Virtual Machines In Cloud Research Articles

Global host allocation policy for virtual machine in cloud computing

In world of cloud computing, allocation of virtual machine are on bases of available hardware and software in server of data centers. Most of allocation policy depends on utilization of hardware and software without affecting SLA and Quality of Service as main concern. Every allocation policy maintains some parameter for provide service in extensive level by keep allocation of virtual machine between upper and lower threshold. But dynamic allocation of virtual machine may have deviation in host workload. To deal with this situation a methodology was adopted utilization threshold that provide absolute median deviation for setting up threshold. This methodology has a major impact on dynamic virtual machine allocation in cloud. The dynamic workload on a host occurs due change in VM requesting resources. Even we get effective utilization of virtual machine through median absolute policy still is some resource unallocated in host. For deal with this situation we introduce a Global cloud methodology, main role is to collect all unallocated resource from different resource and provide access to new VM request for increase resource utilization. In this paper we consider Median absolute deviation with global host establishment for better resource utilization and reduce energy consumption.

Energy-performance optimisation for the dynamic consolidation of virtual machines in cloud computing

Dynamic consolidation of virtual machines (VMs) can reduce energy consumption by switching idle hosts to sleep mode. However, to meet the quality of service of customers, it is necessary to achieve the trade-off between energy and performance. This paper first puts forward a new dynamic threshold adjustment method using the variation coefficient of historical CPU utilisation, actual CPU utilisation and million instructions per second requests by VMs in migration list. Furthermore, it devises a novel VM allocation policy based on the grey correlation degree model, and formulates a conversion model of CPU utilisation for achieving better trade-off between energy consumption and performance. Finally, some experiments are carried out on the CloudSim and the PlanetLab workloads. The experimental results show that the methods proposed in this paper have obvious advantages on the trade-off between energy and performance during the VM consolidation.

Energy-performance optimisation for the dynamic consolidation of virtual machines in cloud computing

Energy-performance optimisation for the dynamic consolidation of virtual machines in cloud computing

Monitoring and modelling service level agreement of multiple virtual machines in cloud computing

Service level agreement (SLA) is a contract between cloud computing customer and provider. Improving the customers' trust with cloud computing requires monitoring and ensuring the quality of the provided services continuously. Therefore, this paper provides a model for monitoring the SLA which belongs to the same customer and a specific provider of multiple virtual machines (VMs) in the same environment. The core foundations for this model are: SLA, quality of service (QoS) parameters, multiple VMs and violations' penalty assessment. The proposed model monitors the QoS parameters within multiple VMs environment dynamically and checks for any violation. Moreover; the penalty for each violation will be calculated and informed to the customer and provider at the same time. The proposed model depends on the time factor while running the VMs in sequentially manner with a short period of time as a gap between each VM. This model prevents any interception between VMs and can maintain synchronisation.

Monitoring and modelling service level agreement of multiple virtual machines in cloud computing

Service level agreement (SLA) is a contract between cloud computing customer and provider. Improving the customers' trust with cloud computing requires monitoring and ensuring the quality of the provided services continuously. Therefore, this paper provides a model for monitoring the SLA which belongs to the same customer and a specific provider of multiple virtual machines (VMs) in the same environment. The core foundations for this model are: SLA, quality of service (QoS) parameters, multiple VMs and violations' penalty assessment. The proposed model monitors the QoS parameters within multiple VMs environment dynamically and checks for any violation. Moreover; the penalty for each violation will be calculated and informed to the customer and provider at the same time. The proposed model depends on the time factor while running the VMs in sequentially manner with a short period of time as a gap between each VM. This model prevents any interception between VMs and can maintain synchronisation.

EATSVM: Energy-Aware Task Scheduling on Cloud Virtual Machines

The pervasive adoption of cloud computing services and applications at a rapid rate makes the underlying data centers exacerbate the problems like carbon footprint and the operational cost, caused by the energy consumption. Various hardware-centric and software-centric approaches are proposed in the literature to reduce the energy consumption of the cloud data centers. Task scheduling algorithms are software-centric approaches to reduce the energy consumption in cloud computing systems. The majority of these algorithms focus on server consolidation leading to idle servers that reduce energy efficiency optimization. In this paper, we propose an Energy-Aware Task Scheduling algorithm on cloud Virtual Machines (EATSVM) that assigns a task to the VM where the increase in energy consumption is the least, considering both active and idle VMs. The algorithm also takes into consideration the increase in the energy consumption of the already running tasks on the VM due to increase in their execution time, while assigning a new task to that VM. We analyze the performance of our algorithm in a heterogeneous cloud environment with increasing number of tasks and compare the energy-savings of our algorithm with that of Energy Conscious Task Consolidation (ECTC) algorithm. Our experimental results demonstrate that EATSVM achieves energy-saving in a heterogeneous cloud-computing environment.

Performance Evaluation of Bandwidth for Virtual Machine Migration in Cloud Computing

The proliferation of virtualisation enables cloud computing industries, such as Amazon, IBM, Google, Microsoft, and Rackspace to increase their physical hardware utilisation by multi-tenant model. One important key characteristic of server virtualisation is virtual machine (VM) migration. With the popularity of cloud paradigm, the number of enterprise applications deployed over cloud-systems are increasing. This shift in cloud services has brought new challenges of frequently varying resource requirement by the VM migration operation. Inaccurate allocation of bandwidth may affect end-user experience and reduce the cloud service provider's profit, Therefore, in this work we setup QEMU-KVM cloud VM migration experimental testbed environment and run CPU, memory intensive cloud benchmarks on the migrated VM. From the experimental results, it is found that increase in bandwidth significantly lower the migration time and downtime up-to an extent, however, reserving maximum bandwidth does not help anymore for performance improvement of migration mechanism.

Performance evaluation of bandwidth for virtual machine migration in cloud computing

The proliferation of virtualisation enables cloud computing industries, such as Amazon, IBM, Google, Microsoft, and Rackspace to increase their physical hardware utilisation by multi-tenant model. One important key characteristic of server virtualisation is virtual machine (VM) migration. With the popularity of cloud paradigm, the number of enterprise applications deployed over cloud-systems are increasing. This shift in cloud services has brought new challenges of frequently varying resource requirement by the VM migration operation. Inaccurate allocation of bandwidth may affect end-user experience and reduce the cloud service provider's profit, Therefore, in this work we setup QEMU-KVM cloud VM migration experimental testbed environment and run CPU, memory intensive cloud benchmarks on the migrated VM. From the experimental results, it is found that increase in bandwidth significantly lower the migration time and downtime up-to an extent, however, reserving maximum bandwidth does not help anymore for performance improvement of migration mechanism.

Performance Evaluation of Apache Spark Vs MPI: A Practical Case Study on Twitter Sentiment Analysis

The advent of various processing frameworks which happens under big data technologies is due to tremendous dataset size and its complexity. The speed of execution was much higher with High Performance computing frameworks rather than big data processing frameworks. As majority of the jobs under big data are mostly data intensive rather than computation intensive, the High Performance Computing paradigms were not been used in big data processing. This paper reviews two distributed and parallel computing frameworks: Apache Spark and MPI. Sentiment analysis on twitter data is chosen as a test case application for benchmarking and implemented on Scala programming for spark processing and in C++ for MPI. Experiments were conducted on Google cloud virtual machines for three data set sizes, 100 GB, 500 GB and 1 TB to compare the execution times. Results shown that MPI outperforms Apache Spark in parallel and distributed cluster computing environments and hence the higher performance of MPI can be exploited in big data applications for improving speedups.

Cost effective deadline aware scheduling strategy for workflow applications on virtual machines in cloud computing

In Cloud paradigm, resources are provisioned on demand and used for the leased time interval as pay per use basis. Generally, Cloud users use these resources to execute their applications. These applications may be the batch of independent or workflow tasks. The existing researches focus mainly on optimizing the various quality of service (QoS) parameters. In this paper, a Cost Effective Deadline Aware (CEDA) scheduling strategy has been proposed for the workflow tasks/applications in order to optimize the total execution time and economic cost while meeting the deadline and precedence constraints in the workflow. CEDA selects the task which has the highest upward rank and dispatches the selected task to the cheapest instance of virtual machines (VMs) considering the VMs acquisition delay. The performance evaluation of proposed strategy has been carried out by comparing it with ICPCP and ICPCPD2 on standard scientific workflows like Montage, CyberShake, LIGO and SIPHT. The experimental results show that CEDA outperforms among all considered algorithms on almost all parameters under study.

Leveraging content similarity among VMI files to allocate virtual machines in cloud

To meet a myriad of customers’ demands, a large number of virtual machines (VMs) have to be provisioned simultaneously in cloud data centers. Provisioning is usually time consuming due to the large size of virtual machine image (VMI) file that needs to be transferred via networks. To address this issue, researchers attempt to leverage the content similarity among different VMI files to reduce the volume of transferred data. In the VM provisioning, the VM packing problem that minimizes the number of physical machines is another important issue. In this paper, our goal is to find a solution that tries to pack VMs to the minimum number of PMs as well as significantly reduces the total amount of transferred data. We formally define the problem of VM packing and minimizing the data transferring in the VM provisioning, named RTVD-VA. We first propose an approximation algorithm to minimize the amount of transferred VMI data when provisioning K VMs with the same size to a single physical machine. We then extend the algorithm to address the scenario of multiple PMs when using the minimum number of PMs. Based on the above two approximation algorithms, we propose a heuristic algorithm, namely Balance-Placement, to solve the problem in general cases. Our simulation results show that Balance-Placement outperforms existing solutions like PSO and Greedy-Cache and achieves the least amount of transferred data and the minimum number of used PMs in most scenarios.

A slave ants based ant colony optimization algorithm for task scheduling in cloud computing environments

Since cloud computing provides computing resources on a pay per use basis, a task scheduling algorithm directly affects the cost for users. In this paper, we propose a novel cloud task scheduling algorithm based on ant colony optimization that allocates tasks of cloud users to virtual machines in cloud computing environments in an efficient manner. To enhance the performance of the task scheduler in cloud computing environments with ant colony optimization, we adapt diversification and reinforcement strategies with slave ants. The proposed algorithm solves the global optimization problem with slave ants by avoiding long paths whose pheromones are wrongly accumulated by leading ants.

Joint routing and mobile VM selection algorithm in multihop C‐RAN networks

SummaryBy combining the cloud radio access network (C‐RAN) and mobile cloud computing, the communication and computation cooperation is convenient to implement, and the mobile operators are able to provide better service for mobile users as well as decrease their construction funds. However, owing to the deficient bandwidths and far distances, some mobile devices are not able to access mobile cloud through C‐RAN directly. In this paper, we propose a multihop C‐RAN network to access mobile cloud that organizes the user equipment (UE) in the C‐RAN into self‐organized network, regarding UEs as relay routers to access the mobile cloud. Under the proposed architecture, the UEs far from remote radio heads are able to access C‐RAN by ad hoc network while the UEs near the remote radio heads will access C‐RAN directly. Besides, considering the benefit of both operators and mobile users, we propose a joint routing and mobile virtual machine (VM) selection algorithm based on the proposed multihop C‐RAN networks where the route is selected for task data transmission, and the VM in the mobile cloud is selected for task execution, which minimizes the total energy cost under the premise of satisfying the task response time required by user. The simulation result shows that the proposed algorithm outperforms conventional separate routing and VM selection on energy saving.

Cloud-Assisted Crowdsourced Livecast

The past two years have witnessed an explosion of a new generation of livecast services, represented by Twitch.tv , GamingLive , and Dailymotion , to name but a few. With such a livecast service, geo-distributed Internet users can broadcast any event in real-time, for example, game, cooking, drawing, and so on, to viewers of interest. Its crowdsourced nature enables rich interactions among broadcasters and viewers but also introduces great challenges to accommodate their great scales and dynamics. To fulfill the demands from a large number of heterogeneous broadcasters and geo-distributed viewers, expensive server clusters have been deployed to ingest and transcode live streams. Yet our Twitch-based measurement shows that a significant portion of the unpopular and dynamic broadcasters are consuming considerable system resources; in particular, 25% of bandwidth resources and 30% of computational capacity are used by the broadcasters who do not have any viewers at all. In this article, through the real-world measurement and data analysis, we show that the public cloud has great potentials to address these scalability challenges. We accordingly present the design of Cloud-assisted Crowdsourced Livecast (CACL) and propose a comprehensive set of solutions for broadcaster partitioning. Our trace-driven evaluations show that our CACL design can smartly assign ingesting and transcoding tasks to the elastic cloud virtual machines, providing flexible and cost-effective system deployment.

An extended Intelligent Water Drops algorithm for workflow scheduling in cloud computing environment

Cloud computing is emerging as a high performance computing environment with a large scale, heterogeneous collection of autonomous systems and flexible computational architecture. Many resource management methods may enhance the efficiency of the whole cloud computing system. The key part of cloud computing resource management is resource scheduling. Optimized scheduling of tasks on the cloud virtual machines is an NP-hard problem and many algorithms have been presented to solve it. The variations among these schedulers are due to the fact that the scheduling strategies of the schedulers are adapted to the changing environment and the types of tasks. The focus of this paper is on workflows scheduling in cloud computing, which is gaining a lot of attention recently because workflows have emerged as a paradigm to represent complex computing problems. We proposed a novel algorithm extending the natural-based Intelligent Water Drops (IWD) algorithm that optimizes the scheduling of workflows on the cloud. The proposed algorithm is implemented and embedded within the workflows simulation toolkit and tested in different simulated cloud environments with different cost models. Our algorithm showed noticeable enhancements over the classical workflow scheduling algorithms. We made a comparison between the proposed IWD-based algorithm with other well-known scheduling algorithms, including MIN-MIN, MAX-MIN, Round Robin, FCFS, and MCT, PSO and C-PSO, where the proposed algorithm presented noticeable enhancements in the performance and cost in most situations.

Self managed virtual machine scheduling in Cloud systems

In Cloud systems, Virtual Machines (VMs) are scheduled to hosts according to their instant resource usage (e.g. to hosts with most available RAM) without considering their overall and long-term utilization. Also, in many cases, the scheduling and placement processes are computational expensive and affect performance of deployed VMs. In this work, we present a Cloud VM scheduling algorithm that takes into account already running VM resource usage over time by analyzing past VM utilization levels in order to schedule VMs by optimizing performance. We observe that Cloud management processes, like VM placement, affect already deployed systems (for example this could involve throughput drop in a database cluster), so we aim to minimize such performance degradation. Moreover, overloaded VMs tend to steal resources (e.g. CPU) from neighbouring VMs, so our work maximizes VMs real CPU utilization. Based on these, we provide an experimental analysis to compare our solution with traditional schedulers used in OpenStack by exploring the behaviour of different NoSQL (MongoDB, Apache Cassandra and Elasticsearch). The results show that our solution refines traditional instant-based physical machine selection as it learns the system behaviour as well as it adapts over time. The analysis is prosperous as for the selected setting we approximately minimize performance degradation by 19% and we maximize CPU real time by 2% when using real world workloads.

An Efficient Decentralized Energy and Communication Aware Workload Management

In this paper, a research work is carried out to improve workload management by minimize energy consumption of node, localizing traffic in a network and reduce communication delay between virtual machines in cloud environment. Cloud computing consists numerous virtual machine to store huge volume of data. The usage of virtual machines is to provide separate guest operating system which is popular now-a-days. The workload management across different virtual machines in cloud is really a difficult process. Decentralized approaches were proposed in the literature for energy efficient management of virtual machines. But still it has some issues like failed to consider the communication between virtual machines and it leads to traffic in a network. Thus it reduces the performance of work load management.

Energy Efficiency of Cloud Virtual Machines: From Traffic Pattern and CPU Affinity Perspectives

Networking and machine virtualization play critical roles in the success of modern cloud computing. The energy consumption of physical machines has been carefully examined in the past, including the impact from network traffic. When it comes to virtual machines (VMs) in cloud data centers, the interplay between energy consumption and network traffic, however, becomes much more complicated. Through real-world measurement on both Xen- and KVM-based platforms, we show that these state-of-the-art virtualization designs noticeably increase the demand of CPU resources when handling network transactions, generating excessive interrupt requests with ceaseless context switching, which in turn, increases energy consumption. Even when a physical machine is in an idle state, its VM's network transactions will incur nontrivial energy consumption. More interestingly, the energy consumption significantly varies with traffic allocation strategies and virtual CPU affinity conditions , which was not seen in conventional physical machines. Looking closely into the virtualization architectures, we then pinpoint the root causes and examine that our measurement results can be extended for various network configurations. Moreover, we also provide initial solutions toward optimizing energy consumption in virtualized environments.

Using OS Design Patterns to Provide Reliability and Security as-a-Service for VM-based Clouds

This paper extends the concepts behind cloud services to offer hypervisor-based reliability and security monitors for cloud virtual machines. Cloud VMs can be heterogeneous and as such guest OS parameters needed for monitoring can vary across different VMs and must be obtained in some way. Past work involves running code inside the VM, which is unacceptable for a cloud environment. We solve this problem by recognizing that there are common OS design patterns that can be used to infer monitoring parameters from the guest OS. We extract information about the cloud user's guest OS with the user's existing VM image and knowledge of OS design patterns as the only inputs to analysis. To demonstrate the range of monitoring functionality possible with this technique, we implemented four sample monitors: a guest OS process tracer, an OS hang detector, a return-to-user attack detector, and a process-based keylogger detector.

Individual learner big data based cloud role player game learning

In this research, an Individual Learner Big Data Based Cloud Role Player Game Learning Corresponding to Individual Learner Big Data is proposed. Based on the proposed platform, all the learning states and information (Big Data) of individual learner can be further analyzed. By using dynamic assigni ng algorithm, individual learner (student) can be separated into different levels related to the learning ability. According to dynamic assigning algorithm, student's answering times and answering correct rate of each education scenario in the proposed cloud based digital game learning system is considered. Then, suitable teaching scenario will be provided for individual user corresponding to personal learning ability. Each designed modular teaching scenario can be embedded into the game platform on the virtual machine in cloud. The information about students in the game learning system can be stored in the cloud database. In addition, the whole learning system is established as a virtual machine. System maintainer can configure the learning system easily and quickly. Based on cloud, different remote devices can connect to server for learning.