• 한국멀티미디어학회논문지
• /
• 제19권8호
• /
• pp.1487-1497
• /
• 2016

Explosively growing service of digital multimedia data increases the need for highly scalable low-cost storage. This paper proposes the new storage architecture based on torus network which does not need network switch and erasure coding for efficient storage usage for high scalability and efficient disk utilization. The proposed model has to compensate for the disadvantage of long network latency and network processing overhead of torus network. The proposed storage model was compared to two most popular distributed file system, GlusterFS and Ceph distributed file systems through a prototype implementation. The performance of prototype system shows outstanding results than erasure coding policy of two file systems and mostly even better results than replication policy of them.

• 한국통신학회논문지
• /
• 제25권8A호
• /
• pp.1177-1185
• /
• 2000

본 논문에서는 긴 전파 지연과 높은 에러율을 지닌 위성링크에 TCP를 사용하는 경우 나타나는 문제점을 도출하고 그에 대한 성능향상방안으로 ENA(Error Notification Ack) 알고리즘을 제안했다. TCP는 에러에 의한 세그먼트 손실과 Network Congestion에 의한 손실을 구분하지 못하고 두 경우 모두 Network Congestion 으로 판단한 후 Slow Start나 Congestion Aboidance 알고리즘을 적용시킨다 위성링크에서는 에러에 의한 세그먼트 손실이 자주 발생하는데 이손실을 Network Congestion에 의한 손실로 받아들여 매번 Congestion Control 알고리즘을 적용시킨다 그로인해 전송률을 줄어들고 성능은 급격히 떨어진다. 본 논문에서는 에러에 의한 손실과 Congestion 의한 손실을 구분해 주는 ENA 알고리즘을 제안하고 구현 방법 또한 제시하였다 그리고 ENA 알고리즘을 Tahoe, Reno. Sack TCP에 적용하여 성능의 변화를 비교 분석했다 그 결과 에러율이 높을수록 성능이 더 향상됨을 알수 있었다.

• 디지털융복합연구
• /
• 제6권4호
• /
• pp.137-145
• /
• 2008

Embedded industry has emerged as one of the important industry for u-IT based application service. Technology development related to embedded hardware and software provides the base for the development of U-IT convergence industry. This study intends to suggest a research model to investigate the influence of industry, organization, technology factors on technology performance in the embedded companies. This study adopted research variables such as global network, local network, industry intensity, and technology capability as independent variables, with technology performance as a dependent variable from the existing literatures. The purpose of this study is to analyze the influence of industrial and organizational factors on technology performance of embedded companies SCM systems, including the moderating effect of government support. 94 companies data were collected by survey. The result of this empirical study is summarized as follows. First, local network and technology capability are the important determinants to influence technology performance of embedded companies in direct effect model. Second, global network and industry intensity has more positive influence on technology performance of embedded companies through a moderating variable of government support.

• 가족자원경영과 정책
• /
• 제17권4호
• /
• pp.85-100
• /
• 2013

The purposes of this study are to explore the effect of the network characteristics of Healthy Family Support Center on its performance, and also to investigate the mediating effect of the organizational properties on the performance. We used the data from 148 healthy family support centers in National Survey in Korea. The analytic sample for this study consists of 102 responses.(response rate=68.9%) Multivariate regression model estimated the effects of the network's structural, interactive and functional characteristics and the interaction between the network's characteristics and organizational properties on the performance The findings of this study demonstrate that healthy family support centers with higher closeness centrality and with better functional characteristics reported more performances. Moreover, Centers that are more independent in organizational properties showed higher performances. However, the findings did not show that the interaction between the network's characteristics and organizational properties mediates on the performance.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제6권6호
• /
• pp.1668-1688
• /
• 2012

Cooperative communications and network coding schemes have been proposed to increase system throughput for ad hoc networks. In this paper, we present throughput and delay analysis of the new network coding-enabled cooperative MAC protocol called NC-MAC, which has been proposed by us in order to significantly enhance system performance. This protocol introduces an approach that can accommodate both cooperative communication and network coding for wireless ad hoc networks by slightly increasing overhead and modifying standards. The protocol's performance is evaluated using mathematical analysis and computer simulation and two performance measures, system throughput and average channel access delay, are used for a performance comparison with previous schemes. It is assumed that all the frames exchanged over a wireless channel are susceptible to transmission errors, which is a new but more reasonable assumption differentiating this research from previous research. Numerical results show this protocol provides significantly enhanced system performance compared with conventional cooperative MAC protocols used in previous research. For instance, system performance is 47% higher using the NC-MAC protocol than when using the rDCF protocol.

• International Journal of Advanced Culture Technology
• /
• 제11권3호
• /
• pp.310-314
• /
• 2023

The purpose of this study is to predict the remaining capacity of lithium-ion batteries and evaluate their performance using five artificial intelligence models, including linear regression analysis, decision tree, random forest, neural network, and ensemble model. We is in the study, measured Excel data from the CS2 lithium-ion battery was used, and the prediction accuracy of the model was measured using evaluation indicators such as mean square error, mean absolute error, coefficient of determination, and root mean square error. As a result of this study, the Root Mean Square Error(RMSE) of the linear regression model was 0.045, the decision tree model was 0.038, the random forest model was 0.034, the neural network model was 0.032, and the ensemble model was 0.030. The ensemble model had the best prediction performance, with the neural network model taking second place. The decision tree model and random forest model also performed quite well, and the linear regression model showed poor prediction performance compared to other models. Therefore, through this study, ensemble models and neural network models are most suitable for predicting the remaining capacity of lithium-ion batteries, and decision tree and random forest models also showed good performance. Linear regression models showed relatively poor predictive performance. Therefore, it was concluded that it is appropriate to prioritize ensemble models and neural network models in order to improve the efficiency of battery management and energy systems.

• 한국정보처리학회논문지
• /
• 제6권11S호
• /
• pp.3367-3378
• /
• 1999

ATM technology, which acts as a representative high-speed bandwidth technology, plays an important role in Internet environment. ATM network, supporting QoS(Quality of Service) and various traffic characters in high speed, configures many VPC(Virtual Path Connection)/VCC(Virtual Channel Connection). It is important to guarantee the QoS of each connection and it is necessary for the network manager to search element affecting the QoS of VPC/VCC and to control ATM network correctly. In the paper, the management information of VPC/VCC, that ATM network manager Using the fault notification for ATM switch, we can manage the configuration, fault and performance of ATM network. Thus, we extracted the configuration, fault and performance monitoring item from the ATM-MIB and SNMP M4 Network Element View MIB. And we designed the ATM network configuration, fault and performance management system based on the extracted item.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.180.3-180
• /
• 2001

In recent years, the remarkable development of communication network technology with the increasing demand of B-ISDN service helps the higg-speed ATM network to be applied a fully integrated global network. The considerable issue of high-speed communication network is a performance of service-link and stability of network queue. In this paper, we propose a feedback control algorithm and PID control method to improve the performance of service-link and stability of network queue and confirm upgraded traffic performance of the high-speed ATM network.

• 전자공학회논문지B
• /
• 제30B권5호
• /
• pp.120-128
• /
• 1993

In this paper, an implementation of high-speed parallel processing system for neural network design on the multicomputer network is presented. Linear speedup expandability is increased by reducing the synchronization penalty and the communication overhead. Also, we presented the parallel processing models and their performance evaluation models for each of the parallization methods of the neural network. The results of the experiments for the character recognition of the neural network bases on the proposed system show that the proposed approach has the higher linear speedup expandability than the other systems. The proposed parallel processing models and the performance evaluation models could be used effectively for the design and the performance estimation of the neural network on the multicomputer network.

• 전자공학회논문지S
• /
• 제34S권3호
• /
• pp.12-23
• /
• 1997

In this paper, we propose a new cell switch fabric for increasing the performance of ATM switching systems. Proposed switching network consists of a sorting network and a routing network. Both of these are multistage networks where each stage performs a fixed permutation on the incoming lines, and then routes them through a clumn of 2x2 switching elements. It is designed for distributing inputs and parallel processing to reduce the hardware complexity and obtain high performance of switching network. The structure and the operation of th eswitching network aredescribed and the performanceof the switching network is anlyzed under uniform traffic models. In this result, though the size of proposed network is increased the large scale, it has always the same throughput as the that of genral output queueing system with N=2. So, it is found that our proposed network is appropriate for the high apeed and lrger size of ATM switching systems.