Distributed cloud resources allocation for fair utilization using multi-objective bin packing algorithm

PurposeCloud computing services gained huge attention in recent years and many organizations started moving their business data traditional server to the cloud storage providers. However, increased data storage introduces challenges like inefficient usage of resources in the cloud storage, in order to meet the demands of users and maintain the service level agreement with the clients, the cloud server has to allocate the physical machine to the virtual machines as requested, but the random resource allocations procedures lead to inefficient utilization of resources.Design/methodology/approachThis thesis focuses on resource allocation for reasonable utilization of resources. The overall framework comprises of cloudlets, broker, cloud information system, virtual machines, virtual machine manager, and data center. Existing first fit and best fit algorithms consider the minimization of the number of bins but do not consider leftover bins.FindingsThe proposed algorithm effectively utilizes the resources compared to first, best and worst fit algorithms. The effect of this utilization efficiency can be seen in metrics where central processing unit (CPU), bandwidth (BW), random access memory (RAM) and power consumption outperformed very well than other algorithms by saving 15 kHz of CPU, 92.6kbps of BW, 6GB of RAM and saved 3kW of power compared to first and best fit algorithms.Originality/valueThe proposed multi-objective bin packing algorithm is better for packing VMs on physical servers in order to better utilize different parameters such as memory availability, CPU speed, power and bandwidth availability in the physical machine.

Resource clustering algorithm for cloud data centers

Recently, the virtual machine deployment algorithm uses physical machine less or consumes higher energy in data centers, resulting in declined service quality of cloud data centers or rising operational costs, which leads to a decrease in cloud service provider’s earnings finally. According to this situation, a resource clustering algorithm for cloud data centers is proposed. This algorithm systematically analyzes the cloud data center model and physical machine’s use ratio, establishes the dynamic resource clustering rules through k-means clustering algorithm, and deploys the virtual machines based on clustering results, so as to promote the use ratio of physical machine and bring down energy consumption in cloud data centers. The experimental results indicate that, regarding the compute-intensive virtual machines in cloud data centers, compared to contrast algorithm, the physical machine’s use ratio of this algorithm is improved by 12% on average, and its energy consumption in cloud data center is lowered by 15% on average. Regarding the general-purpose virtual machines in cloud data center, compared to contrast algorithm, the physical machine’s use ratio is improved by 14% on average, and its energy consumption in cloud data centers is lowered by 12% on average. Above results demonstrate that this method shows a good effect in the resource management of cloud data centers, which may provide reference to some extent.

A continental-scale evaluation of the calibration-free complementary relationship with physical, machine-learning, and land-surface models

The widespread negative correlation between the atmospheric vapor pressure deficit and soil moisture lends strong support to the complementary relationship (CR) of evapotranspiration. While it has showed outstanding performance in predicting actual evapotranspiration (ETa) over land surfaces, the calibration-free CR formulation has not been tested in the Australian continent dominantly under (semi-)arid climates. In this work, we comparatively evaluated its predictive performance with seven physical, machine-learning, and land surface models for the continent at a 0.5° × 0.5° grid resolution. Results showed that the calibration-free CR that forces a single parameter to everywhere produced considerable biases when comparing to water-balance ETa (ETwb). The CR method was unlikely to outperform the other physical, machine-learning, and land surface models, overrating ETa in (semi-)humid coastal areas for 2002–2012 while underestimating in arid inland locations. By calibrating the parameter against water-balance ETa independent of the simulation period, the CR method became able to outperform the other models in reproducing the spatial variation of the mean annual ETwb and the interannual variation of the continental means of ETwb. However, interannual the grid-scale variability and trends were captured unacceptably even after the calibration. The calibrated parameters for the CR method were significantly correlated with the mean net radiation, temperature, and wind speed, implying that (multi-)decadal climatic variability could diversify the optimal parameters for the CR method. The other physical, machine-learning, and land surface models provided a consistent indication with the prior global-scale assessments. We also argued that at least some surface information is necessary for the CR method to describe long-term hydrologic cycles at the grid scale.

Optimization of cloud load balancing using fitness function and duopoly theory

PurposeCurrent industrial scenario is largely dependent on cloud computing paradigms. On-demand services provided by cloud data centre are paid as per use. Hence, it is very important to make use of the allocated resources to the maximum. The resource utilization is highly dependent on the allocation of resources to the incoming request. The allocation of requests is done with respect to the physical machines present in the datacenter. While allocating the tasks to these physical machines, it needs to be allocated in such a way that no physical machine is underutilized or over loaded. To make sure of this, optimal load balancing is very important.Design/methodology/approachThe paper proposes an algorithm which makes use of the fitness functions and duopoly game theory to allocate the tasks to the physical machines which can handle the resource requirement of the incoming tasks. The major focus of the proposed work is to optimize the load balancing in a datacenter. When optimization happens, none of the physical machine is neither overloaded nor under-utilized, hence resulting in efficient utilization of the resources.FindingsThe performance of the proposed algorithm is compared with different existing load balancing algorithms such as round-robin load (RR) ant colony optimization (ACO), artificial bee colony (ABC) with respect to the selected parameters response time, virtual machine migrations, host shut down and energy consumption. All the four parameters gave a positive result when the algorithm is simulated.Originality/valueThe contribution of this paper is towards the domain of cloud load balancing. The paper is proposing a novel approach to optimize the cloud load balancing process. The results obtained show that response time, virtual machine migrations, host shut down and energy consumption are reduced in comparison to few of the existing algorithms selected for the study. The proposed algorithm based on the duopoly function and fitness function brings in an optimized performance compared to the four algorithms analysed.

Virtual Machine Placement in Cloud Computing: Challenges, Research Gaps, and Future

Cloud computing provides various types of services to users. The goal of virtual machine placement (VMP) is to map the best physical machine to a virtual machine. With the help of Virtual Machine Placement, we can reduce cost, maximize resource utilization, reduced energy consumption of data centers in cloud environments. The focus of Virtual Machine Placement is to saving of power, quality of service. In this paper, we have reviewed various placements techniques used in cloud computing. At last, we have also studied various challenges for virtual machine placement in cloud computing. The main motive of various types of Virtual Machine Placement algorithms have to reduced energy consumption and minimize cost by maximizing utilization of various resources in the cloud platform. For further study, the researcher should focus on these challenges for the best virtual machine placement in a cloud environment. In this paper, we critically examine the techniques, challenges, and research gaps in virtual placements in cotext with Cloud Computing. Cloud computing, placement of virtual machines becomes major problems. For finding the solution to the problem we can use the various virtual machine placement algorithms. The main motive is to reduce consumption of energy, maximum resource utilization, minimizing cost factors used for virtual to the physical machine mapping in the cloud environment. For selecting the best algorithm various optimization methods are used. With these different optimization methods, we can analyze different algorithms. There is a great scope of improvement in existing systems of virtual placements to make them more energy-efficient, more reliable, and fault-tolerant. Redundancy in cloud downloading can be made more intelligent and minimized for duplicate data while downloading and uploading.

Performance Evaluation of VM Placement Using Classical Bin Packing and Genetic Algorithm for Cloud Environment

In current era, the trend of cloud computing is increasing with every passing day due to one of its dominant service i.e. Infrastructure as a service (IAAS), which virtualizes the hardware by creating multiple instances of VMs on single physical machine. Virtualizing the hardware leads to the improvement of resource utilization but it also makes the system over utilized with inefficient performance. Therefore, these VMs need to be migrated to another physical machine using VM consolidation process in order to reduce the amount of host machines and to improve the performance of system. Thus, the idea of placing the virtual machines on some other hosts leads to the proposal of many new algorithms of VM placement. However, the reduced set of physical machines needs the lesser amount of power consumption therefore; in current work the authors have presented a decision making VM placement system based on genetic algorithm and compared it with three predefined VM placement techniques based on classical bin packing. This analysis contributes to better understand the effects of the placement strategies over the overall performance of cloud environment and how the use of genetic algorithm delivers the better results for VM placement than classical bin packing algorithms.

Workload prediction of cloud computing based on SVM and BP neural networks

In this study, support vector machine (SVM) and back-propagation (BP) neural networks were combined to predict the workload of cloud computing physical machine, so as to improve the work efficiency of physical machine and service quality of cloud computing. Then, the SVM and BP neural network was simulated and analyzed in MATLAB software and compared with SVM, BP and radial basis function (RBF) prediction models. The results showed that the average error of the SVM and BP based model was 0.670%, and the average error of SVM, BP and RBF was 0.781%, 0.759% and 0.708%, respectively; in the multi-step prediction, the prediction accuracy of SVM, BP, RBF and SVM + BP in the first step was 89.3%, 94.6%, 96.3% and 98.5%, respectively, the second step was 87.4%, 93.1%, 95.2% and 97.8%, respectively, the third step was 83.5%, 90.3%, 93.1% and 95.7%, the fourth step was 79.1%, 87.4%, 90.5% and 93.2%, respectively, the fifth step was 75.3%, 81.3%, 85.9% and 91.1% respectively, and the sixth step was 71.1%, 76.6%, 82.1% and 89.4%, respectively.