检索结果-内蒙古大学图书馆

Ivannikov Ispras open conference (ISPRAS)

作者： Tchernykh, Andrei Facio-Medina, Adrian Pulido-Gaytan, Bernardo Rivera-Rodriguez, Raul Cortes-Mendoza, Jorge M. Radchenko, Gleb Babenko, Mikhail Chernykh, Igor Kulikov, Igor Nesmachnow, Sergio Ivannikov Inst Syst Programming Moscow Russia CICESE Res Ctr Ensenada Baja California Mexico South Ural State Univ Chelyabinsk Russia North Caucasus Fed Univ Stavropol Russia ICMMG SB RAS Novosibirsk Russia Univ Republica Montevideo Uruguay

ISBN: (纸本)9781665412919

A Digital Twin (DT) is a set of computational models representing real-time physical objects and processes in a digital world. The increasing adoption of this paradigm by the major industrial equipment vendors to simulate real-time working conditions and perform smart decision-making, established the Smart Factory Digital Twins architectures, where a set of DTs published as microservices interact with each other exchanging information by streaming technology. In this sense, a fundamental problem consists of selecting adequate computational resources to simulate the physical objects. In an Infrastructure as a Service (IaaS) cloud for DTs, the allocation focuses on distributing the jobs of the set into the virtual machine instances in a way that computational resources demand is satisfied and the cost is minimized In this paper, we propose a set of algorithms based on heuristics, metaheuristics, and Mixed Integer programming to find low-cost solutions. The performance of algorithms is evaluated using Amazon EC2 instances and DT jobs with randomly generated bandwidth, memory, and processor requirements. The experimental results show that the proposed approaches based on bin packing, genetic algorithms, partition, filtering, set coverage, and branch and bound strategies present a competitive performance in the workload allocation of the computational set of jobs of a DT into an IaaS cloud environment. Our allocation heuristic-based techniques allow considerable cost savings in medium and large periods concerning standard approaches such as local search.

关键词： Instance Provisioning Digital Twin Smart Factory EC2 Mixed Integer programming Evolutionary Algorithms Metaheuristics

来源：评论

学校读者我要写书评

暂无评论

A Distributed Mobile Fog Computing Scheme for Mobile Delay-Sensitive Applications in SDN-Enabled Vehicular networks

引用

ieee TRANSACTIONS ON VEHICULAR TECHNOLOGY 2020年第5期69卷 5481-5493页

作者： Lin, Chuan Han, Guangjie Qi, Xingyue Guizani, Mohsen Shu, Lei Dalian Univ Technol Key Lab Ubiquitous Network & Serv Software Liaoni Dalian 116024 Peoples R China Nanjing Agr Univ Coll Engn Nanjing 210095 Peoples R China Dalian Univ Technol Sch Software Dalian 116024 Peoples R China Qatar Univ Dept Comp Sci & Engn Coll Engn Doha 2713 Qatar Univ Lincoln Sch Engn Lincoln England

With the rapid development of intelligent transportation systems, enormous amounts of delay-sensitive vehicular services have been emerging and challenge both the architectures and protocols of vehicular networks. However, existing cloud computing-embedded vehicular networks cannot guarantee timely data processing or service access, due to long propagation delay and traffic congestion at the cloud center. Meanwhile, the current distributed network architecture does not support scalable network management, leading the intelligent data computing policies to be undeployable. With this motivation, we propose to introduce fog computing into vehicular networks and define the Multiple Time-constrained Vehicular applications Scheduling (MTVS) issue. First, to improve the network flexibility and controllability, we introduce a Fog-based Base Station (FBS) and propose a Software-Defined networking (SDN)-enabled architecture dividing the networks into network, fog, and control layers. To address MTVS issue, instead of normal centralized computing-based approaches, we propose to distribute mobile delay-sensitive task in data-level over multiple FBSs. In particular, we regard the fog layer of SDN-enabled network as an FBS-based network and propose to distribute the computing task based on the FBSs along multiple paths in the fog layer. By Linear programming, we optimize the optimal data distribution/transmission model by formulating the delay computation model. Then, we propose a hybrid scheduling algorithm including both local scheduling and fog scheduling, which can be deployed on the proposed SDN-enabled vehicular networks. Simulation results demonstrate that our approach performs better than some recent research outcomes, especially in the success rate for addressing MTVS issue.

关键词： Vehicular networks delay-sensitive fog computing fog-based base station software-defined networking hybrid scheduling

来源：评论

学校读者我要写书评

暂无评论

Cost Efficient Service Mesh Controller Placement for Edge Native Computing

Cost Efficient Service Mesh Controller Placement for Edge Na...

引用

GLOBECOM 2022 - 2022 ieee Global Communications conference

作者： Yuepeng Li Deze Zeng Lvhao Chen Lin Gu Weiyin Ma Feng Gao School of Computer Science China University of Geosciences Wuhan China School of Computer Science and Technology Huazhong University of Science and Technology China School of Biomedical Engineering and Informatics Nanjing Medical University Nanjing China Research Center for Cyber-Physical-Social System Zhejiang Lab Hangzhou China

ISBN: (纸本)9781665435413

Cloud native computing featured by microservice has been regarded as a compelling trend in cloud application development. Edge computing, as an alternative or complemen-tary to cloud computing, is potential to expand the microservice to edge computing, simplifying the development and deployment of edge applications. Despite that, there is still a challenge on how to manage the microservices efficiently in the open and heterogeneous distributed environment. To this end, service mesh provides a potential solution in efficient microservices management. However, as a traditional cloud-oriented architecture, it can not be applied into edge computing directly since the centralized controller policy. To address this problem, in this paper, we propose an edge service mesh architecture with distributively deployed controllers for edge native computing. We further inves-tigate the problem on how to deploy these distributive controllers in a cost efficient manner with the consideration of control cost and the synchronization cost. The problem is formulated into a non-linear optimization form and then linearized into an integer linear programming (ILP) problem. To tackle the computation complexity, we then come up with a customized k-means based algorithm (i.e., ck-means) in polynomial computation complexity. The experimental results verify the efficiency of our ck-means algorithm in comparison with the traditional k-means algorithm.

关键词： Cloud computing Costs Heuristic algorithms Microservice architectures Computer architecture Synchronization Computational complexity

来源：评论

学校读者我要写书评

暂无评论

Array-Level programming of 3-Bit per Cell Resistive Memory and Its Application for Deep Neural network Inference

引用

ieee TRANSACTIONS ON ELECTRON DEVICES 2020年第11期67卷 4621-4625页

作者： Luo, Yandong Han, Xu Ye, Zhilu Barnaby, Hugh Seo, Jae-sun Yu, Shimeng Georgia Inst Technol Sch Elect & Comp Engn Atlanta GA 30332 USA Arizona State Univ Sch Elect Comp & Energy Engn Tempe AZ 85287 USA

The requirement of multilevel cell (MLC) resistive random accessmemory (RRAM) for computing is different than that for MLC storage. It generally requires a linearly spaced conductance median and an ultratight conductance distribution, as the column current are summed up for analog computation. In this article, 3-bit per cell RRAM that is suitable for accurate inference of a deep neural network (DNN) is demonstrated, with ultratight conductance distribution (<1.5% sigma). First, a two-loop write-verify protocol is proposed. Then, statistical experiments are conducted on RRAM array fabricated in Winbond's 90-nm process. By incorporating the measured conductance distribution into DNN simulation considering the real weight mapping, inference accuracy with only 0.5% degradation over software baseline is achieved for CIFAR-10 data set even when 128 rows are read-out in parallel. By enabling parallel read-out, the system-level energy efficiency and throughput could be improvedby 5.3x and 4.4x, respectively, compared to the 3-bit per cell RRAM used as MLC storage.

关键词： Compute-in-memory (CIM) deep neural network (DNN) multilevel cell (MLC) resistive random access memory (RRAM)

来源：评论

学校读者我要写书评

暂无评论

Cephalopode: A custom processor aimed at functional language execution for IoT devices 18

Cephalopode: A custom processor aimed at functional language...

引用

18th ACM-ieee International conference on Formal Methods and Models for System Design (MEMOCODE)

作者： Pope, Jeremy Saget, Jules Seger, Carl-Johan H. Chalmers Univ Technol Dept CSE Gothenburg Sweden Ecole Normale Super Dept Informat Paris France

ISBN: (纸本)9781728191485

The Internet of Things (IoT) conceives a future where "things" are interconnected by means of suitable information and communication technologies. Unfortunately, recent events have demonstrated the high vulnerability of IoT. One of the main reasons for this is the use of low-level programming languages. The Octopi project is developing technologies to easily and securely program IoT devices by the use of functional high-level languages. Unfortunately, a traditional implementation of a modern functional language that runs on traditional hardware is very resource demanding. So resource demanding that few, if any, IoT devices can run them. In the Cephalopode project (which is a subproject of Octopi) we are exploring the implementation of a very low power hardware device directly aimed at running a high-level functional language. By integrating many resource-heavy tasks into dedicated hardware, we aim at creating an execution engine for IoT devices that will allow secure programming.

关键词： Internet of Things IoT Functional Languages Custom hardware architectures

来源：评论

学校读者我要写书评

暂无评论

An error-propagation spiking neural network compatible with neuromorphic processors

An error-propagation spiking neural network compatible with ...

引用

2nd ieee International conference on Artificial Intelligence Circuits and Systems (AICAS)

作者： Cartiglia, Matteo Haessig, Germain Indiveri, Giacomo Univ Zurich Inst Neuroinformat Zurich Switzerland Swiss Fed Inst Technol Zurich Switzerland

ISBN: (纸本)9781728149226

Spiking neural networks have shown great promise for the design of low-power sensory-processing and edge-computing hardware platforms. However, implementing onchip learning algorithms on such architectures is still an open challenge, especially for multi-layer networks that rely on the back-propagation algorithm. In this paper, we present a spike-based learning method that approximates back-propagation using local weight update mechanisms and which is compatible with mixed-signal analog/digital neuromorphic circuits. We introduce a network architecture that enables synaptic weight update mechanisms to back-propagate error signals across layers and present a network that can be trained to distinguish between two spike-based patterns that have identical mean firing rates, but different spike-timings. This work represents a first step towards the design of ultra-low power mixed-signal neuromorphic processing systems with on-chip learning circuits that can be trained to recognize different spatio-temporal patterns of spiking activity (e.g. produced by event-based vision or auditory sensors).

关键词： network layers

来源：评论

学校读者我要写书评

暂无评论

On the Security and Privacy of Hyperledger Fabric: Challenges and open Issues

On the Security and Privacy of Hyperledger Fabric: Challenge...

引用

4th ieee International conference on Edge Computing (ieee EDGE) / ieee World Congress on Services (SERVICES)

作者： Brotsis, Sotirios Kolokotronis, Nicholas Limniotis, Konstantinos Bendiab, Gueltoum Shiaeles, Stavros Univ Peloponnese Tripolis 22131 Greece Univ Portsmouth Portsmouth PO1 2UP Hants England

ISBN: (纸本)9781728182032

In the last few years, a countless number of permissioned blockchain solutions have been proposed, with each one to claim that it revolutionizes the way of the transaction processing along with the security and privacy preserving mechanisms that it provides. Hyperledger Fabric is one of the most popular permissioned blockchain architectures that has made a significant impact on the market. However, there are only few papers of finding architectural risks regarding the security and the privacy preserving mechanisms of Hyperledger Fabric. This paper separates the attack surface of the blockchain platform into four components, namely, consensus, chaincode, network and privacy preserving mechanisms, in all of which an attacker (from inside or outside the network) can exploit the platform's design and gain access to or misuse the network. In addition, we highlight the appropriate counter-measures that can be taken in each component to address the corresponding risks and provide a significantly secure and enhanced privacy preserving Fabric network. We hope that by bringing this paper into light, we can aid developers to avoid security flaws and implementations that can be exploited by attackers but also to motivate further research to harden the platform's security and the client's privacy.

关键词： Hyperledger Fabric cyber-security consensus protocols chaincode risks network threats privacy

来源：评论

学校读者我要写书评

暂无评论

RTC: Route to Controller Algorithm Providing SDN Capabilities in MANETs

RTC: Route to Controller Algorithm Providing SDN Capabilitie...

引用

MILCOM, Military Communications conference

作者： Klement Hagenhoff Maximilian Tränkler Corinna Schmitt Gabri Dreo Rodosek Research Institute CODE Universität der Bundeswehr München Ludwig - Maximilians- Universität München

Decentralized network architectures like MANETs make it difficult to leverage SDN capabilities like centralized path construction since routing is managed by participants' local topology knowledge. Such a distributed routing behavior characterizes MANETs as robust as a certain number of node failures can be covered by participants. However, distributed routing based on inconsistent and incomplete topology knowledge of participants leads to inefficient path constructions. This decreases the residual transmission capacity of the MANETs which could be improved with complete and up-to-date topology knowledge. Previous research proposed RFTKR, an algorithm providing up-to-date topology knowledge stored on a controller in the MANET. Thus, routing can leverage SDN capabilities, where path construction is outsourced to the controller. Participants forward flows based on these paths. However, an open question is still how to maintain a route to this controller for each participant to request new routes. This requirement challenges even more since nodes are moving continuously. Also, control and routing messages must be kept minimal since transmission capacities in MANETs are restricted. This research tackles this challenge and presents RTC, an algorithm that rearranges participants of the MANET to a tree. Participants of this tree, maintain their route to their controller while keeping the message overhead as minimal as possible. Results prove the correct functionality of RTC. In addition, further simulations verify that tree rearrangements minimize the message overhead at runtime.

关键词： Military communication Knowledge engineering Runtime network architecture Routing Ad hoc networks Topology

来源：评论

学校读者我要写书评

暂无评论

Model-Driven-Design of NREn Bridging Application: Case Study AfgREN 44

Model-Driven-Design of NREn Bridging Application: Case Study...

引用

44th Annual ieee-Computer-Society International conference on Computers, Software, and Applications (COMPSAC)

作者： Saay, Salim Margaria, Tiziana Univ Limerick Lero SFI Software Res Ctr Limerick Ireland CSIS Limerick Ireland

ISBN: (纸本)9781728173030

National Research and Education networks (NRENs) are dedicated networks that provide a backbone for the collaboration and data exchange between academic organizations. However, the lack of a domain-specific bridging application, lack of interoperability and data integration are serious challenges in educational technologies, hampering collaboration and resource sharing even within existing agreements. NRENs are cost-effective backbones of large scale networks aimed to deliver convergence and promote educational opportunities beyond individual institutions. In this paper we prototype an inter-organization bridging application based on an abstract NREN architecture based on a broker pattern. The ability to communicate is also an essential precondition for the easy adoption of open Education Resources. The motivating case study is the Afghanistan Research and Educational network (AfgREN). To enhance ease of adoption, adaptation, and evolution, the prototype is designed following an eXtreme Model-Driven Development (XMDD) paradigm, using a low-code development environment for modelling data, processes, user interfaces in an agile rapid prototyping fashion. We generalize the results to the (federated) collaboration of regional and global NRENs, to enable the delivery of easy collaboration, data integration, high accessibility, and resource sharing across educational organizations on a national and cross-national level.

关键词： OER Collaboration scalable open architectures for eLearning AfgREN Moodle eLearning XMDD DIME low-code application development

来源：评论

学校读者我要写书评

暂无评论

Cost-based Optimal Allocation of Shunt Capacitors in Radial Distribution networks considering Load Types

Cost-based Optimal Allocation of Shunt Capacitors in Radial ...

引用

International conference on Engineering and Emerging Technologies (ICEET)

作者： Sunday Adeleke Salimon Ismail Adeyemi Adeyemo Gafari Abiola Adepoju Abiodun Aderemi Baruwa Isaiah Gbadegesin Adebayo Ayooluwa Peter Adeagbo Electronic and Electrical Engineering Department Ladoke Akintola University of Technology Ogbomoso Nigeria Electrical and Electronic Engineering Department Osun State College of Technology Esa-Oke Nigeria Electrical and Electronic Engineering Department Adeleke University Ede Nigeria

ISBN: (纸本)9781665491075

Optimal allocation of shunt capacitors in radial distribution networks (RDNs) have been obtained using several techniques taking the average of the network as constant power load. However, there are different load types on the distribution network that can significantly determine the size and location of shunt capacitors. In this study, the black widow optimizer technique is utilized for optimal allocation of shunt capacitors considering the constant impedance, constant current, constant power and combination of loads scenarios in the radial distribution network. The objective of the study is minimization of the total annual operating cost composed of cost due to power loss, shunt capacitor’s investment, installation and operation cost. The proposed method is implemented on the ieee 33-bus and 69-bus radial distribution networks. The simulation results establish the effectiveness of the proposed technique for the four considered load models. The combination load model yielded the highest percentage savings of 34.79% and 29.62 % of the total annual operating cost for the ieee 33-bus and 69-bus RDN, respectively. The effectiveness and efficiency of the proposed BWO were confirmed by a comparison of the results of the constant power model with well-established optimization techniques found in open works of literature.

关键词： Costs Simulation Capacitors Distribution networks Voltage Linear programming Resource management

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：