Heterogeneous Cloud Systems Research Articles

High-Accuracy Analytical Model for Heterogeneous Cloud Systems with Limited Availability of Physical Machine Resources Based on Markov Chain

The article presents the results of a study on modeling cloud systems. In this research, the authors developed both analytical and simulation models. System analysis was conducted at the level of virtual machine support, corresponding to Infrastructure as a Service (IaaS). The models assumed that virtual machines of different sizes are offered as part of IaaS, reflecting the heterogeneous nature of modern systems. Additionally, it was assumed that due to limitations in access to physical server resources, only a portion of these resources could be used to create virtual machines. The model is based on Markov chain analysis for state-dependent systems. The system was divided into an external structure, represented by a collection of physical machines, and an internal structure, represented by a single physical machine. The authors developed a novel approach to determine the equivalent traffic, approximating the real traffic appearing at the input of a single physical machine under the assumptions of request distribution. As a result, it was possible to determine the actual request loss probability in the entire system. The results obtained from both models (simulation and analytical) were summarized in common graphs. The studies were related to the actual parameters of commercially offered physical and virtual machines. The conducted research confirmed the high accuracy of the analytical model and its independence from the number of different instances of virtual machines and the number of physical machines. Thus, the model can be used to dimension cloud systems.

ESPS: Energy Saving Power Spectrum-Aware Scheduling to Leverage Differences in Power Ratings of Physical Hosts in Datacenters

Cloud Computing has seen massive growth over the past couple of decades, leading to exponential growth in energy consumption at data centres. Data centres consuming high amounts of energy leave a carbon footprint of the same scale, hence Cloud Service Providers (CSPs) have been looking for energy-efficient solutions to task scheduling in cloud to reduce the amount of carbon dioxide emission. Saving energy not only helps reduce the carbon footprint datacentres have on the environment, but also helps cover the costs of running multiple datacentres on the CSP’s end. In this paper, we propose an energy saving task scheduling heuristic for heterogeneous cloud systems which selects the optimal physical host containing virtual machines with the additional consideration of the utilization of any incoming task on that particular virtual machine. We compare the energy efficiency of our proposed heuristic with recent algorithms including ECTC, MaxUtil, Random, and FCFS on several benchmark and synthetic datasets to display its superiority in energy-efficient task scheduling in heterogeneous cloud environments. Our proposed heuristic, namely Energy Saving Power Spectrum-Aware Scheduling (ESPS) minimizes energy consumption in a heterogeneous cloud environment by about 38.65%, 33.59%, 53.02%, and 46.96% when compared to FCFS, MaxUtil, Random and ECTC respectively.

Multi-security-level cloud storage system based on improved proxy re-encryption

Based on the characteristics and data security requirements of the cloud environment, we present a scheme for a multi-security-level cloud storage system that is combined with AES symmetric encryption and an improved identity-based proxy re-encryption (PRE) algorithm. Our optimization includes support for fine-grained control and performance optimization. Through a combination of attribute-based encryption methods, we add a fine-grained control factor to our algorithm in which each authorization operation is only valid for a single factor. By reducing the number of bilinear mappings, which are the most time-consuming processes, we achieve our aim of optimizing performance. Last but not least, we implement secure data sharing among heterogeneous cloud systems. As shown in experiment, our proposed multi-security-level cloud storage system implements services such as the direct storage of data, transparent AES encryption, PRE protection that supports fine-grained and ciphertext heterogeneous transformation, and other functions such as authentication and data management. In terms of performance, we achieve time-cost reductions of 29.8% for the entire process, 48.3% for delegation and 47.2% for decryption.

ECOS: An efficient task-clustering based cost-effective aware scheduling algorithm for scientific workflows execution on heterogeneous cloud systems

Cloud Computing provides an attractive execution environment for scientific workflow execution. However, due to the increasingly high charge cost of using cloud service, cost minimization for workflows execution on cloud systems has become a crucial issue. Traditional work are adopting the sophisticated scheduling techniques to address such issue. Differently, this paper has proposed an efficient task-clustering based cost-effective aware scheduling algorithm (ECOS) to minimize the cost without comprising the deadline constraint. First, with respect to the characteristics of multi-type workflows, cloud heterogeneity and cost model, we have formulated the problem of task-clustering to simplify the structure of workflows and workflow scheduling to minimize cost within the deadline constraint. Then, we have devised ECOS with two key steps: (1) vertical clustering is with the time consideration that selectively merges the sequential tasks to reduce the transferring time within the workflow; (2) horizontal clustering and greedy allocation is to aggregate the parallel tasks and greedily allocate resources to that tasks with the aim of minimizing cost within deadline. Last, we have conducted the experiment that compare with well-known task-clustering based algorithms via WorkflowSim platform. The results have demonstrated that ECOS can efficiently merge tasks and minimize the total cost without comprising the deadline constraint both in small and large datasets. Moreover, we have discussed the ECOS in terms of various schedulers and number of tasks to validate the performance of ECOS.

A Novel, Simulator for Heterogeneous Cloud Systems that Incorporate Custom Hardware Accelerators

The growing use of hardware accelerators in both embedded (e.g., automotive) and high end systems (e.g., Cloud infrastructure) triggers an urgent demand for simulation frameworks that can simulate in an integrated manner all the components (i.e., CPUs, Memories, Networks, and Hardware Accelerators) of a system-under-design(SuD). By utilizing such a simulator, software design can proceed in parallel with hardware development which results in the reduction of the so important time-to-market. The main problem, however, is that currently there is a shortage of such simulation frameworks; most simulators used for modelling the user applications (i.e., full-system CPU/Mem/Peripheral simulators) lack any type of support for tailor-made hardware accelerators. The presented ACSIM framework is the first known open-source, high-performance simulator that can handle holistically system-of-systems including processors, peripherals, accelerators, and networks; such an approach is, for example, very appealing for the design of Cloud Servers that incorporate FPGAs as PCI-connected accelerators. ACSIM is an extension of the COSSIM simulation framework and it integrates, in a novel and efficient way, a combined system and network simulator with a SystemC simulator, in a transparent to the end-user way. ACSIM has been evaluated when executing several real-world use cases; the end results demonstrate that the presented approach has up to 99 percent accuracy in the reported SuD aspects (when compared with the corresponding characteristics measured in the real systems), while the overall simulation time can be accelerated almost linearly with the number of CPUs utilized by the simulator. More importantly, the presented interconnection scheme between the Processing and the SystemC simulators is orders of magnitude faster than the existing solutions, while ACSIM can efficiently simulate up to several hundreds of processing nodes with hardware accelerators interconnected together, in a fully distributed manner.

PL-DVFS: combining Power-aware List-based scheduling algorithm with DVFS technique for real-time tasks in Cloud Computing

In recent years, energy efficiency has emerged as one of the most important design requirements for modern computing systems, ranging from single servers to data centers and Clouds, as they continue to consume an enormous amount of electrical power. Cloud computing can be used to achieve energy efficiency through efficient task scheduling in the distributed environment. This efficient task scheduling helps to improve resource utilization, which, in turn, helps to minimize energy consumption. In this paper, we work toward minimizing energy of directed acyclic graph-structured applications on heterogeneous cloud system. The paper also combines power-aware list-based scheduling algorithm with dynamic voltage and frequency scaling (DVFS) technique for real-time tasks (PL-DVFS) to maintain the quality of service while considering tasks deadlines. The goal of the approach is to improve performance and overall reduced energy consumption comprising CPU energy (busy and idle) and communication energy. Experiments conducted with synthetic workflow graphs clearly demonstrate the advantage of the proposed approach.

Optimal Task Scheduling for Distributed Cluster With Active Storage Devices and Accelerated Nodes

With advancements in compute-intensive and memory-bound applications, the need for faster and more energy-efficient processing platforms continues. In support of these advancements, heterogeneous platforms have been proposed to enhance the performance and efficiency in the cloud. These platforms include field programmable gate arrays and graphical processing units in addition to general-purpose processors. Furthermore, there is a strong interest in advancing active solid-state drives to support both storage and computation. In this paper, we present a generic formulation to support the modeling of such a heterogeneous cloud environment, without being specific to a particular cloud platform such as Spark or Hadoop. We represent the cloud as a collection of clients, middleware control nodes, and high performance compute nodes (HPN), where the HPNs represent the options of advanced compute technologies in a heterogeneous cloud. The objective of the paper is to present a simple and efficient formulation for scheduling applications in such a heterogeneous cloud. Consistent with recent software modeling of artificial intelligence applications, we propose to map applications into directed acyclic graph representations of tasks. The optimization problem is then formulated to infer the best scheduling of tasks on the HPNs, while minimizing the overall execution time and data communication delays between nodes. Unlike existing scheduling algorithms that assume equal performance across nodes, our formulation explicitly takes into account the different compute capabilities of the heterogeneous nodes. The resulting task scheduling is then evaluated to provide insights into the performance gains with the proposed advanced heterogeneous cloud computing environment. The results show improved performance when comparing the proposed task-scheduling algorithm with the genetic algorithm and heterogeneous earliest finish time algorithms. We also show the performance gains achieved with the optimal task scheduling on a heterogeneous cloud system as compared with a conventional CPU-only cloud system.

Budget‐constraint stochastic task scheduling on heterogeneous cloud systems

SummaryIn the past few years, more and more business‐to‐consumer and enterprise applications run in the heterogeneous clouds. Such cloud bag‐of‐tasks applications are usually budget constrained, and their scheduling is an essential problem for cloud provider. The problem is even more complex and challenging when the accurate knowledge about task execution time is unknown in advance. Focusing on these challenges, we first build a cloud resource management architecture and stochastic task model, which divides cloud task into two execution parts. Then, we deduce bag‐of‐tasks applications' schedule length (Makespan) and total cost according to heterogeneous clouds' online feedback information of task first part execution. Thirdly, we formulate this stochastic scheduling problem as a linear programming problem. Lastly, we propose a time and cost multiobjective stochastic task scheduling genetic algorithm, in which can find Pareto optimal schedules for stochastic cloud task that meet its budget constraint. The extensive simulation experiments were carried out on a heterogeneous cloud platform with 400 virtual machines, and tasks were derived from Parallel Workloads Archive and the analysis data of real‐world cloud systems. The experimental results show that our proposed stochastic task scheduling genetic algorithm can get shorter schedule length and lower cost with task budget constraints.

A speculative approach to spatial‐temporal efficiency with multi‐objective optimization in a heterogeneous cloud environment

AbstractA heterogeneous cloud system, for example, a Hadoop 2.6.0 platform, provides distributed but cohesive services with rich features on large‐scale management, reliability, and error tolerance. As big data processing is concerned, newly built cloud clusters meet the challenges of performance optimization focusing on faster task execution and more efficient usage of computing resources. Presently proposed approaches concentrate on temporal improvement, that is, shortening MapReduce time, but seldom focus on storage occupation; however, unbalanced cloud storage strategies could exhaust those nodes with heavy MapReduce cycles and further challenge the security and stability of the entire cluster. In this paper, an adaptive method is presented aiming at spatial–temporal efficiency in a heterogeneous cloud environment. A prediction model based on an optimized Kernel‐based Extreme Learning Machine algorithm is proposed for faster forecast of job execution duration and space occupation, which consequently facilitates the process of task scheduling through a multi‐objective algorithm called time and space optimized NSGA‐II (TS‐NSGA‐II). Experiment results have shown that compared with the original load‐balancing scheme, our approach can save approximate 47–55 s averagely on each task execution. Simultaneously, 1.254‰ of differences on hard disk occupation were made among all scheduled reducers, which achieves 26.6% improvement over the original scheme. Copyright © 2016 John Wiley & Sons, Ltd.

Scalable Loop Self-Scheduling Schemes for Large-Scale Clusters and Cloud Systems

Cloud systems have demonstrated the powerful computation and storage capability in many scientific applications. In this paper, we propose a class of scalable distributed loop self-scheduling schemes to achieve good load balancing and scalability. We implemented these schemes on a large-scale cluster and on a heterogeneous cloud system. The schemes consider the distribution of the output data, which can help reduce communication overhead and improve scalability. We evaluated the schemes using four scientific computations: Mandelbrot set, adjoint convolution, matrix multiplication and quick sort. The results show that the new schemes achieve better load balancing, better scalability and better overall performance than standard distributed loop self-scheduling schemes.

An SLA and power-saving scheduling consolidation strategy for shared and heterogeneous clouds

This paper presents a power-aware scheduling policy algorithm of Virtual Machines into nodes called Green Cloud (GreenC) for Heterogeneous cloud systems. GreenC takes into account optimal assignmen...

Energy Efficiency Oriented Scheduling for Heterogeneous Cloud Systems

Nowadays, how to improve energy efficiency has become a challenging problem in cloud computing. However, most existing efforts in improving the energy efficiency of a cloud system only focus on resource allocation at the system level like managing physical nodes or virtual machines. This paper tries to address the energy efficiency problem of a heterogeneous cloud system at the task scheduling level. A novel task scheduling algorithm is proposed to reduce the energy consumption of the system while maintaining its performance, without closing or consolidating any system resources such as virtual machines or storage systems. The algorithm dynamically monitors CPU and memory load information of participating nodes on a heterogeneous Hadoop platform with Ganglia, then selects and submits an appropriate task to the node with relatively low workload to avoid excessive energy consumption on some nodes. Experimental results show that this novel scheduling algorithm can effectively improve the energy-saving ratio of a heterogeneous cloud platform while maintaining a high system performance.

Fine-grained and heterogeneous proxy re-encryption for secure cloud storage

Cloud is an emerging computing paradigm. It has drawn extensive attention from both academia and industry. But its security issues have been considered as a critical obstacle in its rapid development. When data owners store their data as plaintext in cloud, they lose the security of their cloud data due to the arbitrary accessibility, specially accessed by the un-trusted cloud. In order to protect the confidentiality of data owners’ cloud data, a promising idea is to encrypt data by data owners before storing them in cloud. However, the straightforward employment of the traditional encryption algorithms can not solve the problem well, since it is hard for data owners to manage their private keys, if they want to securely share their cloud data with others in a fine-grained manner. In this paper, we propose a fine-grained and heterogeneous proxy re-encryption (FH-PRE) system to protect the confidentiality of data owners’ cloud data. By applying the FH-PRE system in cloud, data owners’ cloud data can be securely stored in cloud and shared in a fine-grained manner. Moreover, the heterogeneity support makes our FH-PRE system more efficient than the previous work. Additionally, it provides the secure data sharing between two heterogeneous cloud systems, which are equipped with different cryptographic primitives.

Resource preprocessing and optimal task scheduling in cloud computing environments

SummaryCloud computing came into being and is currently an essential infrastructure of many commerce facilities. To achieve the promising potentials of cloud computing, effective and efficient scheduling algorithms are fundamentally important. However, conventional scheduling methodology encounters a number of challenges. During the tasks scheduling in cloud systems, how to make full use of resources and how to effectively select resources are also important factors. At the same time, communication delay also plays an important role in cloud scheduling, which not only leads to waiting between tasks but also results in much idle interval time between processing units. In this paper, a fuzzy clustering method is used to effectively preprocess the cloud resources. Combining the list scheduling with the task duplication scheduling scheme, a new directed acyclic graph based scheduling algorithm called earliest finish time duplication algorithm for heterogeneous cloud systems is presented. Earliest finish time duplication attempts to insert suitable immediate parent nodes of the current selected node in order to reduce its waiting time on the processor. The case study and experimental results illustrate that the algorithm proposed in this paper is better than the popular heterogeneous earliest finish time algorithms. Copyright © 2014 John Wiley & Sons, Ltd.

A green strategy for federated and heterogeneous clouds with communicating workloads.

Providers of cloud environments must tackle the challenge of configuring their system to provide maximal performance while minimizing the cost of resources used. However, at the same time, they must guarantee an SLA (service-level agreement) to the users. The SLA is usually associated with a certain level of QoS (quality of service). As response time is perhaps the most widely used QoS metric, it was also the one chosen in this work. This paper presents a green strategy (GS) model for heterogeneous cloud systems. We provide a solution for heterogeneous job-communicating tasks and heterogeneous VMs that make up the nodes of the cloud. In addition to guaranteeing the SLA, the main goal is to optimize energy savings. The solution results in an equation that must be solved by a solver with nonlinear capabilities. The results obtained from modelling the policies to be executed by a solver demonstrate the applicability of our proposal for saving energy and guaranteeing the SLA.