• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.5
• /
• pp.49-54
• /
• 2022

With the recent widespread adoption of general-purpose GPUs (GPGPUs) in cloud systems, maximizing the resource utilization through multitasking in GPGPU has become an important issue. In this article, we show that resource allocation based on the workload classification of computing-bound and memory-bound is not sufficient with respect to resource utilization, and present a new thread block scheduling policy for GPGPU that makes use of fine-grained resource utilizations of each workload. Unlike previous approaches, the proposed policy reduces scheduling overhead by separating profiling and scheduling, and maximizes resource utilizations by co-locating workloads with different bottleneck resources. Through simulations under various virtual machine scenarios, we show that the proposed policy improves the GPGPU throughput by 130.6% on average and up to 161.4%.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.5
• /
• pp.1567-1587
• /
• 2014

Virtual Machine (VM) resource management is crucial to satisfy the Quality of Service (QoS) demands of various multimedia services in a media cloud platform. To this end, this paper presents a VM resource allocation model that dynamically and optimally utilizes VM resources to satisfy QoS requirements of media-rich cloud services or applications. It additionally maintains high system utilization by avoiding the over-provisioning of VM resources to services or applications. The objective is to 1) minimize the number of physical machines for cost reduction and energy saving; 2) control the processing delay of media services to improve response time; and 3) achieve load balancing or overall utilization of physical resources. The proposed VM allocation is mapped into the multidimensional bin-packing problem, which is NP-complete. To solve this problem, we have designed a Mixed Integer Linear Programming (MILP) model, as well as heuristics for quantitatively optimizing the VM allocation. The simulation results show that our scheme outperforms the existing VM allocation schemes in a media cloud environment, in terms of cost reduction, response time reduction and QoS guarantee.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.2
• /
• pp.312-334
• /
• 2023

In large-scale computing, cloud computing plays an important role by sharing globally-distributed resources. The evolution of cloud has taken place in the development of data centers and numerous servers across the globe. But the cloud information centers incur huge operational costs, consume high electricity and emit tons of dioxides. It is possible for the cloud suppliers to leverage their resources and decrease the consumption of energy through various methods such as dynamic consolidation of Virtual Machines (VMs), by keeping idle nodes in sleep mode and mistreatment of live migration. But the performance may get affected in case of harsh consolidation of VMs. So, it is a desired trait to have associate degree energy-performance exchange without compromising the quality of service while at the same time reducing the power consumption. This research article details a number of novel algorithms that dynamically consolidate the VMs in cloud information centers. The primary objective of the study is to leverage the computing resources to its best and reduce the energy consumption way behind the Service Level Agreement (SLA)drawbacks relevant to CPU load, RAM capacity and information measure. The proposed VM consolidation Algorithm (PVMCA) is contained of four algorithms: over loaded host detection algorithm, VM selection algorithm, VM placement algorithm, and under loading host detection algorithm. PVMCA is dynamic because it uses dynamic thresholds instead of static thresholds values, which makes it suggestion for real, unpredictable workloads common in cloud data centers. Also, the Algorithms are adaptive because it inevitably adjusts its behavior based on the studies of historical data of host resource utilization for any application with diverse workload patterns. Finally, the proposed algorithm is online because the algorithms are achieved run time and make an action in response to each request. The proposed algorithms' efficiency was validated through different simulations of extensive nature. The output analysis depicts the projected algorithms scaled back the energy consumption up to some considerable level besides ensuring proper SLA. On the basis of the project algorithms, the energy consumption got reduced by 22% while there was an improvement observed in SLA up to 80% compared to other benchmark algorithms.

• Journal of the Korean Wood Science and Technology
• /
• v.38 no.3
• /
• pp.199-204
• /
• 2010

Members used for the Korean traditional joints have been processed by handicraft, especially with domestic red pine species. Dovetail joint is most commonly used in woodworking joinery and traditional horizontal and vertical connections. It is able to be processed much easier to cut by handicraft and machines. However, although it is processed straight forwards, it requires a high degree of accuracy to ensure a snug fit. Also, tenons and mortises must fit together with no gap between them so that the joint interlocks tightly. A few scientific studies on the dovetail joints have been conducted so far. For the effective applications of traditional joints and domestic plantation wood species, dovetail joints were assembled by larch glulam members processed by machine pre-cut. To identify the tensile properties of through dovetail joints, larch glulam with 150 150mm in cross section were prepared. Furthermore, various geometric parameters of dovetai joints such as width, length, and tenon angle, were surveyed. The ends in the mortise was cracked mainly at a low strength level in the control specimens without reinforcements. The maximum tensile strengths of reinforced specimens considering real connections such as capital joint and headpiece on a column, increasedby handicraft, especially with domestic red pine species. Dovetail joint is most commonly used in woodworking joinery and traditional horizontal and vertical connections. It is able to be processed much easier to cut by handicraft and machines. However, although it is processed straight forwards, it requires a high degree of accuracy to ensure a snug fit. Also, tenons and mortises must fit together with no gap between them so that the joint interlocks tightly. A few scientific studies on the dovetail joints have been conducted so far. For the effective applications of traditional joints and domestic plantation wood species, dovetail joints were assembled by larch glulam members processed by machine pre-cut. To identify the tensile properties of through dovetail joints, larch glulam with 150 150mm in cross section were prepared. Furthermore, various geometric parameters of dovetai joints such as width, length, and tenon angle, were surveyed. The ends in the mortise was cracked mainly at a low strength level in the control specimens without reinforcements. The maximum tensile strengths of reinforced specimens considering real connections such as capital joint and headpiece on a column, increased by two times with shear failures on the tenon than the control specimens. The maximum tensile strength was obtained in the specimen of 25 degrees, and no difference was observed in the changes of neck widths.

• Journal of the Korean Wood Science and Technology
• /
• v.37 no.3
• /
• pp.184-191
• /
• 2009

In the southern part of the Korean Peninsula including Jeju-island, the production amount of domestic cedar has increased gradually. However, their low qualities, expected to be caused by the low density and frequent knots, have restricted their practical utilization as the high value-added products. In this study, it is aimed to look for the new uses of domestic cedar and to examine the applicability for lamination lumbers of structural glued laminated timber (glulam). Above all, machine stress ratings for individual sawn lumbers confirmed that modulus of elasticity (MOE) of cedar lumber was lower than that of other common softwood species in Korea. On the other hand, cedar lumbers have enough stiffness to manufacture the structural glulam in accordance with Korean Industrial Standard (KS). The bonding strength and durability also met the KS limitation. Nevertheless, from the result of bending tests for cedar glulam, it was shown that the modulus of elasticity (MOE) did not meet the KS limitation. Therefore, it was concluded that additional researches were needed for reinforcing the stiffness of cedar glulam.

• The Journal of the Korea Contents Association
• /
• v.20 no.6
• /
• pp.695-704
• /
• 2020

Recently, There has been an increasing of utilization IT, and studies have been conducted on predicting learning results. In this study, Learning activity data were collected that could affect learning outcomes by using learning analysis. The survey was conducted at a university in South Chung-Cheong Province from October to December 2018, with 1,062 students taking part in the survey. First, A Hierarchical regression analysis was conducted by organizing a model of individual, academic, and behavioral factors for learning results to ensure the validity of predictors in machine learning. The model of hierarchical regression was significant, and the explanatory power (R²) was shown to increase step by step, so the variables injected were appropriate. In addition, The linear regression analysis method of machine learning was used to determine how predictable learning outcomes are, and its error rate was collected at about 8.4%.

• Korean Chemical Engineering Research
• /
• v.58 no.4
• /
• pp.573-580
• /
• 2020

Hydrogen emerged as a sustainable transport energy source. To increase hydrogen utilization, hydrogen refueling stations must be available in many places. However, this requires large-scale financial investment. This paper proposed a methodology for selecting the optimal location to maximize the use of hydrogen charging stations. The location of gas stations and natural gas charging stations, which are competing energy sources, was first considered, and the expected charging demand of hydrogen cars was calculated by further reflecting data such as population, number of registered vehicles, etc. Using k-medoids clustering, one of the machine learning techniques, the optimal location of hydrogen charging stations to meet demand was calculated. The applicability of the proposed method was illustrated in a numerical case of Seoul. Data-based methods, such as this methodology, could contribute to constructing efficient hydrogen economic systems by increasing the speed of hydrogen distribution in the future.

• Journal of Internet Computing and Services
• /
• v.15 no.1
• /
• pp.103-112
• /
• 2014

In recent years, the rapid diffusion of smart devices and growth of internet usage and social media has led to a constant production of huge amount of valuable data set that includes personal information, buying patterns, location information and other things. IT and Production Infrastructure has also started to produce its own data with the vitalization of M2M (Machine-to-Machine) and IoT (Internet of Things). This analysis study researches the applicable effects of Structured and Unstructured Big Data in various business circumstances, and purposes to find out the value creation method for a corporation through the Structured and Unstructured Big Data case studies. The result demonstrates that corporations looking for the optimized big data utilization plan could maximize their creative values by utilizing Unstructured and Structured Big Data generated interior and exterior of corporations.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.05a
• /
• pp.325-328
• /
• 2013

Recently, the national carrier of the next-generation growth engine of M2M (machine to Machine) is attracting attention. Therefore, its uses and utilization of the various disciplines is getting wider, and the increasing number of terminals to be used compared to the existing communication of the information that is sent in every object may have increased. Each data transfer from the bulk terminal to a mobile network, if the traffic situation reaches this limit does not facilitate the processing of M2M communication services, this situation can occur. This study measures the mobile networks will be used in M2M communications when it reaches the breaking point for the smooth processing of M2M services are presented. Things grows increasingly smaller the further development of M2M technology, the explosion in mobile communication network, the data traffic will reach the limitations of these methods will be used in determining the ranking of the M2M communication services should be treated as a priority, to beM2M services to mobile networks will help to facilitate.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.3
• /
• pp.567-575
• /
• 2011

The two most popular virtual machine allocation schemes, both match making and round robin, do consider hardware specifications such as CPU, RAM, and HDD, but not CPU usage, which results in balanced resource distribution, but not in balanced resource usage. Thus, in this paper a new virtual machine allocation scheme considering current CPU usage rate is proposed while retaining even distribution of node resources. In order to evaluate the performance of the proposed scheme, a cloud computing platform composed of three cloud nodes and one front end is implemented. The proposed allocation scheme was compared with both match making and round robin schemes. Experimental results show that the proposed scheme performs better in even distribution of overall CPU usage, which results in efficient load balancing.