu Jin Qiu Shuxian Zhu School of Electronic and Information Engineering Suzhou University of Science and TechnologySuzhou215009China College of Mechanical Engineering Suzhou University of Science and TechnologySuzhou215009China

Discrete Tomography(DT)is a technology that uses image projection to reconstruct *** reconstruction problem,especially the binary image(0–1matrix)has attracted strong *** this study,a fixed point iterative method of integer programming based on intelligent optimization is proposed to optimize the *** solution process can be divided into two ***,the DT problem is reformulated into a polyhedron judgment problembased on lattice basis ***,the fixed-point iterativemethod of Dang and Ye is used to judge whether an integer point exists in the polyhedron of the previous *** the programs involved in this study are written in *** final experimental data show that this method is obviously better than the branch and bound method in terms of computational efficiency,especially in the case of high *** branch and bound method requires more branch operations and takes a long *** also needs to store a large number of leaf node boundaries and the corresponding consumptionmatrix,which occupies a largememory space.

关键词： Discrete tomography integer programming fixed-point iterative algorithm intelligent optimization lattice basis reduction

来源：评论

学校读者我要写书评

暂无评论

Multi-IRS-Aided Secure Communication in UAV-MEC Networks

引用

IEEE Transactions on Vehicular technology 2025年第5期74卷 7327-7338页

作者： Gao, Yuan Wang, Zhenyu Zhang, Yu Lu, Weidang Tang, Jie Zhao, Nan Gao, Feifei Academy of Military Science of the PLA Beijing100084 China Zhejiang University of Technology College of Information Engineering Hangzhou310023 China South China University of Technology School of Electronic and Information Engineering Guangzhou510641 China Dalian University of Technology School of Information and Communication Engineering Dalian116024 China Tsinghua National Laboratory for Information Science and Technology Beijing100084 China

With the merits of high mobility and easy deployment, mounting mobile edge computing (MEC) servers on unmanned aerial vehicles (UAVs) can efficiently fulfill the task offloading of ground users (GUs) over a large area. Nevertheless, data security is a challenging issue for the computation offloading in UAV-MEC networks, especially when there exist flying eavesdroppers. An intelligent reflecting surface (IRS) assisted secure communication scheme for a UAV-MEC network is proposed in this paper, wherein multiple IRSs are utilized to help the secure computation offloading from GUs against a UAV eavesdropper. Our aim is to maximize the secure computation capacity through the joint optimization of the IRS phase-shift, allocation of communication and computing resources and trajectory of UAV. We firstly solve the problem under a fixed UAV trajectory by alternating optimization to obtain the resource allocation and IRS phase-shift, wherein Dinkebach and Taylor expansion methods are used to transform the subproblems into tractable forms. Then, by adopting the proximal policy optimization, a joint optimization approach which further incorporates the UAV trajectory optimization is proposed. Numerical results verify that compared with benchmarks, the proposed scheme efficiently improves the system secure computation capacity. © 1967-2012 IEEE.

关键词： Computation offloading

来源：评论

学校读者我要写书评

暂无评论

Secure Consumer-Centric Demand Response Management in Resilient Smart Grid as Industry 5.0 Application with Blockchain-Based Authentication

引用

IEEE Transactions on Consumer electronics 2024年第1期70卷 1370-1379页

作者： Ayub, Muhammad Faizan Li, Xiong Mahmood, Khalid Shamshad, Salman Saleem, Muhammad Asad Omar, Marwan University of Electronic Science and Technology of China School of Computer Science and Engineering Sichuan Chengdu12599 China National Yunlin University of Science and Technology Graduate School of Intelligent Data Science Douliu64002 Taiwan The University of Lahore Department of Software Engineering Lahore54590 Pakistan Illinois Institute of Technology Information Technology and Management ChicagoIL60616 United States

The development of the industrial Internet of Things and smart grid networks has emphasized the importance of secure smart grid communication for the future of electric power transmission. However, the current deployment of smart meters and wireless communication methods presents several security concerns that must be addressed to ensure sustainable and resilient smart grid networks for Industry 5.0, with a focus on consumer-centric technologies. In this context, we propose a privacy-focused authentication solution for secure consumer-centric demand response management in smart grid networks, incorporating consumer electronics. Our proposed protocol utilizes blockchain-based authentication to enhance resistance against potential attacks and ensure the integrity of demand response data. Additionally, we have incorporated a PUF to prevent physical attacks. We have conducted informal and formal security analyses to verify the effectiveness of our proposed protocol against various threats and to confirm the session key security. Our comparison study has demonstrated that our protocol provides superior security and added functionalities, with lower computation and communication costs compared to similar protocols. Furthermore, we have measured the computational time for implementing the blockchain component of our protocol while considering the impact of varying numbers of block additions and transactions per block. © 1975-2011 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Review on bio-inspired polarized skylight navigation

引用

Chinese Journal of Aeronautics 2023年第9期36卷 14-37页

作者： Fang KONG Yingjing GUO Jianhua ZHANG Xiaojing FAN Xiaohan GUO School of Electrical and Automation Engineering Shandong University of Science and TechnologyQingdao 266590China School of Electronic and Information Engineering Shandong University of Science and TechnologyQingdao 266590China Qingdao Intelligence Ocean Technology Co. Ltd.Qingdao 266590China School of Information Science and Engineering Qingdao School of Shandong UniversityQingdao 266237China

In this review, the research progress of bio-inspired polarized skylight navigation is evaluated from the perspectives of theoretical basis, information detection, sensor design, and navigation realization. First, the theory for characterizing the polarization mode of the skylight was introduced. Second, using sunlight, moonlight, and ocean as backgrounds, the measurement results of skylight polarization distribution under different weather conditions are described to compare the variation patterns. Third, the development history and research outcomes of bionic polarization navigation sensor for polarized skylight detection and navigation information calculation are categorized into two types, namely non-imaging and imaging types. In precision measurement, the non-imaging type is higher than the imaging type, and the accuracy that it can reach is ± 0.1° of navigation accuracy without drift error. Fourth, two polarized skylight orientation algorithms,E-vector-based method and Solar Meridian-Anti Solar Meridian(SM-ASM)-based method are summarized. Fifth, this review details the combined application of polarized skylight navigation sensors and Inertial Navigation System(INS), Global Navigation Satellite System(GNSS), Vision,Simultaneous Localization and Mapping(SLAM), and other navigation systems. The yaw and trajectory accuracy can be increased by about 40% compared to classical navigation system in complex outdoor environments. Finally, the future development trends of polarization navigation are presented.

关键词： Navigation Polarization Polarized skylight navigation sensors Polarized skylight navigation system Skylight polarization pattern

来源：评论

学校读者我要写书评

暂无评论

Design of Dual-Function Radar Communication System Based on Delayed Jump Mapping LFM 8

Design of Dual-Function Radar Communication System Based on ...

引用

8th International Conference on Signal and Image Processing, ICSIP 2023

作者： Xu, Rui Wen, Ruiming Huang, Zihan Li, Gang Wen, Guangjun University of Electronic Science and Technology of China School of Information and Communication Engineering China University of Electronic Science and Technology of China School of Infomation and Software Engineering China

ISBN: (纸本)9798350397932

The deterioration of dual-function performance and increased complexity of communication receivers challenge the efficiency of dual-functional radar-communication (DFRC) system based on linear frequency modulation (LFM). This paper designs a delayed jump mapping LFM (DJM-LFM) waveform-based DFRC system. The frequency delay jumps are generated at the specific points in the LFM cycle to modulate data. After carrier mixing and undersampling, the communication receiver realizes dechirp in the digital domain, to reduce the performance requirements of the coherent signal generation and sampling. In the radar processing link, we propose the breakpoint area deletion and concatenation (BADC) scheme, making the radar performance of DFRC consistent with that of unmodulated frequency modulated continuous wave radar (FMCW). The simulation results show that, compared with the scheme without compensation, the BADC scheme reduces the sidelobe amplitude of the range domain profile by about 38 dB. DJM-LFM reduces the symbol error rate of 2 dB compared with existing DFRC schemes based on the LFM waveform. © 2023 IEEE.

关键词： Deterioration

来源：评论

学校读者我要写书评

暂无评论

Impulsive Stabilization of Unconstrained Multilayer Recurrent Neural Networks with Node-Based Time-varying Delays 8

Impulsive Stabilization of Unconstrained Multilayer Recurren...

引用

8th IEEE International Conference for Convergence in technology, I2CT 2023

作者： Wang, Xiangxiang Yu, Yongbin Feng, Xiao Han, Xinyi Wang, Jingya Cai, Jingye University of Electronic Science and Technology of China School of Information and Software Engineering Chengdu China

ISBN: (纸本)9798350334012

This article discusses the exponential stabilization of node-dependent delayed multilayer neural networks (NDDMNNs) under impulsive control. To address different modeling requirements in complicated applications, node-based interlayer and intralayer parameters are presented to design the neural network model, indicating that The nodes constituting the network can have different structures. Meanwhile, the novel model considers the node-dependent time-varying delays, and this article develops the sparse matrix approach to translate the node-dependent delayed NDDMNNs model into an multiple delayed model, ensuring that the vector form of NDDMNNs can be constructed and studied by using existing technical approaches. Then, an analytical framework with super-Laplacian matrix and time-dependent Lyapunov function methods is proposed to derive exponential stabilization results. Finally, a numerical simulation example is given to verify the obtained results. © 2023 IEEE.

关键词： Stabilization

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：