Load-dependent energy saving in future home environments

Already hundreds of millions of PCs are found in homes, offering high computing capacity without being adequately utilized. This paper reveals the potential for energy saving in future home environments, which can be achieved by sharing resources, and concentrating 24/7 computation on a small number of PCs. We present three evaluation methods for assessing the expected performance. A?newly created prototype is able to interconnect an arbitrary number of homes by using the free P2P-library FreePastry. The prototype is able to carry out task virtualization by sending virtual machines (VMs) from one home to another, most VMs being of size around 4 MB. We present measurement results from the prototype. We then describe a general model for download sharing, and compare performance results from an analytical model to results obtained from a discrete event simulator. The simulation results demonstrate that it is possible to reach almost optimal energy efficiency for this scenario.     

信号级协同计算平台架构及应用思考

针对智能化作战对军事电子信息系统计算能力提升的迫切需求,结合云计算的资源虚拟化、大数据的分布式计算等技术,提出了基于嵌入式CPU+ALL（DSP、FPGA、PPC、GPU、AI处理器等）的异构处理的信号级协同计算平台架构,包括弹性、轻量级异构资源虚拟化模型、分布式实时计算框架和智能计算框架等,形成了一套架构统一、资源共用、使用简便的协同计算和智能计算环境。通过战术级无线电认知和智能信号与信息处理两个典型应用场景,探讨了该信号级协同计算平台可能带来的颠覆性效用。     

A Unified Framework of the Cloud Computing Service Model

After a comprehensive literature review and analysis, a unified cloud computing framework is proposed, which comprises MapReduce, a vertual machine, Hadoop distributed file system (HDFS), Hbase, Hadoop, and virtualization. This study also compares Microsoft, Trend Micro, and the proposed unified cloud computing architecture to show that the proposed unified framework of the cloud computing service model is comprehensive and appropriate for the current complexities of businesses. The findings of this study can contribute to the knowledge for academics and practitioners to understand, assess, and analyze a cloud computing service application.     

云计算技术及其应用

云计算主要基于资源虚拟和分布式并行架构两大核心技术。在虚拟化技术方面,文章探讨了物理资源的池化、资源池的管理与使用、集群的故障定位与维护、资源池的分组与异构等技术,以及异构的虚拟化云计算平台的建设和应用。在分布式技术方面,文章探讨了分布式文件系统和Key/Value存储引擎技术。对于分布式文件系统,提出主机＂瓶颈＂解决方案及存储接口标准化的想法;对于Key/Value存储引擎,提出目录化存储的解决方案。     

Cloud Computing Technology and Its Applications

Virtualization and distributed parallel architecture are typical cloud computing technologies. In the area of virtualization technology, this article discusses physical resource pooling, resource pool management and use. cluster fault location and maintenance, resource pool grouping, and construction and application of heterogeneous virtualization platforms. In the area of distributed technology, distributed file system and Key/Value storage engine are discussed. A solution is proposed for the host bottleneck problem, and a standard storage interface is proposed for the distributed file system. A directory-based storage scheme for Key/Value storage engine is also proposed.     

浦东新区社区云的设计与实现

云计算被认为是继个人计算机和互联网之后电子信息技术领域的下一次重大革命.本文基于云计算理论,整合分布计算、网格计算与虚拟化理论,从系统架构层介绍浦东新区社区卫生服务中心信息系统.浦东新区社区卫生服务中心信息系统是以浦东新区社区卫生服务中心信息状态为基础,依托社区卫生信息专网,整合社区资源.突破了原有架构模式,解决社区信息化的各种压力,包括:资源分配不均的压力,数据共享的压力,系统扩展性的压力,系统应对变化的压力,维护的压力等.改变以往以应用为核心的资源配置模式,转向以资源为核心的资源分配模式,保证业务对资源需求的完整性.结合当前的热点技术,突破传统模式,为社区卫生服务中心信息化改造提供新的思路.     

面向“双碳”战略的绿色通信与网络：挑战与对策

面向国家“碳达峰”与“碳中和”的“双碳”战略需求,移动通信与网络需要在满足不断增长的业务需求前提下大幅度降低全网能耗,因此需要研究使用更少的能量传递更多信息（SMILE, send more information bits with less energy）的理论与技术。为了应对该挑战,仅靠无线传输技术的改进和硬件实现水平的提高是远远不够的,需要从系统和网络的角度探索能量的高效利用机理与方法。从能量的“节流”和“开源”2个维度展开,并针对日益增长的计算能耗给出解决方案。具体地,通过引入超蜂窝网络架构实现网络的柔性覆盖与弹性接入,使业务基站和边缘服务器在业务量较低时可以进入休眠状态,减少能量的浪费（即“节流”）。同时,大量引入可再生绿色能源（即“开源”）,通过能量流与信息流的智能适配,大幅降低电网的能耗。进一步地,通过网络功能虚拟化、通信与计算资源的高能效协同,以及移动智能体的分布式计算与协同等手段,实现绿色计算与人工智能算法。     

The Design Trade-Offs of BitTorrent-Like File Sharing Protocols

The BitTorrent (BT) file sharing protocol is very popular due to its scalability property and the built-in incentive mechanism to reduce free-riding. However, in designing such P2P file sharing protocols, there is a fundamental trade-off between keeping fairness and providing good performance. In particular, the system can either keep peers (especially those resourceful ones) in the system for as long as possible so as to help the system to achieve better performance, or allow more resourceful peers to finish their download as quickly as possible so as to achieve fairness. The current BT protocol represents only one possible implementation in this whole design space. The objective of this paper is to characterize the design space of BT-like protocols. The rationale for considering fairness in the P2P file sharing context is to use it as a measure of willingness to provide service. We show that there is a wide range of design choices, ranging from optimizing the performance of file download time, to optimizing the overall fairness measure. More importantly, we show that there is a simple and easily implementable design knob so that the system can operate at a particular point in the design space. We also discuss different algorithms, ranging from centralized to distributed, in realizing the design knob. Performance evaluations are carried out, both via simulation and network measurement, to quantify the merits and properties of the BT-like file sharing protocols.     

云计算的虚拟化安全问题

随着云计算的发展,云计算的安全问题越来越受到关注。本文全面分析了云计算中与虚拟化安全有关的各类问题,阐述了虚拟化安全的研究现状并提出了未来发展方向。文中先介绍了虚拟化角度下的云计算架构,然后介绍了虚拟化技术,重点介绍了虚拟化安全问题和研究现状,接着以Xen平台为例,介绍了Xen的虚拟化安全问题,最后对未来的发展进行了展望。     

基于计算、存储、传送资源融合化的新型网络虚拟化架构

5G与边缘计算等应用场景的兴起,使得计算、存储等基础IT资源离散部署与多级部署成为一大发展趋势,如何结合网络基础设施为用户提供更为便捷的、定制化的专属服务,提高整体资源利用率,成为网络技术发展的新方向。重点分析了网络虚拟化的特征与发展、资源发展与融合趋势以及新兴业务对资源供给新需求等,提出了一种基于多维资源融合化的网络虚拟化架构,即通过在网络虚拟化架构中引入资源发现与资源交易过程,将多方、异构的资源有机整合成统一资源平面,在此基础上根据用户需求进行资源切割与虚拟化,以适应新兴业务对资源需求快速灵活的特点,并能够有效提高资源利用效率,降低运营成本。由于资源联合优化涉及多个领域的研究,网络虚拟化架构将随着业务需求与商业模式的发展而不断完善,以期为未来业务发挥重要作用。     

Power‐saving policies for annual energy cost savings in green computing

The concept of green computing is a step toward advanced information technology‐related data computations. There is an urgent need to develop sustainable mobile telecommunication networks subscribed by Telecommunication Regulatory Authority of India (TRAI). This paper aims at deploying major recommendations and directions in computing systems directed by regulating authorities. Green computing–based power‐saving policies include virtualization technique, power‐saving method, and recycling technique‐type solution components that we tried to embed in existing systems. The energy‐efficient green computing reserves the reliability and power of information‐driven technology. This research paper provides a comprehensive approach toward applying green mechanism by spotting the difference between energy consumption of current academic scenario and after embedding power‐saving policies of green computing. Moreover, an account has been maintained about the amount of energy preservation. The extraordinary energy‐ and cost‐saving features of green computing make environment sustainable and lively for future generations.     

云计算中关键虚拟化技术及其安全防御机制研究

随着信息技术的发展,云计算技术被广泛应用于各个领域。由于云计算能实现资源共享、灵活供给、快速交付和弹性扩展,政府和企业都在努力建立自己的云计算环境,虚拟化技术是构建云计算环境的关键,它为建立云服务和应用提供了基础。文中深入分析了虚拟化技术的各个方面,包括 Hypervisor 技术、计算虚拟化、存储虚拟化和网络虚拟化。同时,文中还指出了虚拟化给云平台带来的主要安全问题。为解决这些安全问题,文中提出了一些安全防御机制和建议。首先,需构建安全防御建设思路,明确安全目标和策略。其次,可以采用分域控制机制,将虚拟化平台划分为多个安全区域,以增强其安全性。此外,还应设计安全防御措施,包括虚拟化安全、Hypervisor 技术安全、虚拟机安全和虚拟网络安全等。通过针对性地提出这些安全防御机制和措施,可以确保虚拟化平台提供安全、可靠的服务,使政府和企业能更好地应用云计算技术来处理大量的数据     

基于XML/Web Services的P2P文件共享系统的实现

联网计算机之间没有主次之分,各自具有独立的网络自主权,端到端(Peer-to-Peer,P2P)模型能有效地实现计算能力和数字资源的共享和整合.本文介绍一个采用端到端的,层次分布化模型的文件共享系统,定义了关键的系统场景,分析了利用XML/Web Services实现方法,并给出了一个P2P设计模型.     

云雾混合网络下基于多智能体架构的资源分配及卸载决策研究

针对D2D辅助的云雾混合架构下资源分配及任务卸载决策优化问题,该文提出一种基于多智能体架构深度强化学习的资源分配及卸载决策算法。首先,该算法考虑激励约束、能量约束以及网络资源约束,联合优化无线资源分配、计算资源分配以及卸载决策,建立了最大化系统总用户体验质量(QoE)的随机优化模型,并进一步将其转化为MDP问题。其次,该算法将原MDP问题进行因式分解,并建立马尔可夫博弈模型。然后,基于行动者-评判家(AC)算法提出一种集中式训练、分布式执行机制。在集中式训练过程中,多智能体通过协作获取全局信息,实现资源分配及任务卸载决策策略优化,在训练过程结束后,各智能体独立地根据当前系统状态及策略进行资源分配及任务卸载。最后,仿真结果表明,该算法可以有效提升用户QoE,并降低了时延及能耗。     

一种基础设施云系统——YUN

文章设计了一个虚拟化平台层——YUN系统,介绍了YUN系统的设计目标、系统架构及主要子系统的功能。YUN系统是一种基础设施云系统。YUN系统管理和虚拟化异构、分布的物理资源(包括服务器设备、网络设备、存储设备),并以即付即用的方式将这些资源按需提供给用户使用;通过虚拟化和网络技术,将操作系统功能边界扩展到网络侧,使得终端侧和网络侧能够在一个统一的架构内进行计算和资源的配置、调度、管理,实现网络化操作系统充分、合理地使用和共享网络系统内的资源。     

一体化信号处理与先进处理架构展望

多功能一体化系统是电子信息技术领域的重要发展方向之一,一体化信号处理是其中的关键技术,对实现各种功能之间资源共享与高效协同具有重大意义,同时也从算法到处理架构提出了新的要求。本文首先对一体化信号处理的研究现状进行了归纳总结,给出一种基于一体化信号的多功能系统模型,指出进一步开发空域资源是当前一体化信号设计的主要研究方向之一,并且给出相关信号处理的典型算法;然后,针对上述算法进行了核心算子提炼,指出该类算法以大规模矩阵运算为主要特征,对处理架构提出高算力、高能效的需求;最后,针对上述算法的核心算子设计了基于存内计算和光子计算的处理架构,由于避免了数据搬移并采用高性能模拟计算模式,因此可以大幅提升算力和能效,为一体化信号处理先进架构设计提供了新的技术途径。     

Enforcing Cooperative Resource Sharing in Untrusted P2P Computing Environments

Peer-to-Peer (P2P) computing is widely recognized as a promising paradigm for building next generation distributed applications. However, the autonomous, heterogeneous, and decentralized nature of participating peers introduces the following challenge for resource sharing: how to make peers profitable in the untrusted P2P environment? To address the problem, we present a self-policing and distributed approach by combining two models: PET, a personalized trust model, and M-CUBE, a multiple-currency based economic model, to lay a foundation for resource sharing in untrusted P2P computing environments. PET is a flexible trust model that can adapt to different requirements, and provides the solid support for the currency management in M-CUBE. M-CUBE provides a novel self-policing and quality-aware framework for the sharing of multiple resources, including both homogeneous and heterogeneous resources. We evaluate the efficacy and performance of this approach in the context of a real application, a peer-to-peer Web server sharing. Our results show that our approach is flexible enough to adapt to different situations and effective to make the system profitable, especially for systems with large scale.     

Virtualizing on-chip distributed ScratchPad memories for low power and trusted application execution

Emerging multicore platforms are increasingly deploying distributed scratchpad memories to achieve lower energy and area together with higher predictability; but this requires transparent and efficient software management of these critical resources. In this paper, we introduce the concept of ScratchPad Memory virtualization, a hardware/software run-time layer (called SPMVisor) that virtualizes the scratchpad memory space in order to facilitate the use of distributed SPMs in an efficient, transparent and secure manner. We introduce the notion of virtual scratchpad memories (vSPMs), which can be dynamically created and managed as regular SPMs. The SPMVisor exploits policy-driven allocation strategies based on application privilege levels and data level prioritization metrics (e.g., utilization) to efficiently manage the on-chip memory real-estate. Our experimental results on Mediabench/CHStone benchmarks running on various Chip-Multiprocessor configurations and software stacks (RTOS, virtualization, secure execution) showed that SPMVisor enhances performance by 71 % on average and reduces power consumption by 79 % on average with respect to traditional context switching schemes. We showed the benefits of using vSPMs in a various environments (a RTOS multi-tasking environment, a virtualization environment, and a trusted execution environment). Furthermore, we explored the effects of mapping instructions and data onto vSPMs, and showed that sharing on-chip space reduces both execution time and energy by an average 16 % and 12 % respectively. We then compared our priority-driven memory allocation scheme with traditional dynamic allocation and showed an average 54 % execution time reduction and 65 % energy savings. Finally, to further validate the SPMVisor’s benefits, we modified the initial bus-based architecture to include a mesh-based CMP with up to 4×4 nodes. We were able to observe that SPMVisor’s priority-driven allocator was able to reduce execution time by an average 17 % with respect to competing allocation policies, while saving an average 65 % across various architectural configurations. We were also able to observe that SPMVisor reduces execution time by an average 12.6 % with respect to competing allocation policies, while saving an average 63.5 % in total energy for various architectural configuration running 1024 jobs.     

Analysis of a discrete multipriority queueing system involving acentral shared processor serving many local queues

The authors consider a multipriority queuing system which involves several distributed local queues and a central server which performs round-robin processor sharing (RRPS). This queuing model, referred to as multiqueue processor sharing (MPS), is an extension of Kleinrock's classical processor sharing model with generalization to multiple priorities and the addition of a buffer at each traffic source for each priority to buffer additional packets queued at that source. The authors present an exact analysis of the MPS model which leads to a closed-form result for the mean packet delay as a function of the packet length for each priority. It is demonstrated by simulation that the result obtained is applicable for accurately computing the average packet delay for a DQDB (distributed queue dual bus) subnetwork, given that stations transmitting on the same bus are not widely separated     

Repeated Public Goods Game Mode for Trust Based P2P Networks

In recent years, peer-to-peer (P2P) network systems have been widely used in the Internet. Particularly, P2P file sharing mechanism has emerged popularity and attract millions of users. However, to create an efficient P2P system, end users should share their resources among a group of other users. To satisfy this objective, this paper applies the repeated public goods game model to P2P systems. By adopting an interactive self-learning mechanism, the proposed scheme gradually leads the P2P system into an efficient network equilibrium. In a distributed manner, our approach is a practical and suitable method in real world P2P network operations. With a simulation study, it is demonstrated that the proposed scheme can obtain better performance than other existing schemes under widely diverse file request rates.