The complexity of high-performance computing (HPC) workflows is an important issue in the provision of HPC cloud services in most national supercomputing centers. This complexity problem is especially critical because it affects HPC resource scalability, management efficiency, and convenience of use. To solve this problem, while exploiting the advantage of bare-metal-level high performance, container-based cloud solutions have been developed. However, various problems still exist, such as an isolated environment between HPC and the cloud, security issues, and workload management issues. We propose an architecture that reduces this complexity by using Docker and Singularity, which are the container platforms most often used in the HPC cloud field. This HPC cloud architecture integrates both image management and job management, which are the two main elements of HPC cloud workflows. To evaluate the serviceability and performance of the proposed architecture, we developed and implemented a platform in an HPC cluster experiment. Experimental results indicated that the proposed HPC cloud architecture can reduce complexity to provide supercomputing resource scalability, high performance, user convenience, various HPC applications, and management efficiency.

Recently, cloud service providers have been gradually changing from virtual machine-based cloud infrastructures to container-based cloud-native infrastructures that consider performance and workload-management issues. Several data network performance issues for virtual instances have arisen, and various networking solutions have been newly developed or utilized. In this paper, we propose a solution suitable for a high-performance computing (HPC) cloud through a performance comparison analysis of container-based networking solutions. We constructed a supercomputer-based test-bed cluster to evaluate the serviceability by executing HPC jobs.

E-documents have been partially distributed. When it comes to the distribution of important documents such as contract and notice, however, paper or a particular system with enhanced security has only been available. This study proposes a distribution system which allows both companies and individuals to distribute e-documents in open environment through certified electronic address and circulation certificate and guarantees reliability through a trusted third party. The proposed distribution system can provide large-scale distribution services and keep them reliable. From the economic aspect, in addition, cost reduction, work efficiency and improvement of productivity are expected from individuals as well as public organizations and private companies.

Ponte Academic JournalDec 2017, Volume 73, Issue 12 AN INTEGRATED HOME ENERGY MANAGEMENT SYSTEMAuthor(s): Sang Boem Lim ,Guohua LiJ. Ponte - Dec 2017 - Volume 73 - Issue 12 doi: 10.21506/j.ponte.2017.12.53 Abstract:Nowadays, home network becomes applied to our daily life and most of new apartments include home network technology to save energy and provide comfortable service to users. However, there are still many old apartments have the economic reasons to build this system for users. In this paper, we intent to design economical integrated home energy management system for all kinds of apartments. We focus on implementing REST based sensing information collecting module, sending sensing information to cloud server module, controlling sensor module, sending/receiving sensing information module, monitoring sensing information, saving to database module. This integrated home energy management system will provide real-time monitoring and notification service so that can find the ways to save energy. Download full text:Check if you have access through your login credentials or your institution Username Password

Ponte Academic JournalApr 2017, Volume 73, Issue 4 DEVELOPMENT OF AN SDN-BASED AUTOMATIC INTRUSION DETECTION SYSTEM USING AN ONOS CONTROLLER Author(s): Sang Boem Lim ,Rongxu Xu, Guohua Li, Xinhua Jin, Nam-Gyu KimJ. Ponte - Apr 2017 - Volume 73 - Issue 4 doi: 10.21506/j.ponte.2017.4.46 Abstract:Existing hardware-centric network equipment cannot satisfy various user demands for the expansion of network resources. Many SDN (Software Define Network)-based controllers have been developed to address these limitations by using software to control these network resources flexibly. Among them, ONOS (Open Network Operating System) is one of the largest participating vendors capable of providing the operating functions of an OS. ONOS can be extended for applications by adding plug-ins developed by programmers. Although SDN is more convenient and efficient than traditional network management systems, several security vulnerabilities have been found. ONOS overcomes these problems by providing an ACL (Access Control List) application as a firewall against static network attacks. However, it is not sufficient for dynamic continuous intrusion detection. This paper presents the system we developed to provide automatic network intrusion detection and defense using an SDN-based ONOS controller. By adopting machine-learning algorithms, we expect to implement an automatic intrusion detection system for security of ONOS controller. Download full text:Check if you have access through your login credentials or your institution Username Password

Ponte Academic JournalDec 2016, Volume 72, Issue 12 IMPLEMENTATION AND PERFORMANCE ANALYSIS OF KVM-BASED GPU PASS-THROUGH FOR CLOUD DAASAuthor(s): Sang Boem Lim ,Guohua Li, Hyeyoung Cho, Jaegyoon HahmJ. Ponte - Dec 2016 - Volume 72 - Issue 12 doi: 10.21506/j.ponte.2016.12.13 Abstract:Desktop as a service (DaaS) is a cloud service that is hosted in the back-end of a virtual desktop infrastructure (VDI). Nowadays, increasing numbers of cloud users are on virtual desktops and most hypervisors support graphics virtualization. However, there are performance issues associated with rendering 3D games and other graphics rendering software on open source hypervisors such as kernel virtual machine (KVM) and Xen. To overcome these problems, we propose using GPU direct pass-through technology to enhance 3D rendering on KVM and to improve the graphics performance of its virtual machines (VMs). In this study, we compared GPU pass-through graphics performance with bare-metal system using two different types of GPU performance benchmark tools and analyzed the performance issues associated with cloud DaaS. The results obtained indicate that direct pass-through does not give the same performance as bare-metal but can be close, virtualization performance is dependent on the number of cores and vertices used, and the appropriate rendering API specific for the job at hand should be used for better performance. Download full text:Check if you have access through your login credentials or your institution Username Password

After the Fukushima nuclear accident, attention has been paid toward the construction and maintenance of nuclear power plants. A nuclear material spill originating from cracks in the nuclear plant's concrete structure due to natural disasters such as earthquakes or inappropriate planning and construction will have harmful consequences. There are ongoing studies for developing technologies to predict cracking in a structure when said structure is harmed by unexpected damages. This paper deals with studies on a ubiquitous crack detection and analysis system that is a combination of the extended finite element method (X-FEM) and ubiquitous sensor network (USN) technologies and can respond quickly when a nuclear plant is damaged. Because X-FEM is a considerably developed analysis technology, its use allows for relatively accurate crack analysis. Thus, the combined ability of real-time damage reporting using USN and data-based estimation of the scale of damage through crack analysis is expected to be useful for reducing damages due to unpredicted calamities.

Ponte Academic JournalNov 2016, Volume 72, Issue 11 DESIGN OF RESEARCH-SPECIFIC CLOUD SYSTEM FOR HIGH-PERFORMANCE COMPUTING OVER CLOUD SERVICEAuthor(s): Sang Boem Lim ,Guohua Li, Xinhua Jin, Rongxu XuJ. Ponte - Nov 2016 - Volume 72 - Issue 11 doi: 10.21506/j.ponte.2016.11.16 Abstract:Traditional high-performance computing (HPC) services for scientific applications offer high performance and advantages such as large-scale task execution, concurrency, load balancing, and system utilization. However, they fail to provide any scalability due to their inflexible architectures. Therefore, to provide scalability as well as cloud advantages, “HPC over Cloud services” has become a major area of interest in the field of HPC research. To provide a HPC over Cloud service, any of three representative base architectures can be adopted. These are bare metal (BM)-based, container-based, and virtual machine (VM)-based. The results of a study which compared these three base architectures indicated that the container- and BM-based architectures offer almost the same levels of performance. In this study, we set out to design a research-specific cloud system for HPC over Cloud service. As part of our efforts, we build a test-bed system which provides a real container-based HPC over Cloud service for evaluation. The results of our experiments indicate that the proposed system architecture for a container-based HPC over Cloud service can be successfully adopted for practical applications. Download full text:Check if you have access through your login credentials or your institution Username Password

The rise of densely populated societies in metropolitan areas has led to several forms of pollution, thereby leading to increasing health concerns. Among the various types of pollution, air pollution has become a crucial factor in the quality of life. Currently, the meteorological administration in Korea provides a regional scale of air quality index. However, this broad-based information is not relevant to local urban areas. We believe that air quality information about local environments such as homes, workplaces, and parks would be more relevant to people. We have developed a micro-scale air quality monitoring system called AirScope that covers local environments using a ubiquitous air quality sensor network. In this study, we focus on the applications of AirScope. We have developed AirScope as a general-purpose desktop PC application as well as a mobile application that can increase user mobility and provide real-time air quality information about the local user environment.

Air pollution threatens our health and exacerbates respiratory diseases such as bronchitis and asthma; therefore, many researchers and organizations are interested in the study of air pollution and emissions. In this paper, we will discuss a data management system for a micro-scale urban air quality management system. Using small sensors, this system automatically senses temperature, humidity, air pressure, dust, and so on. Then, we will discuss the possibility of allowing for the integration of data applications with metadata management systems. We will also describe the design procedure for the sensor information using SensorML.

We have been developing AirScope, an event-based air quality monitoring system, since 2008 and regularly add new features to it. The first version of AirScope is up and running on desktop and mobile platforms; however, it is limited in its capability to assimilate new sensors and components from other parties. In order to add third party components, extensive manual integration is required. In this paper, we propose using Enterprise Service Bus (ESB) as AirScope’s data communication and exchange channel. ESB is a centralized, logical, architectural component that operates in a distributed, heterogeneous environment to facilitate the requirements of a highly scalable, faulttolerant, service-messaging framework. ESB also secures delivery of messages by enforcing authentication, authorization, nonrepudiation, and confidentiality.

Air pollution threatens our health with respiratory diseases, such as bronchitis and asthma; therefore, many people are concerned about air quality. Air pollution is also blamed for global warming; therefore, many researchers and organizations are interested in studying the link between global warming and air pollution. Every day, we commute using buses, automobiles, subways, and other forms of transportation. These vehicles are a significant cause of air pollution. Therefore, we need to be able to determine the emission rates in certain areas. In this paper, we discuss the Distributed Emission Monitoring System and Emission Data Management System. We automatically detect the volume, type, and speed of a vehicle using a camera equipped with this system. We estimate and analyze emission rates based on the information, and the results will be provided via the portal website. Because many sensors are used in the studies about global warming and air pollution, we will explain the dynamic extension of sensors and the Metadata Management System that controls data for reuse in various applications.

A new concept of CFD-based virtual sensor data was implemented in a micro-scale air quality management system. This new concept is expected to bridging gaps between present and future USN application. In addition to the VS implementation, air quality data management and multi-modal scientific visualization module are discussed in the paper.

Residents of urban areas are becoming increasingly concerned about air quality, especially that in indoor environment, such as the subway. The subway is the most important and most widely used public transportation system in the crowded Seoul Metropolitan Area. Seoul Metro tries to maintain subway air quality using single-purpose systems such as an environment monitoring system and a facility management system. However, since these systems are not interconnected, it is difficult to have an overall picture of the entire system and manage air quality efficiently. In order to monitor and control subway air quality using integrated data, we propose an integrated management system called AirCleaner. In conducting this research, we are actively cooperating with Seoul Metro, which provides system requirements, and with related companies. To make our system more robust, we used proven commercial solutions.

AirScope is a micro‐scale modeling system as well as a micro‐scale air quality monitoring system, which comprises as a micro‐scale air quality management system. Importance of micro‐scale air monitoring is rising due to the concern about environment near residential places. Traditional monitoring methods are providing overall air quality indexes. However, these methods have limited functionalities to provide air quality of near my house or where I am now. In this paper, we are trying to overcome the limitation of traditional methods by using ubiquitous sensor network (USN). AirScope consists of computational fluid dynamics based air quality modeling, USN‐based sensor monitoring, and multi‐modal interaction platform. We present a brief overview of AirScope and several aspects of constructed initial indoor test environment with a few validity tests. The proposed system will be extended to an outdoor real‐world testbed with most of modern urban elements. Copyright © 2011 John Wiley & Sons, Ltd.

In this paper, we present a novel approach to micro-scale air quality monitoring for urban areas. This approach is based on two major technologies: wireless sensor networks (WSN) and service-oriented architecture (SOA). We discuss technical issues such as architectural designs, system integration, and user interfaces. We present a prototype system developed for the Konkuk University which uses an Enterprise Service Bus (ESB) system called ServiceMix.