• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제3권5호
• /
• pp.444-460
• /
• 2009

In this paper, we propose an expanded patching technique in order to reduce the server network bandwidth requirements to support true VoD services in VoD Systems. Double Patching, which is a typical multicast technique, ensures that a long patching stream delivers not only essential video data for the current client but also extra video data for future clients. Since the extra data may include useless data, it results in server network bandwidth wastage. In order to prevent a server from transmitting useless data, the proposed patching technique uses a new kind of stream called a linking stream. A linking stream is transmitted to clients that have received short patching streams, and it plays a linking role between a patching stream and a regular stream. The linking stream enables a server to avoid transmitting unnecessary data delivered by a long patching stream in Double Patching, so the server never wastes its network bandwidth. Mathematical analysis shows that the proposed technique requires less server network bandwidth to support true VoD services than Double Patching. Moreover, simulation results show that it has better average service latency and client defection rate compared with Double Patching.

• Journal of Communications and Networks
• /
• 제12권1호
• /
• pp.52-66
• /
• 2010

Since large objects consume substantial resources, web proxy caching incurs a fundamental trade-off between performance (i.e., hit-ratio and latency) and overhead (i.e., resource usage), in terms of caching and relaying large objects to users. This paper investigates how and to what extent the current dedicated-server based web proxy caching scheme is affected by large file transfers in a high bandwidth campus network environment. We use a series of trace-based performance analyses and profiling of various resource components in our experimental squid proxy cache server. Large file transfers often overwhelm our cache server. This causes a bottleneck in a web network, by saturating the network bandwidth of the cache server. Due to the requests for large objects, response times required for delivery of concurrently requested small objects increase, by a factor as high as a few million, in the worst cases. We argue that this cache bandwidth bottleneck problem is due to the fundamental limitations of the current centralized web proxy caching model that scales poorly when there are a limited amount of dedicated resources. This is a serious threat to the viability of the current web proxy caching model, particularly in a high bandwidth access network, since it leads to sporadic disconnections of the downstream access network from the global web network. We propose a peer-to-peer cooperative web caching scheme to address the cache bandwidth bottleneck problem. We show that it performs the task of caching and delivery of large objects in an efficient and cost-effective manner, without generating significant overheads for participating peers.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권4호
• /
• pp.784-799
• /
• 2013

This paper presents an adaptive rate control scheme for streaming-based content sharing service. This scheme delivers multimedia contents from a user device to another device or seamlessly redirects streaming service across heterogeneous user devices. In the proposed scheme, a streaming server adjusts video quality level according to the network and client status. Our scheme is different from other rate control schemes, because the video quality at the server is decided not only based on the available bandwidth, but also based on the device characteristics and bandwidth requirement at the access network. We also propose a bandwidth estimation method to achieve more equitable bandwidth allocations among streaming flows competing for the same narrow link with different Round Trip Times (RTTs). Through the simulation, we prove that our scheme improves the network stability and the quality of streaming service by appropriately adjusting the quality of the video stream. The simulation results also demonstrate the ability of the proposed scheme in ensuring RTT-fairness while remaining throughput efficient.

• 한국인터넷방송통신학회논문지
• /
• 제13권4호
• /
• pp.29-37
• /
• 2013

전형적으로 멀티플레이어 게임은 클라이언트-서버 구조 혹은 peer-to-peer 구조를 기반으로 구성된다. 클라이언트-서버 구조는 플레이어의 수가 증가할 때 서버에서 대역폭 요건이 커지기 때문에 규모조정이 어렵다. 반면 peer-to-peer 구조는 각 플레이어마다 자신의 상태와 다른 모든 플레이어들의 상태 간의 일관성을 점검해야 하기 때문에 상당한 오버헤드가 수반된다. 본 논문에서는 두 구조의 장점을 결합하는 기법을 제시한다. 이 기법에서는 플레이어들이 우선순위가 낮은 갱신 작업은 peer-to-peer 방식으로 상호 교환하며 우선순위가 높은 갱신 작업에 대해서는 중앙 서버와 직접 통신하게 된다. 결과적으로 제시된 기법은 클라이언트-서버 구조 보다 통신 부하 요건이 감소되며 서버의 대역폭 병목 현상도 제거된다. 멀티플레이어 게임의 다른 중요한 사항인 플레이어 간의 상태 일관성도 이 기법에서 항상 정확히 유지된다. 제시된 기법의 성능은 분석과 다양한 실험을 통하여 평가되었다.

• International Journal of Advanced Culture Technology
• /
• 제2권1호
• /
• pp.14-19
• /
• 2014

In this paper, we propose a stream based patching technique in order to reduce demands of network output bandwidth required to provide the true video-on-demand (VoD) service in a Multimedia server. The proposed scheme calculates required streams to clients accurately by analyzing temporal relationships between already arrived requests in a multimedia server and still progressing streams, and then transmits streams freshly. Since our stream based patching technique induces new linking stream which is playing a link role between long and short patching streams, it reduces demand of network output bandwidth required to provide the true VoD service in a multimedia server. Accordingly, we know that the proposed scheme improves service latency and defection rate than those of existing patching technique by a simulation study.

• ETRI Journal
• /
• 제35권2호
• /
• pp.234-244
• /
• 2013

Internet protocol television (IPTV) service depends on the network quality of service (QoS) and bandwidth of the broadband service provider. IEEE 802.16j mobile multihop relay Worldwide Interoperability for Microwave Access networks have the opportunity to offer high bandwidth capacity by introducing relay stations. However, to actually satisfy QoS requirements for offering IPTV services (HDTV, SDTV, Web TV, and mobile TV) for heterogeneous users' requests, providers must use a video server for each IPTV service type, which increases the network load, especially bandwidth consumption and forwarding time. In this paper, we present a solution for forwarding IPTV video streaming to diverse subscribers via an 802.16j broadband wireless access network. In particular, we propose a new multicast tree construction and aggregation mechanism based on the unique property of prime numbers. Performance evaluation results show that the proposed scheme reduces both bandwidth consumption and forwarding time.

• 한국정보처리학회논문지
• /
• 제7권2S호
• /
• pp.577-593
• /
• 2000

A distributed video-on-demand (VoD) system is one where collection of video data is located at dispersed sites across a computer network. In a single site environment, a local video server retrieves video data from its local storage device. However, in the setting of a distributed VoD system, when a customer requests a movie from the local server, the server may need to interact with other servers located across the network. In this paper, we present three types of presentation plans that a local server must construct in order to satisfy the customer request. Informally speaking, a presentation plan is a temporally synchronized detailed sequence of steps that the local server must perform for presenting the requested movie to the customer. This involves obtaining commitments from other video servers, obtaining commitments from the network service provider, as well as making commitments of local resources, within the limitations of available bandwidth, available buffer, and customer data consumption rates. Furthermore, for evaluating the goodness of a presentation plan, we introduce two measures of optimality for presentation plans: minimizing wait time for a customer, and minimizing access bandwidth is used. We develop algorithms to compute optimal presentation plans for all three types, and carry out extensive experiments to compare their performance. We have also mathematically proved certain results for the presentation plans that had previously been verified experimentally in the literature.

• 한국컴퓨터정보학회논문지
• /
• 제20권4호
• /
• pp.87-93
• /
• 2015

최근에 사용자 스스로가 네트워크를 구축하여 자신이 소유한 AP의 일부 대역폭을 다른 사람과 공유하는 방법이 대두되었는데 이러한 네트워크를 공유 네트워크라 한다. 응용 애플리케이션으로 공유 네트워크에서 SVC 기술을 사용하는 비디오 스트리밍 전송 시스템을 구축하는 방안이 제안되었는데, 서버로부터 클라이언트에게 비디오 스트림을 보내기 위해서는 루트는 서버이고 내부노드는 공유 AP이며 리프는 클라이언트인 트리 구조를 만들게 된다. 기존의 연구들은 공유 AP의 공유대역폭의 합을 최소로 사용해서 모든 클라이언트를 서비스하는 최소 공유대역폭 트리를 구축하는데 주안점을 두고 있다. 본 논문에서는 공유 AP들의 집합이 주어졌을 때 클라이언트의 비디오 스트림 요구를 최대로 만족시키는 최대 요구대역폭 트리를 구축하는 문제가 NP-하드임을 증명하였다. 또 이 문제를 해결하기 위한 효율적인 휴리스틱 알고리즘을 개발하고, 실험을 통해 성능을 평가하였다.

• 정보처리학회논문지C
• /
• 제16C권4호
• /
• pp.487-494
• /
• 2009

VOD(Video On Demand) 시스템은 실시간으로 사용자의 요구를 받아들여 동영상 서비스를 제공하는 시스템으로서 크게 서비스를 제공하는 서버와 사용자의 요구를 처리하는 클라이언트로 구성된다. 하나의 서버에서 다수의 사용자에게 1:1로 서비스를 제공하기에는 네트워크 대역폭의 제약이 크기 때문에 이를 해결하기 위한 다양한 연구들이 진행되어왔다. 그 동안 제안된 다양한 멀티캐스트 기반의 VOD시스템들 중에서 Batching방식의 VOD시스템이 단순하면서 네트워크 부하가 적은 것으로 알려져 있다. 하지만 Batching방식에 의한 VOD시스템에서는 VCR(Video Cassette Recorder)기능을 제공하기 어렵기 때문에 VOD시스템의 On-Demand 특성을 제대로 제공하지 못하는 단점이 있다. 본 논문에서는 대표적인 동영상 압축표준인 MPEG의 특성을 이용하여 VCR기능을 제공하기 위해 필요한 대역폭을 최소화하는 기법을 제안한다. 제안하는 기법에서는 MPEG로 압축된 동영상에서 독립적 재생이 가능한 I픽쳐만 추출하여 빠른 재생을 위한 데이터를 별도로 구성한다. 이렇게 구성된 빠른 재생을 위한 데이터와 일반적인 재생을 위한 데이터 모두 Batching방식으로 멀티캐스팅으로 전송한다. 성능분석을 통하여 제안된 기법을 사용할 경우 클라이언트의 버퍼요구량과 네트워크 사용량을 줄이고 이와 더불어 CPU사용량도 줄어드는 것을 확인하였다.

• 디지털산업정보학회논문지
• /
• 제10권3호
• /
• pp.171-179
• /
• 2014

Among the P2P based multimedia streaming architecture, multiple chain architecture has advantage in adapting to dynamically changing network topology simply and rapidly, so this architecture is used for UCC broadcasting system. In UCC broadcasting system, general peer involved in DSLAM becomes UCC server rather than broadcasting system that transfers data from ISP servers. Therefore UCC data generated from UCC server peers is transmitted to peers through DSLAM, and this transmission uses uplink bandwidth of DSLAM. In this paper, I propose an efficient management method of DSLAM uplink bandwidths through negotiating tracker and UCC server peer or head peers of DSLAM. I propose the method that tracker restricts a bitrate of uplink stream of UCC servers when used uplink bandwidth of DSLAM exceeds a certain point of maximum uplink bandwidths. I will show the improved performance of proposed scheme rather than general method with respect to the uplink bandwidth of DSLAM by numerical analysis and simulation.