检索结果-内蒙古大学图书馆

Distributed computation offloading in Mobile Fog Computing: A Deep Neural Network Approach

IEEE COMMUNICATIONS LETTERS 2022年第3期26卷 696-700页

作者： Yang, Zhongjun Bai, Wenle North China Univ Technol Sch Informat Sci & Technol Beijing 100043 Peoples R China

In this letter, the performance of offloading is studied, which aims at minimizing the energy consumption in offloading with constraints on the delay. To solve binary computational offloading decision problem, a learning offloading algorithm based on distributed DNN is proposed, which uses multiple parallel DNNs to generate offloading decisions. The DNN are further improved by using the back-propagation method with cross-entropy as the loss function and using the newly generated decisions as a public training set. Besides, an innovative hierarchical offloading model is presented, based on which derives closed-form expressions for delay and energy in offloading. Then, the Delay-Energy Weighted Sum (DEWS) metric is defined and introduced as system utility to construct a gradient optimization problem to study. Extensive simulation indicate that the algorithm modified with the DEWS metric is able to achieve significant reduction on energy consumption with comparably less the total delay and maintain a high offloading accuracy.

关键词： Task analysis Delays Servers Cloud computing Wireless communication Measurement Energy consumption Mobile fog computing DEWS metric joint optimization offloading computation distributed DNN

来源：评论

学校读者我要写书评

暂无评论

Efficient GPU Cloud architectures for outsourcing high-performance processing to the Cloud

引用

INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY 2024年第1-2期133卷 949-958页

作者： Sanchez-Ribes, Victor Macia-Lillo, Antonio Mora, Higinio Jimeno-Morenilla, Antonio Univ Alicante Dept Comp Sci Technol & Computat Alicante Spain

The world is becoming increasingly dependant in computing intensive applications. The appearance of new paradigms, such as Internet of Things (IoT), and advances in technologies such as Computer Vision (CV) and Artificial Intelligence (AI) are creating a demand for high-performance applications. In this regard, Graphics Processing Units (GPUs) have the ability to provide better performance by allowing a high degree of data parallelism. These devices are also beneficial in specialized fields of manufacturing industry such as CAD/CAM. For all these applications, there is a recent tendency to offload these computations to the Cloud, using a computing offloading Cloud architecture. However, the use of GPUs in the Cloud presents some inefficiencies, where GPU virtualization is still not fully resolved, as our research on what main Cloud providers currently offer in terms of GPU Cloud instances shows. To address these problems, this paper first makes a review of current GPU technologies and programming techniques that increase concurrency, to then propose a Cloud computing outsourcing architecture to make more efficient use of these devices in the Cloud.

关键词： GPU Cloud computing High-performance processing offloading computation

来源：评论

学校读者我要写书评

暂无评论

offloading strategy with PSO for mobile edge computing based on cache mechanism

引用

CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS 2022年第4期25卷 2389-2401页

作者： Zhou, Wenqi Chen, Lunyuan Tang, Shunpu Lai, Lijia Xia, Junjuan Zhou, Fasheng Fan, Liseng Guangzhou Univ Sch Comp Sci Guangzhou Peoples R China Guangzhou Univ Sch Elect & Commun Engn Guangzhou Peoples R China

With the development of Internet of Things (IoT) devices and the growth of users' demand for computation and real-time services, artificial intelligence has been applied to reduce the system cost for future network systems. To meet the demand of network services, the paradigm of edge networks is increasingly shifting towards the joint design of computation, communication and caching services. This paper investigates a multi-user cache-enabled mobile edge computing (MEC) network and proposes an intelligent particle swarm optimization (PSO) based offloading strategy with cache mechanism. In each time slot, the server selects one file among multiple ones to pre-store, according to the proposed cache replacement strategy. In the next time slot, the requested files by the users needn't to be computed and offloaded, if these files have been cached in the server. For the files that have not been cached in the server, PSO algorithm is adopted to find an appropriate offloading ratio to implement the partial offloading. Simulation results are finally presented to validate the proposed studies. In particular, we can find that incorporating the proposed cache replacement strategy into the computation offloading can effectively reduce the system latency and energy consumption for the future networks.

关键词： Edge computing offloading computation Cache-enabled Cache replacement

来源：评论

学校读者我要写书评

暂无评论

offloading strategies for Stencil kernels on the KNC Xeon Phi architecture: Accuracy versus performance

引用

INTERNATIONAL JOURNAL OF HIGH PERFORMANCE COMPUTING APPLICATIONS 2020年第2期34卷 199-207页

作者： Hernandez, Mario Cebrian, Juan M. Cecilia, Jose M. Garcia, Jose M. Univ Autonoma Guerrero Fac Ingn Guerrero Mexico BSC Barcelona Spain Univ Catolica San Antonio Murcia Dept Ingn Informat Murcia Spain Univ Murcia Dept Ingn & Tecnol Comp Murcia Spain

The ever-increasing computational requirements of HPC and service provider applications are becoming a great challenge for hardware and software designers. These requirements are reaching levels where the isolated development on either computational field is not enough to deal with such challenge. A holistic view of the computational thinking is therefore the only way to success in real scenarios. However, this is not a trivial task as it requires, among others, of hardware-software codesign. In the hardware side, most high-throughput computers are designed aiming for heterogeneity, where accelerators (e.g. Graphics Processing Units (GPUs), Field-Programmable Gate Arrays (FPGAs), etc.) are connected through high-bandwidth bus, such as PCI-Express, to the host CPUs. Applications, either via programmers, compilers, or runtime, should orchestrate data movement, synchronization, and so on among devices with different compute and memory capabilities. This increases the programming complexity and it may reduce the overall application performance. This article evaluates different offloading strategies to leverage heterogeneous systems, based on several cards with the first-generation Xeon Phi coprocessors (Knights Corner). We use a 11-point 3-D Stencil kernel that models heat dissipation as a case study. Our results reveal substantial performance improvements when using several accelerator cards. Additionally, we show that computing of an approximate result by reducing the communication overhead can yield 23% performance gains for double-precision data sets.

关键词： offloading computation Stencil codes approximate computing heterogeneous computing

来源：评论

学校读者我要写书评

暂无评论

Toward Improved offloading Efficiency of Data Transmission in the IoT-Cloud by Leveraging Secure Truncating OFDM

引用

IEEE INTERNET OF THINGS JOURNAL 2019年第3期6卷 4252-4261页

作者： Jia, Min Yin, Zhisheng Li, Dongbo Guo, Qing Guo, Xuemai Harbin Inst Technol Commun Res Ctr Harbin 150080 Heilongjiang Peoples R China Harbin Inst Technol Dept Sch Elect & Informat Engn Harbin 150080 Heilongjiang Peoples R China

Cloud computing provides powerful computing ability of mobile devices in the Internet of Things (IoT) networks. However, the large amounts of data interaction with cloud suffers bandwidth limit and energy efficiency for data processing and transmission, and the energy consumption of data processing is far less than data transmission. In this paper, offloading is considered in transmission to improve the battery lifetime by employing a spectral-energy efficient transmission scheme with efficient computing in IoT-Cloud. The offloaded resource can be saved to serve more services if the physical air interface is designed efficiently. In addition, many personal things are unloaded to the IoT-Cloud which creates a risk of privacy and security. The improved offloading efficiency of data transmission scheme secure truncating orthogonal frequency division multiplexing (STOFDM) is generated by deliberately truncating the orthogonal frequency division multiplexing signal in time domain. Particularly, the truncations are selected by a dynamic random private matrix based on the proposed offloading power amplifier theorem. The corresponding legitimate receiver is designed with private mapping using the efficient fast Fourier transformation (FFT) for offloading computation. Moreover, the closed-form expression for the FFT-based STOFDM system is analyzed and be verified by simulation results. In light of the analysis, the STOFDM performs intercarrier interference as an orthogonal sequence is partially transmitted, which degrades the reliability of transmission link. Further, two enhanced detectors with low computing-complexity is also given to improve the performance of Bob while restrict eavesdropper's reception and further provides offloading computation.

关键词： Internet of Things (IoT) offloading computation offloading efficiency secure truncating secure truncating orthogonal frequency division multiplexing (STOFDM) spectral efficiency

来源：评论

学校读者我要写书评

暂无评论

Efficient Mobile computation using the Cloud 3

Efficient Mobile Computation using the Cloud

引用

3rd International Conference on Future Internet of Things and Cloud (FiCloud) / International Conference on Open and Big Data (OBD)

作者： Karim, S. M. Azharul Prevost, John J. Univ Texas San Antonio Dept Elect Engn San Antonio TX USA

ISBN: (纸本)9781467381031

Mobile devices have limited resources in terms of power and bandwidth. Cloud computing offers a way to reduce the power consumption of mobile devices by offloading computation to the cloud. However, offloading computation means an increase in communication energy consumption. The trade-off between energy and network characteristics (bandwidth/latency) in a mobile device is very important. Therefore computation offloading must be done strategically. The optimum utilization of the available mobile device resources needs to be assured. In this paper, we propose an intelligent and dynamic algorithm to offload computation to the cloud. We focus on offloading computation based upon the communication topology, device energy and user inputs. We analyze the cost of offloading computation for different user inputs. Based on the inputs, we decide whether to offload the application to the cloud or not. We have simulated our algorithm in MATLAB, and compared our result to previous approaches. We have found out that our algorithm saves more time, compared to a previous approach, and also reduces device energy usage by moving energy hungry processes to the cloud.

关键词： Cloud computing offloading computation network topology bandwidth latency MATLAB (R)

来源：评论

学校读者我要写书评

暂无评论

Offload Destination Selection to Enable Distributed computation on Battlefields 33

Offload Destination Selection to Enable Distributed Computat...

引用

33rd Annual IEEE Military Communications Conference on Affordable Mission Success - Meeting the Challenge (MILCOM)

作者： Sookoor, Tamim Doria, David Bruno, David Shires, Dale Swenson, Brian Pollock, Lori US Army Res Lab Div Comp Sci Aberdeen Proving Ground MD 21005 USA Georgia Inst Technol Sch Elect & Comp Engn Atlanta GA 30332 USA Univ Delaware Dept Comp & Informat Sci Newark DE 19716 USA

ISBN: (纸本)9781479967704

The tactical edge (battlefields, disaster relief operations, etc.)is an ideal domain for utilizing mobile devices for computation. However, these situations require jobs to complete in a timely manner. Efficiently offloading computation can ensure timely job completion, but access to cloud computing infrastructure is typically limited, unreliable, or unavailable. As an alternative, we propose using vehicle-mounted high performance computers, called Tactical EIPCs (T-HPCs), as offload targets. A common scenario includes multiple offload targets with different computation capabilities, multiple clients wanting to offload computations, and wireless ad-hoc connectivity. While offloading strategies exist, currently none address the requirements of task scheduling in this setting. This paper presents an algorithm for offloading tasks from multiple sources while taking into account the computation capabilities and current utilization of available offload targets. In addition, distributed scheduling avoids a single point of failure which could be disastrous on the tactical edge. We report the results of simulations showing that our method reduces job completion time compared to alternative offloading schemes.

关键词： cloud computing military computing mobile computing battlefield cloud computing infrastructure distributed computation job completion time mobile devices offload destination selection offloading computation tactical HPC vehicle-mounted high performance computers wireless ad-hoc connectivity Clouds Processor scheduling Resource management Schedules Servers Smart phones

来源：评论

学校读者我要写书评

暂无评论

Securely Outsourcing Exponentiations with Single Untrusted Program for Cloud Storage

Securely Outsourcing Exponentiations with Single Untrusted P...

引用

19th European Symposium on Research in Computer Security (ESORICS)

作者： Wang, Yujue Wu, Qianhong Wong, Duncan S. Qin, Bo Chow, Sherman S. M. Liu, Zhen Tan, Xiao Wuhan Univ Key Lab Aerosp Informat Secur & Trusted Comp Minist Educ Sch Comp Wuhan 430072 Peoples R China City Univ Hong Kong Dept Comp Sci Hong Hom Hong Kong Peoples R China Beihang Univ Sch Elect & Informat Engn Beijing Peoples R China Renmin Univ Sch Informat Beijing Peoples R China Chinese Univ Hong Kong Dept Informat Engn Hong Hom Hong Kong Peoples R China

ISBN: (纸本)9783319112039;9783319112022

Provable Data Possession (PDP) allows a file owner to outsource her files to a storage server such that a verifier can check the integrity of the outsourced file. Public verifiable PDP schemes allow any one other than the file owner to be a verifier. At the client side (file owner or verifier), a substantial number of modular exponentiations is often required. In this paper we make PDP more practical via proposing a protocol to securely outsource the (most generic) variable-exponent variable-base exponentiations in one untrusted program model. Our protocol demonstrates advantages in efficiency or privacy over existing protocols coping with only special cases in two or single untrusted program model. We then apply our generic protocol to Shacham-Waters PDP and a variant of Yuan-Yu PDP. The analyses show that our protocol makes PDP much more efficient at the client side.

关键词： offloading computation Verifiable computation Modular exponentiation Provable Data Possession Cloud storage

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：