基于云计算的人工智能AIaaS云服务平台研究

随着人工智能技术在各领域的应用推广,传统互联网人工智能云服务平台或产品难以满足各行业不同业务场景、模型的集约管理以及服务能力提升等迫切需求。提出通过在开源的K8S云平台容器框架上导入并集成OpenVINO?Model Server强大的AI服务组件,构建企业级人工智能服务AIaaS云服务平台。实现了AI模型快速部署、便捷运维、集约化管理,提高了服务能力和用户体验。测试结果表明,提出的框架在性能上优于同类技术框架,满足实际生产业务需求。     

运营商IT系统云原生部署方案研究

云原生技术栈统一的标准化交付能力大幅提升了云端效能。云原生技术有利于各组织在公有云、私有云和混合云等新型动态环境中构建和运行可弹性扩展的应用,将重构IT运维和开发模式。云原生和微服务是软件架构的发展趋势。运营商IT系统正积极探索云原生应用,以期避免软件厂商的绑架、支持软件系统的全网统一部署、助推业务应用的创新。结合运营商IT系统上云的需求,给出了运营商IT系统云原生的目标架构、演进路径和部署要点。     

面向云网融合的智能云原生架构和关键技术研究

作为云计算的最新技术成果,云原生技术快速推动互联网和企业应用上云。云原生技术可以为通信运营商网络提供更加经济、便捷的部署和运营方法,随着运营商云网融合工作推进,云原生成为运营商网络云化的核心技术和关键抓手。分析了云原生技术应用情况和存在的问题,提出面向云网融合的智能云原生架构,研究演进设计、架构部署方案和关键技术,提出云原生化推进举措。     

基于REST架构风格的云物理服务器部署机制

全球云计算市场快速平稳增长,越来越多的企业和科研机构将应用部署在公用云计算平台上。但是有部分应用在虚拟云主机上运行时的效率很低或根本无法运行,为解决这个问题,提出了基于REST架构风格的云物理服务器部署机制,通过该机制可以将这类应用直接部署在云物理服务器上。在服务器端借助Cobbler控制物理服务器,并基于REST架构风格对Cobbler服务器进行了二次开发和封装,通过调用相应的REST接口,Web服务器可以与Cobbler服务器进行交互,实现了用户通过Web管理面板对云物理服务器的完全控制。在真实环境下对该部署机制进行了测试,实现了预期的设计目标。     

云原生下基于深度强化学习的移动目标防御策略优化方案

针对云原生环境下攻击场景的复杂性导致移动目标防御策略配置困难的问题,该文提出一种基于深度强化学习的移动目标防御策略优化方案(SmartSCR)。首先,针对云原生环境容器化、微服务化等特点,对其安全威胁及攻击者攻击路径进行分析;然后,为了定量分析云原生复杂攻击场景下移动目标防御策略的防御效率,提出微服务攻击图模型并对防御效率进行刻画。最后,将移动目标防御策略的优化问题建模为马尔可夫决策过程,并使用深度强化学习解决云原生应用规模较大时带来的状态空间爆炸问题,对最优移动目标防御配置进行求解。实验结果表明,SmartSCR能够在云原生应用规模较大时快速收敛,并实现逼近最优的防御效率。     

基于云原生技术敏捷交付云网融合应用

云网融合是通信运营商近年推动的新一代信息基础设施的核心能力,云原生技术是云网融合的基础,促成能力汇聚和业务创新。DevOps流程和工具链作为云原生的核心特征,让云网融合应用可以敏捷迭代和部署,用持续交付的高质量应用实现商业价值。以通信运营商的视角,从敏捷流程转型、敏捷交付关键技术、DevOps平台建设3方面,给出云原生环境下敏捷交付云网融合应用的思路和方案,并用DevOps平台的实际运行情况论证。     

面向云原生的智能运维架构和关键技术

凭借应用简单快捷、部署应用轻松自如、运行应用按需伸缩等优点,云原生技术得到迅速推广。但随着云原生的应用,系统架构愈加复杂,资源规模愈加庞大,迫切需要更加智能化的运维。利用智能运维,可以更好地助力云原生的应用开发,降低运维成本,提高服务质量。分析了智能运维的应用场景、关键点、经典实践以及存在的问题,提出了一种面向云原生的智能运维架构,详细介绍了核心服务算法平台中趋势预测、数据异常检测和故障定位诊断3个场景主要原理,最后展望智能运维未来。     

融合网格的NGN增值服务平台及建模分析

该文提出一种融合网格的下一代网络增值服务平台以解决下一代网络应用服务器的性能问题。该平台将下一代网络应用服务器中的增值业务以网格服务的形式进行封装,并为封装后的增值服务提供运行环境。平台采用一种基于网格技术的任务调度算法,通过利用现有网络上的处理能力以提高系统整体处理能力和性能。采用随机Petri网对平台进行建模,并进行性能仿真实验。实验结果说明本平台能较好地达到利用网络中空闲处理能力以提高系统整体性能的目标。     

基于日志可观测的云——边协同微服务部署优化

依托微服务、容器化等云原生能力,数字化业务可拆分成细粒度的微服务模块,通过云边协同的方式优化微服务部署模式。一般来说,边缘计算可通过将计算资源扩展到网络边缘侧,降低物联网应用的响应时延及运行开销,但边缘侧设备计算及存储能力有限,通常难以满足组合服务多类型资源需求。因此,将中心云与边缘侧设备的微服务功能进行划分,是提高服务质量、优化网络性能的必要手段。为了实现微服务模块的合理配置,提出了一种基于日志可观测的云—边协同微服务部署优化方法,构建基于微服务的时序过程模型,并通过时序约束挖掘算法发现微服务间连接关系。采用多目标优化算法,最小化微服务配置时延和能耗,实现云—边协同微服务部署优化。最后,实验验证了方法的有效性。     

基于二维云模型的网格服务可靠性评价

网格是一个集成的计算和资源环境，具有动态性、异构性、可扩展性和自治性等特点。OGSA是一种新的网格体系架构，是以服务为中心的，提出了“网格服务”的概念。网格服务因网格的特点也具有动态性和不确定性，但是用户在网格进行其业务时，付出了金钱和时间，希望能获得可靠的网格服务。因此，对网格服务进行可靠性评价是关键。提出采用云模型的方法，从多个分指标来综合评价网格服务，这样就可以保证用户可以获得满足其需要的网格服务。     

上下文感知的6G无线网络

ICDT深度融合是移动通信演进的重要技术趋势之一,如何实现无线网络和AI技术的深度融合是无线网络中演进的重要课题。基于内生AI（native AI）概念,研究在无线网络中使用AI工具进行无线资源优化。提出了一种上下文感知的6G无线网络架构,并在RRM中引入内生AI工具,形成智能控制器智能化无线资源管理（AI-driven RRM）,完成智能无线资源管理的控制器,在大数据和人工智能的驱动下,实现对无线资源的智能化管理。该部署方案把智能控制器按照功能进行部署,并支持动态的功能伸缩,让其部署独立于基站接入点之外以实现基站硬件成本最小化。     

基于边缘计算的高效视频内容分发关键技术与挑战

近年来移动互联网、工业互联网的快速发展,引发媒体计算与服务的一个新的趋势:以视频为代表的多媒体数据的产生、处理和分发越来越多地趋向网络边缘。复杂应用环境下,用户行为、系统资源的不确定性成为网络视频服务面临的重大挑战。如何引入人工智能与机器学习的方法,利用网络边缘的计算、存储和网络资源实现视频内容分发随需而动,从而支撑更低延迟、更高带宽需求的网络视频服务,逐渐成为新的研究和应用热点。该综述分析了基于边缘计算的视频分发所面临的挑战,提出了通过边缘计算的网络、存储和计算能力来进行视频内容分发的框架,并在此框架下给出了边缘缓存及替换、边缘内容预取、边缘内容收集和边缘计算迁移等视频分发的优化策略设计。     

Concast: design and implementation of an active network service

Concast is a network layer service that provides many-to-one channels: multiple sources send messages toward one destination, and the network delivers a single “merged” copy to that destination. As we have defined it, the service is generic but the relationship between the sent and received messages can be customized for particular applications. We describe the concast service and show how it can be implemented in a back ward-compatible manner in the Internet. We describe its use to solve a problem that has eluded scalable end-system-only solutions: collecting feedback in multicast applications. Our preliminary analysis of concasting effectiveness shows that it provides significant benefits, even with partial deployment. We argue that concast has the characteristics needed for a programmable service to be widely accepted and deployed in the Internet     

The evolution of multicast: from the MBone to interdomain multicastto Internet2 deployment

Multicast communication-the one-to-many or many-to-many delivery of data-is a hot topic. It is of interest in the research community, among standards groups, and to network service providers. For all the attention multicast has received, there are still issues that have not been completely resolved. One result is that protocols are still evolving, and some standards are not yet finished. From a deployment perspective, the lack of standards has slowed progress, but efforts to deploy multicast as an experimental service are in fact gaining momentum. The question now is how long it will be before multicast becomes a true Internet service. The goal of this article is to describe the past, present, and future of multicast. Starting with the Multicast Backbone (MBone), we describe how the emphasis has been on developing and refining intradomain multicast routing protocols. Starting in the middle to late 1990s, particular emphasis has been placed on developing interdomain multicast routing protocols. We provide a functional overview of the currently deployed solution. The future of multicast may hinge on several research efforts that are working to make the provision of multicast less complex by fundamentally changing the multicast model. We survey these efforts. Finally, attempts are being made to deploy native multicast routing in both Internet2 networks and the commodity Internet. We examine how multicast is being deployed in these networks     

Carrier-grade Ethernet challenges for IPTV deployment

Carrier-grade Ethernet standardization and deployment is gaining momentum due to the ease of deployment, lower cost, and compatibility with existing networks on the access end. When Internet protocol television (IPTV) is deployed using Ethernet as the underlying interconnect fabric infrastructure, meeting fine-grained traffic management (TM) requirements on the service provider side to meet quality of service (QoS), billing, and security features implementation on the user side poses several challenges. Such challenges could be met using the TM features built into network processors (NPs).     

Introducing new Internet services: why and how

Active networks permit applications to inject programs into the nodes of local and, more important, wide area networks. This supports faster service innovation by making it easier to deploy new network services. In this article, we discuss both the potential impact of active network services on applications and how such services can be built and deployed. We explore the impact by suggesting sample uses and arguing how such uses would improve application performance. We explore the design of active networks by presenting a novel architecture, ANTS (active network transport system), that adds extensibility at the network layer and allows for incremental deployment of active nodes within the Internet. In doing so, ANTS tackles the challenges of ensuring that the flexibility offered by active networks does not adversely impact performance or security. Finally, we demonstrate how a new network service may be expressed in ANTS     

Research and design of wap service system based on MISC platform

1 Introduction With the introduction of high mobile handsets with increasingly powerful functions and the applications of WAP2.0 with considerably novel technologies, a series of diverse hot WAP services have come into being and have been successfully lau…     

基于Web Services的分布式服务发现系统的研究

Internet中分布着大量不同类型的计算服务．为了更有效的查找这些服务，设计了一个面向计算的分布武服务发现系统。网络中的计算资源被部署为Web服务，并通过组件之间的互操作性调用服务。改进了UDDI中的服务订阅机制．并给出了服务部署、服务发布、服务定位和授权认证等关键问题的解决方案。利用集群及PC机环境构建系统。并进行了实际测试。     

Infrastructure for Intelligent Automation Services in the Smart Grid

The electricity grid is undergoing a radical transformation from a production-driven to a demand-driven energy delivery platform known as the smart grid. The integration of a large amount of renewable and distributed energy resources, together with new patterns of electricity production, accentuates the need for research in information and communication technologies to control bi-directional energy flows. The European FP7 project: “Energy Demand Aware Open Services for Smart Grid Intelligent Automation” is contributing to this research by providing an intelligent infrastructure for service deployment for the smart grid. The project defines a system architecture that provides interoperability between wireless sensors in home area networks connected over the Internet to a service provider function deployed in a cloud infrastructure. A key component in this infrastructure is the Home Energy Controlling Hub that, on the one hand, provides a platform for monitoring and aggregation of electricity consumption data from devices and appliances and, on the other hand, is the link between the deployed intelligent automation services and the home. To ensure openness and simplicity, the proposed infrastructure is based on the representational state transfer style architecture. This is adopted by implementing the emerging ZigBee IP and Smart Energy Profile 2.0 standards that to a wide extend conform with the Internet Protocol suite and state-of-the art web services development.