• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.11
• /
• pp.3603-3618
• /
• 2022

The offloading method is important when there are multiple mobile nodes and multiple edge servers. In the environment, those mobile nodes connect with edge servers with different bandwidths, thus taking different time and energy for offloading tasks. Considering the system load of edge servers and the attributes (the number of instructions, the size of files, deadlines, and so on) of tasks, the energy-aware offloading problem becomes difficult under our mobile edge environment (MCE). Most of the past work mainly offloads tasks by judging where the job consumes less energy. But sometimes, one task needs more energy because the preferred edge servers have been overloaded. Those methods always do not pay attention to the influence of the scheduling on the future tasks. In this paper, first, we try to execute the job locally when the job costs a lower energy consumption executed on the MD. We suppose that every task is submitted to the mobile server which has the highest bandwidth efficiency. Bandwidth efficiency is defined by the sending ratio, the receiving ratio, and their related power consumption. We sort the task in the descending order of the ratio between the energy consumption executed on the mobile server node and on the MD. Then, we give a "suffrage" definition for the energy consumption executed on different mobile servers for offloading tasks. The task selects the mobile server with the largest suffrage. Simulations show that our method reduces the execution time and the related energy consumption, while keeping a lower value in the number of uncompleted tasks.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.12 no.6
• /
• pp.547-553
• /
• 2019

Presence server should process massive SIP subscription request messages and massive presence event notifications from presence resources in real time. Therefore multiple servers architecture is needed for presence service system. In this paper, an architecture of multiple servers presence service system using SIP based CCMP control messages for lowering presence server load level has been presented. In this system, each presence server exchanges current load status using CCMP control messages, and total system load according to variance of users number and amount of presence resources has been effectively distributed processed. The CCMP control messages has been optimally designed to control presence servers, and exchange procedures of these control messages between presence servers has been also presented and the performance of the proposed multiple servers presence service system has been analysed by experiments. The result shows that average presence subscription processing time reduced from 40.8% to 69.2% and average presence notification processing time reduced from 29.4% to 62.7%.

• Journal of the Korea Society of Computer and Information
• /
• v.22 no.10
• /
• pp.101-107
• /
• 2017

In this paper, we study the problem of parallel machine scheduling considering the moving time of multiple servers. The parallel machine scheduling is to assign jobs to parallel machines so that the total completion time(makespan) is minimized. Each job has a setup phase, a processing phase and a removal phase. A processing phase is performed by a parallel machine alone while a setup phase and a removal phase are performed by both a server and a parallel machine simultaneously. A server is needed to move to a parallel machine for a setup phase and a removal phase. But previous researches have been done under the assumption that the server moving time is zero. In this study we have proposed an efficient algorithm for the problem of parallel machine scheduling considering multiple server moving time. We also have investigated experimentally how the number of servers and the server moving time affect the total completion time.

• Journal of the Korean Statistical Society
• /
• v.24 no.2
• /
• pp.389-405
• /
• 1995

Output processes emanating from exit arcs in a mulitple server open Jackson network with node i having $s_i$ servers are determined. Beutler and Melamed (1978) showed, for traffics on all exit arcs of single server open Jackson network in equilibrium, that the customer streams leaving any exit set are Poisson and that the collections over all nodes which yield the Poisson departure processes are mutually independent. In this paper we generalize the above results to multiple servers open Jackson network in equilibrium. While no weak limit result is possible under the equilibrium condition, nonetheless approximations to the distributions of maximum queue lengths for no feedback nodes in multiple servers open Jackson network are established.

• KEPCO Journal on Electric Power and Energy
• /
• v.7 no.2
• /
• pp.277-283
• /
• 2021

Power plant simulators have been used for operator training, control verification and engineering verification. In general, simulators can be used in the place where they are installed by only single user group at a time. Considering high cost of simulator development, a lot of available scenarios, the diversity of user level and accessibility based on users' work location, development of simulator system that can be used by multiple user groups regardless of location is required in order to enhance utilization of simulators. In this paper, the simulator system that can be used by multiple user group simultaneously without location limitation is proposed. The simulator system is composed of simulator servers, database servers, HMI servers, a web server, web clients. Simulator server consists of control model, process model that are developed for Circulating Fluidized Bed power plant located overseas. A web server manages user accounts, operation procedures, multiple server access between web client group and simulator server group. In other words, a web server makes a user group select a simulator server at a time. The developed simulator system is integrated after implementing process model, control model, HMI, and web server. Web client systems are installed on local site where power plant is located, while simulator servers, HMI servers, database servers, and a web server are located in KEPCO RI. The developed simulator system is verified by steady-state test, malfunction test and so on via remote access.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.7
• /
• pp.1335-1341
• /
• 2017

In this paper, a new architecture of multiple conference servers which use extended control channel framework in SIP(session initiation protocol) session has been presented. For this purpose, in this study, a new extended control channel framework architecture which can distribute total conference system loads to multiple servers effectively has been presented. In the implementation, extended control channels have been connected by using SIP sessions that was established between each conference servers, and extended control channel messages which can be transferred through control channels have been designed in this study. These extended control channel messages can distribute system load effectively between multiple conference servers, and conference information data format that can represent extended control channel framework has also been designed. Furthermore, exchange procedures of extended control channel messages have also been presented. The performance of the proposed system has been analysed by simulation. The analysis results show that average SIP messages delay time and average media stream delay time have improved.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.4
• /
• pp.123-128
• /
• 2019

In modern society, there are WEB sites that provides information in various fields by many advances in IT technology. As the number of users accessing the Web increases, one server becomes unavailable, and multiple servers are deployed to provide the service. In addition, systems that control servers are required to manage multiple servers. However, server control systems in the existing market are mostly those that notify managers through SMS and apps when a server's down or a controlled port is closed. However, in case of servers that generate a lot of traffic, the Web server and the WAS are operated and managed each independently. The WEB and WAS provide service by connecting to each other. However, the connection between WEB and WAS may be disconnected due to various environmental factors. In this case, the existing control system can not determine whether the service is working properly. Even in the case of WEB and WAS of a server that is operated independently, there is a phenomenon that the existing control system does not know the problem even when the normal service is not provided due to environmental factors such as disconnection to DB. In this paper, we implemented a system to check the normal state of Web service using Web crawling to solve this problem.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.12
• /
• pp.2252-2258
• /
• 2016

CCMP(centralized conferencing manipulation protocol) enables adding and removing conference participants, changing their roles, adding and removing media streams in conference system. In this paper, by using extended CCMP, a new distributed conference system architecture which can be used to multiple servers distributed conference system in SIP(session initiation protocol) environment has been presented. In this study, according to increasing number of participants, a new extended CCMP architecture which can distribute conference system loads to multiple servers dynamically to decrease loads of servers has been designed. This extended CCMP architecture also can add dynamically new servers from the prepared servers pool. Furthermore, new conference information data format which can represent extended CCMP has been designed, and exchange procedures of extended CCMP control messages which can distribute loads between servers have also been presented. The performance of the proposed system has been analysed by simulation.

• Journal of Convergence for Information Technology
• /
• v.10 no.6
• /
• pp.209-216
• /
• 2020

Protein antigens and their epitopes are targets for epitope based vaccines. There are many prediction servers which can be used for identification of binding peptides to MHC molecules. However, choosing of appropriate prediction servers is difficult. This study compared data obtained from prediction servers and evaluate them in scope of binding affinity to MHC-I molecules. Here we predicted HLA-A2-restricted cytotoxic T lymphocyte epitopes from survivin as a potential target for multiple myeloma. We suggest a procedure for prediction of antigenic peptides which could bind to MHC-I molecule. The results of this study will assist researchers in selection and prediction of noble antigenic peptides.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.5
• /
• pp.979-985
• /
• 2016

In this paper, a distributed instant message system with multiple servers architecture which can distribute system load effectively using an extended media control channel has been presented. A media control channel provides establishing a reliable control channel and also keeping a reliable control channel between SIP server and client in the field of real-time media transport area. In this study, a new instant message system architecture which can distribute massive instant message including multimedia data to multiple servers has been presented. The presented instant message system architecture can distribute system load by extending media control channel. For this purpose, media control channel messages, which distribute system load to multiple servers dynamically according to increasing number of users, have been designed in our presented system. And, in our research, an exchanging procedures of media control channel messages between servers have also been presented. The performance of the proposed system has been analysed by simulation.