• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.3
• /
• pp.762-777
• /
• 2014

With the increasing usage of cloud applications such as MapReduce and social networking, the amount of data traffic in data center networks continues to grow. Moreover, these appli-cations follow the incast traffic pattern, where a large burst of traffic sent by a number of senders, accumulates simultaneously at the shallow-buffered data center switches. This causes severe packet losses. The currently deployed TCP is custom-tailored for the wide-area Internet. This causes cloud applications to suffer long completion times towing to the packet losses, and hence, results in a poor quality of service. An Explicit Congestion Notification (ECN)-based approach is an attractive solution that conservatively adjusts to the network congestion in advance. This legacy approach, however, lacks scalability in terms of the number of flows. In this paper, we reveal the primary cause of the scalability issue through analysis, and propose a new congestion-control algorithm called FaST. FaST employs a novel, virtual congestion window to conduct fine-grained congestion control that results in improved scalability. Fur-thermore, FaST is easy to deploy since it requires only a few software modifications at the server-side. Through ns-3 simulations, we show that FaST improves the scalability of data center networks compared with the existing approaches.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.5 no.4
• /
• pp.741-762
• /
• 2011

Recently, multicast routing protocols become increasingly important aspect in Mobile Ad hoc Networks (MANETs), as they effectively manage group communications. Meanwhile, multimedia and real-time applications are becoming essential need for users of MANET. Thus it is necessary to design efficient and effective Quality of Service (QoS) multicast routing strategies. In this paper, we address the scalability problem of multicast routing protocols to support QoS over MANETs. In particular, we introduce a Position-Based QoS Multicast Routing Protocol (PBQMRP). Basically, the protocol based on dividing the network area into virtual hexagonal cells. Then, the location information is exploited to perform efficient and scalable route discovery. In comparison with other existing QoS multicast routing protocols, PBQMRP incurs less control packets by eliminating network flooding behavior. Through simulation, the efficiency and scalability of PBQMRP are evaluated and compared with the well-known On-Demand Multicast Routing Protocol (ODMRP). Simulation results justify that our protocol has better performance, less control overhead and higher scalability.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.10
• /
• pp.975-979
• /
• 2010

Existing quality adaptation schemes are useful for improving network stability in a congested network, but these schemes do not guarantee the quality of experience on video streaming due to the frequent variations in playback quality for a streaming service. In this paper, we propose a network-adaptive quality adaptation scheme to guarantee the quality of experience on SVC(Scalable Video Coding) video streaming. The proposed scheme estimates the available bandwidth by bandwidth measurement scheme using media characteristic, and then smoothly adjusts the quality level of SVC video stream according to the estimated bandwidth. Through the simulation, we prove that our scheme guarantees the quality of experience for video streaming by minimizing quality variation.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2013.11a
• /
• pp.98-101
• /
• 2013

스마트폰과 스마트TV와 같은 다양한 콘텐츠 소비 단말들이 급속히 보급되는 최근의 IT환경에서는 콘텐츠 제작, 유통, 소비에 있어서 예전과는 다른 패러다임을 요구하게 되었다. 예를 들어 각기 다른 해상도, 연산량, 사용자환경 등의 다양한 조건들에 대한 고려가 중요한 문제로 부각되고 있다. 이를 해결하고자 단일 서비스 콘텐츠 패키지로 여러 단말들에게 적응적인 서비스를 제공하는 Scalable Application Description Language(SADL)에 기반한 스케일러블 어플리케이션 프레임워크가 제안되었다. 본 논문에서는 이러한 스케일러블 어플리케이션 프레임워크에서 적응형 서비스 콘텐츠를 쉽게 생산하고 패키징 할 수 있도록 이클립스 공개소스 플랫폼 기반의 저작도구를 제안 및 개발하였다. 개발한 저작도구는 유지 보수 및 확장성을 고려하여 모델-뷰-컨트롤러에 기반한 Graphical Editing Framework(GEF)를 이용했다. 제안하는 저작도구는 다양한 운영체제에서 작동하며, 유지보수 및 확장성이 우수하다. 또한 서비스 콘텐츠 개발을 위해 이클립스 플랫폼이 지원하는 다양한 플러그인 도구들을 그대로 활용 가능하다는 장점을 갖는다. 뿐만 아니라 본 저작도구는 기능의 추가적인 확장을 통해 홈 내 가상화 장치들을 위한 응용 프로그램 제작에도 활용할 수 있다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2012.07a
• /
• pp.352-355
• /
• 2012

최근 인터넷 및 디지털 방송 서비스 환경 변화에 따라 사용자에게 제공되는 디지털 콘텐츠가 기하급수적으로 증가하게 되었고, 스마트 TV, 스마트 패드, 스마트폰 등 디지털 콘텐츠를 이용할 수 있는 기기들이 다양화 되어지고 있다. 또한, 사용자가 디지털 콘텐츠를 수집하는 경로와 이용하는 환경도 다양해지고 있다. 하지만, 현재 사용자가 제공되어 지고 있는 디지털 콘텐츠들은 특정 단말 및 사용환경에 종속된 형태로 제작되어 서비스되어지고 있으며, 다양한 성능을 가지는 단말들의 특성과 디지털 콘텐츠를 이용하는 사용자의 사용환경에 최적화된 서비스를 제공하지 못하고 있는 실정이다. 이에, 본 논문에서는 단말의 특성 및 사용자 사용환경에 최적화된 서비스를 제공할 수 있는 스케일러블 데이터 서비스를 제공하기 위한 프레임워크 기술과 스케일러블 데이터 서비스를 기술하기 위한 언어인 SADL(Scalable Application Descript Language)를 소개하고, 사용자가 사용하는 단말 특성과 사용환경에 최적화된 서비스를 제공하기 위한 SADL기반 콘텐츠를 저작할 수 있는 저작도구를 제안한다.

• Journal of Communications and Networks
• /
• v.9 no.4
• /
• pp.428-437
• /
• 2007

Along with the development of network, more and more functions and services are required by users, while traditional network fails to support all of them. Although overlay is a good solution to some demands, using them in an efficient, scalable way is still a problem. This paper puts forward a framework on how to construct an efficient, scalable overlay mesh in real network. Main differences between other overlays and ours are that our overlay mesh processes some nice features including class-of-service(CoS) and traffic engineering(TE). It embeds the end-to-end optimal traffic control law which can distribute traffic in an optimal way. Then, an example is given for better understanding the framework. Particularly, besides good scalability, and failure recovery, it possesses other characteristics such as routing simplicity, self-organization, etc. In such an overlay mesh, an applicable source routing scheme called hierarchical source routing is used to transmit data packet based on UDP protocol. Finally, a guideline derived from a number of simulations is proposed on how to set various parameters in this overlay mesh, which makes the overlay more efficient.

• Journal of Digital Contents Society
• /
• v.19 no.2
• /
• pp.407-413
• /
• 2018

In this paper, we present a scalable data delivery infrastructure for such IoT computing environment where we need a common platform where data providers share their diverse sensing data and applications can easily access and receive such data from providers. For efficient data delivery, this paper proposes a new delivery path management technique that take advantage of diverse consumer QoS when building bandwidth-efficient delivery paths. We perform primitive experiments on the path construction and reconstruction which may be major overhead of the scalable infrastructure. The results show that the proposed infrastructure achieves a high level of scalability, and demonstrates that the management overhead is not significant.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.5
• /
• pp.2211-2232
• /
• 2018

The unstructured and semi-structured big data in social network poses new challenges in query retrieval. This requirement needs to be met by introducing quality retrieval time measures like indexing. Due to the huge volume of data storage, there originate the need for efficient index algorithms to promote query processing. However, conventional algorithms fail to index the huge amount of frequently obtained information in real time and fall short of providing scalable indexing service. In this paper, a new LIndex algorithm, which is a heuristic on Lucene is built on Neo4jHA architecture that holds the social network Big data. LIndex is a flexible and simplified adaptive indexing scheme that ascendancy decomposed shortest paths around term neighbors as basic indexing unit. This newfangled index proves to be effectual in query space pruning of graph database Neo4j, scalable in index construction and deployment. A graph query is processed and optimized beyond the traditional Lucene in a time-based manner to a more efficient path method in LIndex. This advanced algorithm significantly reduces query fetch without compromising the quality of results in time. The experiments are conducted to confirm the efficiency of the proposed query retrieval in Neo4j graph NoSQL database.

• Journal of Korea Multimedia Society
• /
• v.24 no.8
• /
• pp.1101-1113
• /
• 2021

The rapid growth of sense-and-respond applications and the emerging cloud computing model present a new challenge: providing publish/subscribe middleware as a scalable and elastic cloud service. The publish/subscribe interaction model is a promising solution for scalable data dissemination over wide-area networks. In addition, there have been some work on the publish/subscribe messaging paradigm that guarantees reliability and availability in the face of node and link failures. These publish/subscribe systems are commonly used in information-centric networks and edge-fog-cloud infrastructures for IoT. The IoT has an edge-fog cloud infrastructure to efficiently process massive amounts of sensing data collected from the surrounding environment. In this paper. we propose a quorum-based hierarchical fault-tolerant publish/subscribe systems (QHFPS) to enable reliable delivery of messages in the presence of link and node failures. The QHFPS efficiently distributes IoT messages to the publish/subscribe brokers in fog overlay layers on the basis of proposing extended stepped grid (xS-grid) quorum for providing tolerance when faced with node failures and network partitions. We evaluate the performance of QHFPS in three aspects: number of transmitted Pub/Sub messages, average subscription delay, and subscritpion delivery rate with an analytical model.

• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.232-239
• /
• 2009

Emerging social networking services provide a new paradigm for human-to-human communication. However, these services are centralized and managed by single service provider. In this paper, we propose MicroPost, a decentralized event notification service architecture for social applications based on publish/subscribe model. In our design space, event brokers are structured as an overlay network which provides the substrate of distributed peer-to-peer lookup service for storing and retrieving subscriptions with hashed keys. Event clients interact with event brokers to publish or subscribe social messages over the wide-area network. Using XML standards, we present an efficient algorithm to forward events for rendezvous-based matching in this paper. In our design space, the cost of routing is O(${\omega}log_kN$), where N is the number of event brokers, ${\omega}$ is the number of meta-data obtained from event messages, and k is a constant, which is selected by our design, to divide the identifier space and to conquer the lookup of given key. Consequently, what we achieved is an asynchronous social messaging service architecture which is decentralized, efficient, scalable, and flexible.