深度学习驱动下IaaS云运维异常检测算法的研究进展

异常检测是IaaS云系统运维中的一个关键任务,通过早期预警和提前干预,可有效避免系统崩溃等严重事故的发生。但相较于传统数据中心,IaaS云系统具有较大规模的计算节点,节点拓扑复杂、监测数据量大、缺少标注信息等特点,为IaaS云运维异常检测带来新的挑战。从深度学习的技术框架出发,分析了异常检测问题面临的难点,调研总结了IaaS云系统下常见异常检测算法和相关技术。面向节点异常和系统异常两类典型问题,对深度学习驱动的解决方法进行调研:面向节点级别异常,重点调研了时间依赖的运维数据下由时序数据驱动的检测算法;面向系统级别异常,重点调研了网络拓扑建模下由图数据驱动的检测算法。最后,提出了数据驱动下IaaS云运维数据异常检测中的新问题与新挑战。

IaaS云满足预算约束的工作流应用调度算法

为了解决IaaS(Infrastructure as a Service)云的工作流调度优化问题,提出基于预算约束的工作流调度算法。以最小化工作流调度时长为目标,算法分调度任务选择和虚拟机实例选择两阶段进行。第一阶段将工作流任务依据依赖关系作层次划分,同层次组成包任务,以Min-Max方法对层次任务估算时间作标准化处理,定义最迟完成时间与最早完成时间差值最大者为调度任务;第二阶段在期望预算下以最早完成时间最小为标准选择资源,实现任务与资源间的映射。利用算例阐述了算法实现过程,并通过仿真实验测试了算法性能。结果证实,改进算法执行效率与调度成功率优于同类算法。

IaaS Public Cloud Computing Platform Scheduling Model and Optimization Analysis

IaaS (Infrastructure as a Platform) public cloud is one mainstream service mode for public cloud computing. The design aim of one IaaS public cloud is to enlarge the hardware-usage of whole platform, optimize the virtual machine deployment and enhance the accept rate of service demand. In this paper we create one service model for IaaS public cloud, and based on the waiting-line theory to optimize the service model, the queue length and the configuration of scheduling server. And create one demand-vector based scheduling model, to filter the available host machine according to the match of demand and metadata of available resource. The scheduling model can be bonded with the virtual machine motion to reallocate the resources to guarantee the available rate of the whole platform. The feasibility of the algorithm is verified on our own IaaS public cloud computing platform.

Cloud Computing: Purpose and Future

Cloud computing is the new norm within business entities as businesses try to keep up with technological advancements and user needs. The concept is defined as a computing environment allowing for remote outsourcing of storage and computing resources. A hybrid cloud environment is an excellent example of cloud computing. Specifically, the hybrid system provides organizations with increased scalability and control over their data and support for a remote workforce. However, hybrid cloud systems are expensive as organizations operate different infrastructures while introducing complexity to the organization’s activities. Data security is critical among the most vital concerns that have resulted from the use of cloud computing, thus, affecting the rate of user adoption and acceptance. This article, borrowing from the hybrid cloud computing system, recommends combining traditional and modern data security systems. Traditional data security systems have proven effective in their respective roles, with the main challenge arising from their recognition of context and connectivity. Therefore, integrating traditional and modern designs is recommended to enhance effectiveness, context, connectivity, and efficiency.

Hybrid Prairie Dog and Beluga Whale Optimization Algorithm for Multi-Objective Load Balanced-Task Scheduling in Cloud Computing Environments

The cloud computing technology is utilized for achieving resource utilization of remotebased virtual computer to facilitate the consumers with rapid and accurate massive data services.It utilizes on-demand resource provisioning,but the necessitated constraints of rapid turnaround time,minimal execution cost,high rate of resource utilization and limited makespan transforms the Load Balancing(LB)process-based Task Scheduling(TS)problem into an NP-hard optimization issue.In this paper,Hybrid Prairie Dog and Beluga Whale Optimization Algorithm(HPDBWOA)is propounded for precise mapping of tasks to virtual machines with the due objective of addressing the dynamic nature of cloud environment.This capability of HPDBWOA helps in decreasing the SLA violations and Makespan with optimal resource management.It is modelled as a scheduling strategy which utilizes the merits of PDOA and BWOA for attaining reactive decisions making with respect to the process of assigning the tasks to virtual resources by considering their priorities into account.It addresses the problem of pre-convergence with wellbalanced exploration and exploitation to attain necessitated Quality of Service(QoS)for minimizing the waiting time incurred during TS process.It further balanced exploration and exploitation rates for reducing the makespan during the task allocation with complete awareness of VM state.The results of the proposed HPDBWOA confirmed minimized energy utilization of 32.18% and reduced cost of 28.94% better than approaches used for investigation.The statistical investigation of the proposed HPDBWOA conducted using ANOVA confirmed its efficacy over the benchmarked systems in terms of throughput,system,and response time.

An Agent Based Model for Ransomware Detection and Mitigation in a Cloud System

The increasing trend toward dematerialization and digitalization has prompted a surge in the adoption of IT service providers, offering cost-effective alternatives to traditional local services. Consequently, cloud services have become prevalent across various industries. While these services offer undeniable benefits, they face significant threats, particularly concerning the sensitivity of the data they handle. Many existing mathematical models struggle to accurately depict the complex scenarios of cloud systems. In response to this challenge, this paper proposes a behavioral model for ransomware propagation within such environments. In this model, each component of the environment is defined as an agent responsible for monitoring the propagation of malware. Given the distinct characteristics and criticality of these agents, the impact of malware can vary significantly. Scenario attacks are constructed based on real-world vulnerabilities documented in the Common Vulnerabilities and Exposures (CVEs) through the National Vulnerability Database. Defender actions are guided by an Intrusion Detection System (IDS) guideline. This research aims to provide a comprehensive framework for understanding and addressing ransomware threats in cloud systems. By leveraging an agent- based approach and real-world vulnerability data, our model offers valuable insights into detection and mitigation strategies for safeguarding sensitive cloud-based assets.

ICFF:一种IaaS模式下的云取证框架

分析了云取证技术所面临的挑战,提出了一种基础设施即服务(IaaS)云模型下的取证框架ICFF,并在开源IaaS云平台Eucalyptus中进行了实现,最后通过实验的方法对ICFF进行了验证分析。实验结果表明,该框架能够有效并快速地获取云平台中的证据数据。

IaaS公有云平台调度模型研究

抽象出IaaS公有云平台的服务模型,基于排队论对平台服务模式、队列长度、调度服务器设置等进行了优化分析。在此基础上提出一种基于IaaS平台需求向量的调度模型,根据需求与可用资源的匹配度从平台管理的物理机集合中筛选出可用的宿主机,若一次性无法找到符合要求的宿主机,平台调度算法结合虚拟机迁移操作,对物理资源进行重新分配,在实现平台资源利用率最大化的同时,保障了平台的可用性。将该算法应用在自主研发的云计算平台上,实验结果验证了该算法的可行性。

基于云计算IaaS产品测试技术的研究

随着云计算的发展,为了保障云服务质量的可靠性,云测试的研究日益受到关注。除了基于云计算资源的软件测试,针对云中的基础设施及云环境本身的云平台测试是云测试的另一个重要方面。在云产品的测试过程中,作为云平台基石的IaaS性能好坏将严重影响其他层云服务质量的可靠性。通过研究IaaS的体系结构和系统部署,从物理服务器、虚拟机、策略、安全等不同层面分析了其主要测试点,并展望了未来亟待解决的关键问题,为IaaS测试相关研究提供了参考。

IaaS环境下虚拟机无代理通信加密机制

针对Iaa S(infrastructure as a service)环境下虚拟机通信数据在共享网络基础设施中的安全性问题,提出了一种虚拟机无代理通信加密机制。该机制通过加载于虚拟化节点内的加密模块与平台统一加密控制器间的协作,实现了Iaa S环境下虚拟机通信无代理按需加密;同时,引入通信加密策略有效性保障机制,保障了虚拟机全生命周期内的通信加密策略有效性。实验结果表明,该机制在引入较小性能开销的前提下,可以有效实现虚拟机通信加密,并保障虚拟机全生命周期内加密策略的有效性。

一种IaaS模式“云训练”系统设计

针对网络化模拟训练真实感不强,训练效率低等问题,提出了一种Iaa S(Infrastructure as a Service)模式的"云训练"。阐述了"云训练"的体系结构和运行模式,研究了"云训练"的3项核心技术。通过GPU虚拟化技术解决云环境中终端用户3D图形图像处理能力弱的问题。根据模拟训练特点,建立用户需求模型,将模糊理论引入资源调度技术中,实现虚拟资源的动态调度;结合检查点回滚、虚拟机备份和虚拟机迁移技术,实现系统高效动态容错,保证了系统的稳定性与可靠性。实验证明,"云训练"系统改善了传统模拟训练系统中资源的按需共享能力,提升了资源利用率,保证了模拟训练效果。

电信运营商开放式IaaS云平台研究

近年来,电信运营商不断推出自有IaaS云计算服务和产品,IaaS云平台作为其底层资源的统一管理工具,由于其封闭性逐渐成为资源弹性调度与业务灵活提供的瓶颈。为了更好地适应未来电信运营商云业务的开展,需要结合自身云计算业务需求打造端到端开放式IaaS云管理平台。基于平台实现产业内多厂商的技术合作与开发,联合云计算企业推动国内开放化的计算、存储、网络等平台体系架构以及云间互联互通标准。在实现开放平台体系的过程中,积极借鉴以OpenStack为代表的开源云平台的架构优势与技术优势,实现云平台系统的可扩展、底层兼容、差异化服务以及规模部署能力,基于运营商的优势智能管道,致力于功能细化、架构优化与部署规模化,最终实现云平台的精细化、构件化与服务化的运营。

面向IaaS云服务基础设施的电子证据保全与取证分析系统设计

随着云技术在计算机网络领域的广泛应用,云环境下的安全审计与电子取证需求也日益迫切。由于云取证与传统计算机取证在取证环境、证据获取及证据分析方面有较大区别,目前尚缺乏有效的针对云的电子取证方法及技术手段,云系统作为一种信息系统,其可审计性得不到保证。文章设计了一套新的云取证系统,面向IaaS云服务的基础设施,通过采集终端对云系统中虚拟机进行监控并主动采集证据,同时将采集到的证据集中存放于一处,取证系统实时取证、证据集中保全的特性可以有效应对云环境下证据易失、证据提取困难的特点,达到高效取证。

数字图书馆IaaS云计算平台安全策略研究

"云"计算是一种新兴的共享基础架构方法。"云"计算虽然给用户带来经济与高效的应用,但用户信息资源安全与隐私保护也受到极大的挑战。本文分析了数字图书馆IaaS云计算平台的安全问题,然后根据IaaS云计算平台特点,提出了数字图书馆IaaS云计算平台安全结构与安全策略。

面向IaaS云平台的用户异常行为检测方法

针对IaaS(Infrastructure as a Service)云平台中用户异常行为的检测问题,提出了一种基于用户行为模型和神经网络相结合的异常检测方法.该方法通过构造一种基于时间、地点和事件的用户行为模型,在此基础上建立用户的正常行为模式,并与神经网络算法相结合,将用户当前行为网络输出值与给定阈值进行比较,以此来判断用户的行为是否异常,从而实现用户行为的异常检测.实验结果表明,相比其它类似的用户行为检测方法,该方法能更有效发现用户的异常行为.

煤炭企业接入公有云IaaS的成本效用分析

公有云因其易维护、可扩展性、按需定制等多种优势,被认为是未来信息技术产业的发展方向,越来越多的煤炭企业开始关注公有云。文章从煤炭企业最为关心的成本这一核心要素,结合实践案例,探讨了传统方式下所需要的软件、硬件、电力、人力、网络接入等整体投入成本,以及接入公有云需要的服务器实例成本,对比二者KPI大小,从而帮助煤炭企业选择适合自己的机房构建方式,提出了煤炭企业信息化建设的新思路。

提供可信IaaS服务的云计算平台构建

为建立用户对云服务的信任,构建了一种提供可信基础设施即服务(IaaS)的云计算平台。针对虚拟化层Hypervisor的特点,为IaaS云计算平台构建信任链。采用顺序的加载时度量方式建立由可信根至GuestOS kernel的信任链。对于管理虚拟机上动态加载的应用软件,采用基于可信可执行程序列表的无序度量方式实现对应用程序的完整性度量,从而建立完整的信任链。设计协议允许用户将其虚拟机镜像与云计算平台的完整性绑定,保证用户虚拟机开启在可信的IaaS平台。基于Xen系统和Linux内核实现了度量机制。实验结果表明,该方案具有较小性能开销。

IaaS模式“云训练”资源预测-调度方法

基础设施即服务(infrastructure as a service,IaaS)模式"云训练"是基于IaaS云计算提出的武器装备系统模拟训练的模式,根据用户需求对训练资源进行预测调度是提高训练效果的重要保证。分析了"云训练"中用户任务、资源需求特点,采用阈值法进行预处理,通过动态权值系综模型得到预处理结果。在此基础上,提出基于减法-模糊聚类的模糊神经网络的资源需求预测方法(subtractive-fuzzy clustering based fuzzy neural network,SFCFNN),并引入自适应学习率和动量项以提升收敛速度和稳定性。调度器根据预测结果实现用户需求与资源之间的动态匹配。实验表明该方法可精确预测用户资源需求,实现资源动态调度,有效提高资源利用率与训练效果。

基于IaaS的医院云平台构建研究

云计算以其高资源利用率和扩展性架构满足了医院对软硬件资源弹性分配、高效管理、安全可靠和低成本等需求。立足于医院信息建设现状,探讨了基于IaaS的医院云平台构建模式,并给出了具体步骤、措施和建议。

面向IaaS云服务的云系统中虚拟机监控及证据采集

基于云系统实例,分析在虚拟机监控与证据采集中,如何面向Iaa S云服务,优化设计系统功能,提升其监控及证据采集能力,降低系统成本。云系统中面向Iaa S云服务,设计实现虚拟机监控与证据采集,提升虚拟机监控能力,较之前提升21.0%,其证据采集能力也得到提高,且降低系统开发成本,节约成本费用达到38.0%。在云系统的虚拟机监控与证据采集中,应用面向Iaa S云服务,发挥积极应用价值,提升系统监控及数据采集能力,发挥积极影响。