• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.3
• /
• pp.954-972
• /
• 2012

Content Delivery Networks (CDN) server loads that fluctuant necessitate CDN to improve its service scalability especially when the peak load exceeds its service capacity. The peer assisted scheme is widely used in improving CDN scalability. However, CDN operators do not want to lose profit by overusing it, which may lead to the CDN resource utilization reduced. Therefore, improving CDN scalability moderately and guarantying CDN resource utilization maximized is necessary. However, when and how to use the peer-assisted scheme to achieve such improvement remains a great challenge. In this paper, we propose a new method called Dynamic Moderate Peer-assisted Method (DMPM), which uses time series analysis to predict and decide when and how many server loads needs to offload. A novel peer-assisted mechanism based on the prediction designed, which can maximize the profit of the CDN operators without influencing scalability. Extensive evaluations based on an actual CDN load traces have shown the effectiveness of DMPM.

• The Journal of the Korea Contents Association
• /
• v.7 no.11
• /
• pp.69-75
• /
• 2007

In this paper, we propose a new distributed processing scheme to support MMORPG (Massively Multiplayer Online Role-Playing Games). But existing distributed game servers have some problems such as hotspot, congestion, server failure problems, and so on. To solve such problems, our proposed scheme begins by splitting the large virtual world into smaller regions, each region handled by a different server. We present a scheme that reduces the bandwidth requirements for both game servers and clients. Also our scheme allows seamless interaction among players residing on areas handled by different servers. We show an excellence of the proposed solution through various experiments.

• Journal of the Korea Society of Computer and Information
• /
• v.22 no.6
• /
• pp.17-24
• /
• 2017

In recent digital broadcasting, up to 250 channels are multiplexed and transmitted. The channel transmission is made in the form of MPEG-2 Transport Stream (TS) and transmits one channel (Video, Audio). In order to check if many broadcast channels are transmitted normally, in multi-channel multi-view system, ability of real-time monitoring is required. In order to monitor efficient multi-channel, a distributed system in which functions and load are distributed should be implemented. In the past, we used an inefficient system that gave all of the functionality to a piece of hardware, which limited the channel acceptance and required a lot of resources. In this paper, we implemented a distributed multi-view system which can reduce resources and monitor them economically through efficient function and load balancing. It is able to implement efficient system by taking charge of decoding, resizing and encoding function in specific server and viewer function in separate server. Through this system, the system was stabilized, the investment cost was reduced by 19.7%, and the wall monitor area was reduced by 52.6%. Experimental results show that efficient real-time channel monitoring for multi-channel digital broadcasting is possible.

• KIPS Transactions on Computer and Communication Systems
• /
• v.2 no.12
• /
• pp.569-576
• /
• 2013

Cloud computing has been receiving increasing attention recently. Despite this attention, security is the main problem that still needs to be addressed for cloud computing. In general, a cloud computing environment protects data by using distributed servers for data storage. When the amount of data is too high, however, different pieces of a secret key (if used) may be divided among hundreds of distributed servers. Thus, the management of a distributed server may be very difficult simply in terms of its authentication, encryption, and decryption processes, which incur vast overheads. In this paper, we proposed a efficiently data storage and recovery scheme using XOR and RAID in Hadoop environment.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.3
• /
• pp.911-931
• /
• 2021

Recently, most cloud services use Docker container environment to provide their services. However, there are no researches to evaluate the performance of communication libraries for multi-GPU based distributed deep learning in a Docker container environment. In this paper, we propose an efficient communication architecture for multi-GPU based deep learning in a Docker container environment by evaluating the performances of various communication libraries. We compare the performances of the parameter server architecture and the All-reduce architecture, which are typical distributed deep learning architectures. Further, we analyze the performances of two separate multi-GPU resource allocation policies - allocating a single GPU to each Docker container and allocating multiple GPUs to each Docker container. We also experiment with the scalability of collective communication by increasing the number of GPUs from one to four. Through experiments, we compare OpenMPI and MPICH, which are representative open source MPI libraries, and NCCL, which is NVIDIA's collective communication library for the multi-GPU setting. In the parameter server architecture, we show that using CUDA-aware OpenMPI with multi-GPU per Docker container environment reduces communication latency by up to 75%. Also, we show that using NCCL in All-reduce architecture reduces communication latency by up to 93% compared to other libraries.

• Journal of information and communication convergence engineering
• /
• v.21 no.4
• /
• pp.300-305
• /
• 2023

Audience reactions in response to remote virtual performances must be compressed before being transmitted to the server. The server, which aggregates these data for group insights, requires a distribution code for the transfer. Recently, distributed learning algorithms such as federated learning have gained attention as alternatives that satisfy both the information security and efficiency requirements. In distributed learning, no individual user has access to complete information, and the objective is to achieve a learning effect similar to that achieved with the entire information. It is therefore important to distribute interdependent information among users and subsequently aggregate this information following training. In this paper, we present a new extension technique for minimal code that allows a new minimal code with a different length and Hamming weight to be generated through the product of any vector and a given minimal code. Thus, the proposed technique can generate minimal codes with previously unknown parameters. We also present a scenario wherein these combined methods can be applied.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1995.10a
• /
• pp.885-888
• /
• 1995

Virtual Manufacturing System(VMS) is a computer model that represents the precise and whole structure of manufacturing system and simulates their physical and logical behavior in operation. In this paper, a real time simulation for the virtual factory is proposed to integrate a process planning with scheduling under distributed environments. In order to communicate the information under distributed environment, weuse a sever/client concept and socket program. the VMS is implemented on the internet environment.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2002.10a
• /
• pp.492-496
• /
• 2002

We present the web-based remote monitoring system using distributed object technology. In order to provide the desired functionality, the system has used CORBA(Common Object Request Architecture) and Java Servlet to implement the integrated distributed object environment. It converts the existing standalone machine monitoring system into web-based machine monitoring system. It consists of applet program, CORBA server and CORBA client. The usefulness of our system will be illustrated by the application to ICM(Integrated Condition Monitoring) System developed by KIST Tribology Center.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.4 no.1
• /
• pp.29-33
• /
• 2004

I propose a personalized digital library system (PDLS) based on an advanced distributed agent platform. The new platform is developed by improving the DECAF (Distributed Environment-Centered Agent Framework) which is one of the conventional distributed agent development toolkits. Also, a mobile ORB (Object Request Broker), Voyager, and a new multi agent negotiation algorithm are adopted to develop the advanced platform. The new platform is for mobile multi agents as well as the distributed environment, whereas the DECAF is for the distributed and non-mobile environment. From the results of the simulation the searched time of PDLS is lower, as the numbers of servers and agents are increased. And the user satisfaction is four times greater than the conventional client-server model. Therefore, the new platform has some optimality and higher performance in the distributed mobile environment.

• Journal of the Korea Computer Industry Society
• /
• v.3 no.8
• /
• pp.1019-1026
• /
• 2002

The Distributed system environments are developing into a structure of the opening information communication network based on object-oriented concepts and distributed technologies. Such a reason is that it can not only decrease the complexity of distributed softwares, but also support object oriented application services to distributed environments without changes of its own communication network structure. In this paper, we designed object group model, that is, an extended middleware, we developed before. The distributed environment suggested consists of the CTS server and clients. As our results, we showed the interaction procedures between/among object groups and service procedures of distributed application in given distributed system.