• 대한산업공학회지
• /
• 제7권1호
• /
• pp.5-11
• /
• 1981

In the case of numerical implementation, the exact solution method for the M/M/s system where customers demand multiple server use [2] reveals limitations, if a system has large number of servers or types of customers. This is due to the huge matrices involved in the course of the calculations. This paper offers an approximation scheme for such cases. Capitalizing the characteristics of the service rate curve of the system, this method approximates the service rate as a piecewise linear function. With the service rates obtained from the linear function for each number of customers n (n=0. 1. 2,$\cdots$), ${\mu}(n)$, steady-state probabilities and measures of performance are found treating this system as an ordinary M/M/s system. This scheme performs well when the traffic intensity of a system is below about 0.8. Some numerical examples are presented.

• Journal of Information Processing Systems
• /
• 제9권3호
• /
• pp.489-498
• /
• 2013

In this paper, we propose a common simulation model that can be reused for different performance evaluations of networked virtual environments. To this end, we analyzed the common features of NVEs, in which multiple regions compose a shared space, and where a user has his/her own interest area. Communication architecture can be client-server or peer-server models. In usual simulations, users move around the world while the number of users varies with the system. Our model provides various simulation parameters to customize the region configuration and user movement pattern. Furthermore, our model introduces a way to mimic a lot of users in a minimal experiment environment. The proposed model is integrated with our network framework, which supports various scalability approaches. We specifically applied our model to the interest management and load distribution schemes to evaluate communication overhead. With the proposed simulation model, a new simulation can be easily designed in a large-scale environment.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제4권6호
• /
• pp.1237-1252
• /
• 2010

This paper proposes an intelligent technique for data sharing and event transition among personal devices including smart phones, laptops, and desktops. We implemented the PES (Personal Event Service) system that proactively executes appropriate tasks across multiple devices without explicit user requests by sharing the data used by the user and recognizing user intention based on the observed actions of the user for specific devices. The client module of PES installed on each device monitors the user actions and recognizes the intention of the user. The server provides data sharing and maintenance for clients. The connection between client and server is established by Java RMI (Remote Method Invocation). A series of experiments were performed to evaluate user satisfaction and system accuracy, and the results showed that the PES system can proactively provide appropriate, personalized services with a high degree of satisfaction to the user in an effective and efficient manner.

• 한국경영과학회지
• /
• 제31권1호
• /
• pp.1-13
• /
• 2006

In this paper we consider a design problem of a cyclic queueing network with two stages, each with a local buffer of limited capacity. Based on the theory of reversibility and product-form solution, we derive the throughput function of the network as a key performance measure to maximize. Two cases are considered. In case each stage consists of a single server, an optimal allocation policy of a given buffer capacity and work load between stages as well as the optimal number of customers is identified by exploiting the properties of the throughput function. In case each stage consists of multiple servers, the optimal policy developed for the single server case doesn't hold any more and an algorithm is developed to allocate with a small number of computations a given number of servers, buffer capacity as well as total work load and the total number of customers. The differences of the optimal policies between two cases and the implications of the results are also discussed. The results can be applied to support the design of certain manufacturing and computer/communication systems.

• 전자공학회논문지B
• /
• 제32B권11호
• /
• pp.1365-1373
• /
• 1995

In this paper, we address the issues related to storage and retrieval of continuous media (CM)data we face in designing multimedia on-demand (MOD) storage servers. To support the two orthogonal factors of MOD server design, i.e., storage and retrieval of CM data, this paper discusses the techniques of disk layout, disk striping and real-time disk scheduling, which are integrated as a combined solution to the high- performance MOD storage subsystem. The proposed clustered striping technique enables either a multiple-disk or a parallel system to guarantee a continuous retrieval of CM data at the bandwidth required to support user playback rate by avoiding the formation of I/O bottlenecks.

• 한국컴퓨터정보학회논문지
• /
• 제20권8호
• /
• pp.85-92
• /
• 2015

Due to the advancements in the capabilities of smart devices and home networks, we are able to easily access multimedia contents stored in a home server. In this paper, we present a wireless media content sharing mechanism for home networks that utilizes UPnP-based DLNA technology. We also present a novel Peer-to-Peer content sharing system that is able to operate on the client as well as server. Our system supports multiple push/pull services simultaneously via a multi-thread technique, and our intuitive user interface facilitates ease of use. Future studies would explore the feasibility of implementing our system in a multi-hop environment or providing a community-wide service.

• Journal of Information Processing Systems
• /
• 제17권2호
• /
• pp.227-241
• /
• 2021

Object detection techniques based on deep learning such as YOLO have high detection performance and precision in a single channel video stream. In order to expand to multiple channel object detection in real-time, however, high-performance hardware is required. In this paper, we propose a novel back-end server framework, a real-time AI vision platform (RAVIP), which can extend the object detection function from single channel to simultaneous multi-channels, which can work well even in low-end server hardware. RAVIP assembles appropriate component modules from the RODEM (real-time object detection module) Base to create per-channel instances for each channel, enabling efficient parallelization of object detection instances on limited hardware resources through continuous monitoring with respect to resource utilization. Through practical experiments, RAVIP shows that it is possible to optimize CPU, GPU, and memory utilization while performing object detection service in a multi-channel situation. In addition, it has been proven that RAVIP can provide object detection services with 25 FPS for all 16 channels at the same time.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2022년도 춘계학술발표대회
• /
• pp.45-47
• /
• 2022

Mobile edge computing (MEC), which enables mobile terminals to offload computational tasks to a server located at the user's edge, is considered an effective way to reduce the heavy computational burden and achieve efficient computational offloading. In this paper, we study a multi-user MEC system in which multiple user devices (UEs) can offload computation to the MEC server via a wireless channel. To solve the resource allocation and task offloading problem, we take the total cost of latency and energy consumption of all UEs as our optimization objective. To minimize the total cost of the considered MEC system, we propose an DRL-based method to solve the resource allocation problem in wireless MEC. Specifically, we propose a Asynchronous Advantage Actor-Critic (A3C)-based scheme. Asynchronous Advantage Actor-Critic (A3C) is applied to this framework and compared with DQN, and Double Q-Learning simulation results show that this scheme significantly reduces the total cost compared to other resource allocation schemes

• 한국멀티미디어학회논문지
• /
• 제21권10호
• /
• pp.1162-1170
• /
• 2018

This paper presents an augmented reality system for multiple users. The proposed system performs ar image-based pose estimation of users and pose of each user is shared with other uses via a network server. For camera-based pose estimation, we install multiple markers in a pre-determined space and select the marker with the best appearance. The marker is detected by corner point detection and for robust pose estimation. the marker's corner points are tracked by optical flow tracking algorithm. Experimental results show that the proposed system successfully provides an augmented reality application to multiple users even when users are rapidly moving and some of markers are occluded by users.

• 정보처리학회논문지A
• /
• 제12A권7호
• /
• pp.627-636
• /
• 2005

본 논문에서는 분산 VOD 서버의 내부 통신망에 발생하는 부하를 줄이기 위해 channel bonding 기반 M-VIA 및 인터벌 캐쉬를 적용하는 방법을 제안한다. 분산 VOD 서버의 각 노드는 클러스터상에 분산 저장된 비디오 데이터를 서버 내부 통신망을 사용하여 전송받아 사용자에게 제공한다. 이 때, 대량의 비디오 데이터가 서버 내부 통신망을 통하여 전송됨으로 서버 내부 통신망에 부하가 증가한다. 본 논문에서는 서버 내부 통신망의 부하를 감소시키기 위해서 두 가지 기법을 적용하였다. 첫째, channel bonding을 지원하는 M-VIA를 개발하여 Gigabit Ethernet기반 서버 내부 통신망에 적용하였다. M-VIA는 TCP/IP의 통신 오버헤드를 제거한 사용자 수준 통신 프로토콜로 통신에 소요되는 시간을 감소시켜준다. 이러한 M-VIA에 복수개의 네트워크 카드를 사용하여 통신이 가능하게 하는 channel bonding 기법을 적용함으로써 서버 내부 통신망 자체의 대역폭을 증가시켰다. 두번째, 인터벌 캐쉬 기법을 적용하여 원격 서버 노드에서 전송 받은 비디오 데이터를 지역 노드의 메인 메모리에 캐쉬함으로써, 서버 내부 통신망에 발생하는 통신량을 감소시켰다. 실험을 통하여 분산 VOD 서버의 성능을 측정하였으며, TCP/IP에 기반하고 인터벌 캐쉬를 지원하지 않는 기존의 분산 VOD 서버와 성능을 비교하였다. 실험결과, channel bonding 기반 M-VIA의 적용으로 약$20\%$의 성능 향상, 그리고 인터벌 캐쉬 기법을 적용하여 추가로 약 $10\%$의 성능 향상이 생겨 총 $30\%$의 성능 향상을 얻을 수 있었다.