• Korean Management Science Review
• /
• v.19 no.1
• /
• pp.29-38
• /
• 2002

Due to the rapid increase In the Internet traffic volume, ISPs are faced with the definite need of the expansion of server capacity. In order to Provide prompt services for customers and still prevent excessive facility cost, it is critical to determine the optimum level of internet server capacity. The purpose of this Paper is to provide a simple but effective strategy on the expansion of servers capacity according to the increase in internet traffic. We model an internet server as an M/G/m/m queueing system and derive an efficient method to compute the loss probability which, In turn, Is used as a basis to determine proper server capacity. The Process of estimating the traffic parameter values at each server based on log data analysis is also given. All the procedures are numerically demonstrated through the process of analyzing actual log data collected from a game company.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.04a
• /
• pp.394-396
• /
• 2000

Currently, lots of research s going on in the field of the load distribution within HTTP. RR-DNS and SWEB are the most representative load distribution research. But, there are still many problems: unbalancing of load, load increase of web server and cost increase. Also, clients that require lots of data like multimedia happens to increase network load. To solve these, research about client/agent/server architecture is going on. But, the clients must know the agent's address and there are complexity and migration problems for design of such as protocol. This paper proposes TBSMS that is capable of choosing the optimal server considering the service capacity of the server as well as the network load. This paper demonstrates that TBSMS uses the web to solve the problem that client must know the agent's address and uses SNMP to solve the complexity and migration problem.

• Korean Management Science Review
• /
• v.17 no.2
• /
• pp.97-113
• /
• 2000

The introduction of client server systems raises some serious IS control concerns. Although client server systems increase system flexibility and compatibility, and facilitates system downsizing and process restructuring, multiple operating systems, database management systems, and platforms of client-server system increase th potential exposures and risks of the system. It is needed to recommend the effective control framework to mitigate risks. This paper suggests risks and control framework for client server system. The results of two case studies indicate that program and database management are important as program and data should be located and maintained in client and servers. It becomes difficult to manage divided programs and data logic that are distributed across clients and servers that have different platforms. The case studies of two banks show that the extent of distribution of program and data logic affects the importance of program and database management controls.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.26 no.3
• /
• pp.108-114
• /
• 2014

On a large scale of data center, heat generation rates from sever computers occupy almost the entire cooling load of the building, and it is gradually increasing. The efficiency of air distribution system in data centers can be affected by heat generation rates of server computers. In this study, the distributions of airflow and temperature in a data center have been investigated by CFD simulations under various conditions of heat generation rates for server computers. From the results, air around the cold aisle which has high temperature flows tremendously into the cold aisle according to the increase of heat generation rates for server computers and the air temperature in the cold aisle becomes higher. The SHI (supply heat index) and RHI (return temperature index) show almost similar values to the cases study because the air inflow rates to server computers increase with the heat generation rates of server computers.

• Journal of Information Processing Systems
• /
• v.6 no.4
• /
• pp.553-562
• /
• 2010

The core services in cloud computing environment are SaaS (Software as a Service), Paas (Platform as a Service) and IaaS (Infrastructure as a Service). Among these three core services server virtualization belongs to IaaS and is a service technology to reduce the server maintenance expenses. Normally, the primary purpose of sever virtualization is building and maintaining a new well functioning server rather than using several existing servers, and in improving the various system performances. Often times this presents an issue in that there might be a need to increase expenses in order to build a new server. This study intends to use grid service architecture for a form of server virtualization which utilizes the existing servers rather than introducing a new server. More specifically, the proposed system is to enhance system performance and to reduce the corresponding expenses, by adopting a scheduling algorithm among the distributed servers and the constituents for grid computing thereby supporting the server virtualization service. Furthermore, the proposed server virtualization system will minimize power management by adopting the sleep severs, the subsidized servers and the grid infrastructure. The power maintenance expenses for the sleep servers will be lowered by utilizing the ACPI (Advanced Configuration & Power Interface) standards with the purpose of overcoming the limits of server performance.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2012.10a
• /
• pp.793-796
• /
• 2012

Recently adoption of the Green IT is regarded as an essential element in order to decrease server heat and save energy in data center because of continuous increase of energy consumption and energy price. Consequently the conventional IT infrastructure is replaced with cloud computing platform. In this paper, we have implemented a Linux virtual server load balancing in open source-based cloud platform and the performance of the LVS load balancing is analyzed.

• Journal of Korea Game Society
• /
• v.9 no.2
• /
• pp.105-113
• /
• 2009

The most important service of the online game is the stability. However, in online games, the increase in the number of users burdens the server as thousands of users connect to the server at the same time. While various techniques to reduce the load on the server are studied, the study is limited only to the server part like an improvement of server algorithms. In this paper, a program to handle the largest load of the server, the message synchronization of both the server and client, is designed and implemented.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.6 no.4
• /
• pp.95-105
• /
• 2010

DNS(Domain Name System) is a huge distributed database that converts host name to IP address. We are expecting the importance of DNS is more increased because many Internet application services appear according to the continuous increase of Internet users and nearly all the Internet application services use DNS. To prevent the interruption of DNS service, DNS server is configured with primary DNS server and a secondary DNS server which takes the place of primary DNS server in case of the service interruption. But this scheme is difficult for providing DNS service constantly in case of DDoS attack, which brings about much network load or network problems in DNS server group. Therefore, This paper proposed the scheme to locally distribute load of DNS server, and the use of address system to group the distributed DNS servers. Also, it proposed the authentication scheme of the correspondent server in case the server is changed in DNS server group having grouping address. In this paper, it is shown that the prosed scheme guarantees the improved service reliability with maintaining the present service performance through the evaluation. Through this, we can expect the high improved DNS service can be provided in the Internet environment in the future.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.4
• /
• pp.79-85
• /
• 2013

In SIP(Session Initiation Protocol) environment, the presence server should process SIP SUBSCRIBE request messages including multiple presence resources addresses from users, and also precess massive notification messages from the subscribed presence resources. The load of the presence server increases as number of users increase, and it limits system extendability. Therefore a new multiple presence servers architecture has been suggested in this research. In this architecture presence servers can be added dynamically and each server's load can be controlled effectively as number of users increase. Each presence server can monitor current load status of entire presence system by using presence event notification package which newly has been suggested in this paper. When a particular presence server's load increases over predefined limit, the presence service processing is distributed by selecting a server which has the smallest load, or by generating a new server dynamically. In this system the overall load of the entire system can be controlled optimally and extendability of the system can be increased. For this purpose a new presence event notification package and presence information data format have been suggested. The performance of the proposed system has been evaluated by experiments. They shows 44.3% increase in SUBSCRIBE message processing time, and 43.1% increase in Notification message processing time.

• Journal of Korean Institute of Industrial Engineers
• /
• v.6 no.1
• /
• pp.1-7
• /
• 1980

An exact solution technique for M/M/s multi-server demanding queue is introduced, and a general form of the curves representing service rates of the system is presented. As the number of customers in the system increases, the service rate is shown to increase initially, then decrease, and finally converge to a certain value. It is also shown that this phenomenon persists regardless of the numbers of servers and customer types.